Chunyan Miao

AAAI Conference 2026 Conference Paper

Adaptive Piecewise Distillation for Efficient LiDAR Data Generation

• Ruibo Li
• Xiaofeng Yang
• Ze Yang
• Jiacheng Wei
• Chunyan Miao
• Guosheng Lin

LiDAR data generation has emerged as a promising solution to the high cost and limited scalability of real-world LiDAR sensing. Recent diffusion and rectified flow models have demonstrated strong capabilities in synthesizing realistic 3D point clouds; however, their iterative sampling procedures result in significant inference overhead. To address this, we focus on efficient few-step LiDAR generation for both unconditional and multi-modal conditional settings. Specifically, we propose an adaptive piecewise distillation strategy tailored for rectified flow-based LiDAR generation models, where the teacher model’s flow trajectory is adaptively segmented into consecutive intervals, and the student is trained only at the start of each interval to directly predict the velocity toward its endpoint. By sequentially sampling at the start timestep of each interval, our method enables fast few-step generation. Moreover, instead of uniform partitioning, we introduce an adaptive timestep selection strategy that chooses interval boundaries with minimal initial error, thereby reducing the complexity of distillation. Experimental results show that our method achieves comparable or superior performance to state-of-the-art methods in both unconditional and multi-modal conditional LiDAR generation, using only four sampling steps.

IJCAI Conference 2025 Conference Paper

A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning

• Xuejiao Zhao
• Siyan Liu
• Su-Yin Yang
• Chunyan Miao

Misdiagnosis causes significant harm to healthcare systems worldwide, leading to increased costs and patient risks. MedRAG is a smart multimodal healthcare copilot equipped with powerful large language model (LLM) reasoning, designed to enhance medical decision-making. It supports multiple input modalities, including non-intrusive voice monitoring, general medical queries, and electronic health records. MedRAG provides recommendations on diagnosis, treatment, medication, and follow-up questioning. Leveraging retrieval-augmented generation enhanced by knowledge graph-elicited reasoning, MedRAG retrieves and integrates critical diagnostic insights, reducing the risk of misdiagnosis. It has been evaluated on both public and private datasets, outperforming existing models and offering more specific and accurate healthcare assistance. A demonstration video of MedRAG is available at: https: //www. youtube. com/watch? v=PNIBDMYRfDM. The source code is available at: https: //github. com/SNOWTEAM2023/MedRAG.

AAAI Conference 2025 Conference Paper

Bites of Tomorrow: Personalized Recommendations for a Healthier and Greener Plate

• Jiazheng Jing
• Yinan Zhang
• Chunyan Miao

The recent emergence of extreme climate events has significantly raised awareness about sustainable living. In addition to developing energy-saving materials and technologies, existing research mainly relies on traditional methods that encourage behavioral shifts towards sustainability, which can be overly demanding or only passively engaging. In this work, we propose to employ recommendation systems to actively nudge users toward more sustainable choices. We introduce Green Recommender Aligned with Personalized Eating (GRAPE), which is designed to prioritize and recommend sustainable food options that align with users’ evolving preferences. We also design two innovative Green Loss functions that cater to green indicators with either uniform or differentiated priorities, thereby enhancing adaptability across a range of scenarios. Extensive experiments on a real-world dataset demonstrate the effectiveness of our GRAPE.

NeurIPS Conference 2025 Conference Paper

Continual Optimization with Symmetry Teleportation for Multi-Task Learning

• Zhipeng Zhou
• Ziqiao Meng
• Pengcheng Wu
• Peilin Zhao
• Chunyan Miao

Multi-task learning (MTL) is a widely explored paradigm that enables the simultaneous learning of multiple tasks using a single model. Despite numerous solutions, the key issues of optimization conflict and task imbalance remain under-addressed, limiting performance. Unlike existing optimization-based approaches that typically reweight task losses or gradients to mitigate conflicts or promote progress, we propose a novel approach based on Continual Optimization with Symmetry Teleportation (COST). During MTL optimization, when an optimization conflict arises, we seek an alternative loss-equivalent point on the loss landscape to reduce conflict. Specifically, we utilize a low-rank adapter (LoRA) to facilitate this practical teleportation by designing convergent, loss-invariant objectives. Additionally, we introduce a historical trajectory reuse strategy to continually leverage the benefits of advanced optimizers. Extensive experiments on multiple mainstream datasets demonstrate the effectiveness of our approach. COST is a plug-and-play solution that enhances a wide range of existing MTL methods. When integrated with state-of-the-art methods, COST achieves superior performance.

ICML Conference 2025 Conference Paper

Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity

• Wanjin Feng
• Xingyu Gao 0001
• Wenqian Du 0005
• Hailong Shi
• Peilin Zhao
• Pengcheng Wu
• Chunyan Miao

Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive. In this paper, we propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture or introducing additional assumptions. FPT reduces the time complexity to $O(K)$, where $K$ is a small constant (usually $K=3$), by using a fixed-point iteration form of Leaky Integrate-and-Fire (LIF) neurons for all $T$ timesteps. We provide a theoretical convergence analysis of FPT and demonstrate that existing parallel spiking neurons can be viewed as special cases of our approach. Experimental results show that FPT effectively simulates the dynamics of original LIF neurons, significantly reducing computational time without sacrificing accuracy. This makes FPT a scalable and efficient solution for real-world applications, particularly for long-duration simulations.

IJCAI Conference 2025 Conference Paper

Enhancing Counterfactual Estimation: A Focus on Temporal Treatments

• Xin Wang
• Shengfei Lyu
• Kangyang Luo
• Lishan Yang
• Huanhuan Chen
• Chunyan Miao

In the medical field, treatment sequences significantly influence future outcomes through complex temporal interactions. Therefore, highlighting the role of temporal treatments within the model is crucial for accurate counterfactual estimation, which is often overlooked in current methods. To address this, we employ Koopman theory, known for its capability to model complex dynamic systems, and introduce a novel model named the Counterfactual Temporal Dynamics Network via Neural Koopman Operators (CTD-NKO). This model utilizes Koopman operators to encapsulate sequential treatment data, aiming to capture the causal dynamics within the system induced by temporal interactions between treatments. Moreover, CTD-NKO implements a weighting strategy that aligns joint and marginal distributions of the system state and the current treatment to mitigate time-varying confounding bias. This deviates from the balanced representation strategy employed by existing methods, as we demonstrate that such a strategy may suffer from the potential information loss of historical treatments. These designs allow CTD-NKO to exploit treatment information more thoroughly and effectively, resulting in superior performance on both synthetic and real-world datasets.

NeurIPS Conference 2025 Conference Paper

Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning

• Zhipeng Zhou
• Ziqiao Meng
• Pengcheng Wu
• Peilin Zhao
• Chunyan Miao

Nowadays deep models are required to be versatile due to the increasing realistic needs. Multi-task learning (MTL) offers an efficient way for this purpose to learn multiple tasks simultaneously with a single model. However, prior MTL solutions often focus on resolving conflicts and imbalances during optimization, which may not outperform simple linear scalarization strategies~\citep{xin2022current}. Instead of altering the optimization trajectory, this paper leverages mode connectivity to efficiently approach the Pareto front and identify the desired trade-off point. Unlike Pareto Front Learning (PFL), which aims to align with the entire Pareto front, we focus on effectively and efficiently exploring optimal trade-offs. However, three challenges persist: (1) the low-loss path can neither fully traverse trade-offs nor align with user preference due to its randomness, (2) commonly adopted Bézier curves in mode connectivity are ill-suited to navigating the complex loss landscapes of deep models, and (3) poor scalability to large-scale task scenarios. To address these challenges, we adopt non-uniform rational B-Splines (NURBS) to model mode connectivity, allowing for more flexible and precise curve optimization. Additionally, we introduce an order-aware objective to explore task loss trade-offs and employ a task grouping strategy to enhance scalability under massive task scenarios. Extensive experiments on key MTL datasets demonstrate that our proposed method, EXTRA (EXplore TRAde-offs), effectively identifies the desired point on the Pareto front and achieves state-of-the-art performance. EXTRA is also validated as a plug-and-play solution for mainstream MTL approaches.

AAAI Conference 2025 Conference Paper

Motif Guided Graph Transformers with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification

• Haocong Rao
• Chunyan Miao

Person re-identification (re-ID) via 3D skeleton data is a challenging task with significant value in many scenarios. Existing skeleton-based methods typically assume virtual motion relations between all joints, and adopt average joint or sequence representations for learning. However, they rarely explore key body structure and motion such as gait to focus on more important body joints or limbs, while lacking the ability to fully mine valuable spatial-temporal sub-patterns of skeletons to enhance model learning. This paper presents a generic Motif guided graph transformer with Combinatorial skeleton prototype learning (MoCos) that exploits structure-specific and gait-related body relations as well as combinatorial features of skeleton graphs to learn effective skeleton representations for person re-ID. In particular, motivated by the locality within joints' structure and the body-component collaboration in gait, we first propose the motif guided graph transformer (MGT) that incorporates hierarchical structural motifs and gait collaborative motifs, which simultaneously focuses on multi-order local joint correlations and key cooperative body parts to enhance skeleton relation learning. Then, we devise the combinatorial skeleton prototype learning (CSP) that leverages random spatial-temporal combinations of joint nodes and skeleton graphs to generate diverse sub-skeleton and sub-tracklet representations, which are contrasted with the most representative features (prototypes) of each identity to learn class-related semantics and discriminative skeleton representations. Extensive experiments validate the superior performance of MoCos over existing state-of-the-art models. We further show its generality under RGB-estimated skeletons, different graph modeling, and unsupervised scenarios.

NeurIPS Conference 2025 Conference Paper

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

• Sicong Leng
• Yun Xing
• Zesen Cheng
• Yang Zhou
• Hang Zhang
• Xin Li
• Deli Zhao
• Shijian Lu

Recent advancements in large multimodal models (LMMs) have significantly enhanced performance across diverse tasks, with ongoing efforts to further integrate additional modalities such as video and audio. However, most existing LMMs remain vulnerable to hallucinations, the discrepancy between the factual multimodal input and the generated textual output, which has limited their applicability in various real-world scenarios. This paper presents the first systematic investigation of hallucinations in LMMs involving the three most common modalities: language, visual, and audio. Our study reveals two key contributors to hallucinations: overreliance on unimodal priors and spurious inter-modality correlations. To address these challenges, we introduce the benchmark The Curse of Multi-Modalities (CMM), which comprehensively evaluates hallucinations in LMMs, providing a detailed analysis of their underlying issues. Our findings highlight key vulnerabilities, including imbalances in modality integration and biases from training data, underscoring the need for balanced cross-modal learning and enhanced hallucination mitigation strategies. Based on our observations and findings, we suggest potential research directions that could enhance the reliability of LMMs.

AAAI Conference 2024 Conference Paper

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

• Zhixiang Su
• Di Wang
• Chunyan Miao
• Lizhen Cui

Aiming to accurately predict missing edges representing relations between entities, which are pervasive in real-world Knowledge Graphs (KGs), relation prediction plays a critical role in enhancing the comprehensiveness and utility of KGs. Recent research focuses on path-based methods due to their inductive and explainable properties. However, these methods face a great challenge when lots of reasoning paths do not form Closed Paths (CPs) in the KG. To address this challenge, we propose Anchoring Path Sentence Transformer (APST) by introducing Anchoring Paths (APs) to alleviate the reliance of CPs. Specifically, we develop a search-based description retrieval method to enrich entity descriptions and an assessment mechanism to evaluate the rationality of APs. APST takes both APs and CPs as the inputs of a unified Sentence Transformer architecture, enabling comprehensive predictions and high-quality explanations. We evaluate APST on three public datasets and achieve state-of-the-art (SOTA) performance in 30 of 36 transductive, inductive, and few-shot experimental settings.

AAAI Conference 2024 Conference Paper

CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning

• Chenyu Sun
• Hangwei Qian
• Chunyan Miao

Offline reinforcement learning (RL) aims to learn an effective policy from a pre-collected dataset. Most existing works are to develop sophisticated learning algorithms, with less emphasis on improving the data collection process. Moreover, it is even challenging to extend the single-task setting and collect a task-agnostic dataset that allows an agent to perform multiple downstream tasks. In this paper, we propose a Curiosity-driven Unsupervised Data Collection (CUDC) method to expand feature space using adaptive temporal distances for task-agnostic data collection and ultimately improve learning efficiency and capabilities for multi-task offline RL. To achieve this, CUDC estimates the probability of the k-step future states being reachable from the current states, and adapts how many steps into the future that the dynamics model should predict. With this adaptive reachability mechanism in place, the feature representation can be diversified, and the agent can navigate itself to collect higher-quality data with curiosity. Empirically, CUDC surpasses existing unsupervised methods in efficiency and learning performance in various downstream offline RL tasks of the DeepMind control suite.

AAAI Conference 2024 Conference Paper

Latent Diffusion Transformer for Probabilistic Time Series Forecasting

• Shibo Feng
• Chunyan Miao
• Zhong Zhang
• Peilin Zhao

The probability prediction of multivariate time series is a notoriously challenging but practical task. This research proposes to condense high-dimensional multivariate time series forecasting into a problem of latent space time series generation, to improve the expressiveness of each timestamp and make forecasting more manageable. To solve the problem that the existing work is hard to extend to high-dimensional multivariate time series, we present a latent multivariate time series diffusion framework called Latent Diffusion Transformer (LDT), which consists of a symmetric statistics-aware autoencoder and a diffusion-based conditional generator, to implement this idea. Through careful design, the time series autoencoder can compress multivariate timestamp patterns into a concise latent representation by considering dynamic statistics. Then, the diffusion-based conditional generator is able to efficiently generate realistic multivariate timestamp values on a continuous latent space under a novel self-conditioning guidance which is modeled in a non-autoregressive way. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular high-dimensional multivariate time series datasets.

ICML Conference 2024 Conference Paper

Test-Time Model Adaptation with Only Forward Passes

• Shuaicheng Niu
• Chunyan Miao
• Guohao Chen
• Pengcheng Wu
• Peilin Zhao

Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. However, in real-world scenarios, models are usually deployed on resource-limited devices, e. g. , FPGAs, and are often quantized and hard-coded with non-modifiable parameters for acceleration. In light of this, existing methods are often infeasible since they heavily depend on computation-intensive backpropagation for model updating that may be not supported. To address this, we propose a test-time Forward-Optimization Adaptation (FOA) method. In FOA, we seek to solely learn a newly added prompt (as model’s input) via a derivative-free covariance matrix adaptation evolution strategy. To make this strategy work stably under our online unsupervised setting, we devise a novel fitness function by measuring test-training statistic discrepancy and model prediction entropy. Moreover, we design an activation shifting scheme that directly tunes the model activations for shifted test samples, making them align with the source training domain, thereby further enhancing adaptation performance. Without using any backpropagation and altering model weights, FOA runs on quantized 8-bit ViT outperforms gradient-based TENT on full-precision 32-bit ViT, while achieving an up to 24 -fold memory reduction on ImageNet-C. The source code is available at: https: //github. com/mr-eggplant/FOA.

AAAI Conference 2023 Conference Paper

Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

• Zhixiang Su
• Di Wang
• Chunyan Miao
• Lizhen Cui

Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions. In this paper, we introduce the concepts of relation path coverage and relation path confidence to filter out unreliable paths prior to model training to elevate the model performance. Moreover, we propose Knowledge Reasoning Sentence Transformer (KRST) to predict inductive relations in KGs. KRST is designed to encode the extracted reliable paths in KGs, allowing us to properly cluster paths and provide multi-aspect explanations. We conduct extensive experiments on three real-world datasets. The experimental results show that compared to SOTA models, KRST achieves the best performance in most transductive and inductive test cases (4 of 6), and in 11 of 12 few-shot test cases.

IJCAI Conference 2022 Conference Paper

CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning

• Chenyu Sun
• Hangwei Qian
• Chunyan Miao

In reinforcement learning (RL), it is challenging to learn directly from high-dimensional observations, where data augmentation has recently remedied it via encoding invariances from raw pixels. Nevertheless, we empirically find that not all samples are equally important and hence simply injecting more augmented inputs may instead cause instability in Q-learning. In this paper, we approach this problem systematically by developing a model-agnostic Contrastive-Curiosity-driven Learning Framework (CCLF), which can fully exploit sample importance and improve learning efficiency in a self-supervised manner. Facilitated by the proposed contrastive curiosity, CCLF is capable of prioritizing the experience replay, selecting the most informative augmented inputs, and more importantly regularizing the Q-function as well as the encoder to concentrate more on under-learned data. Moreover, it encourages the agent to explore with a curiosity-based reward. As a result, the agent can focus on more informative samples and learn representation invariances more efficiently, with significantly reduced augmented inputs. We apply CCLF to several base RL algorithms and evaluate on the DeepMind Control Suite, Atari, and MiniGrid benchmarks, where our approach demonstrates superior sample efficiency and learning performances compared with other state-of-the-art methods. Our code is available at https: //github. com/csun001/CCLF.

AAAI Conference 2022 System Paper

CrowdFL: A Marketplace for Crowdsourced Federated Learning

• Daifei Feng
• Cicilia Helena
• Wei Yang Bryan Lim
• Jer Shyuan Ng
• Hongchao Jiang
• Zehui Xiong
• Jiawen Kang
• Han Yu

Amid data privacy concerns, Federated Learning (FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists a need for a platform that matches data owners (supply) with model requesters (demand). In this paper, we present CrowdFL, a platform to facilitate the crowdsourcing of FL model training. It coordinates client selection, model training, and reputation management, which are essential steps for the FL crowdsourcing operations. By implementing model training on actual mobile devices, we demonstrate that the platform improves model performance and training efficiency. To the best of our knowledge, it is the first platform to support crowdsourcing-based FL on edge devices.

AAAI Conference 2022 System Paper

Dynamic Incentive Mechanism Design for COVID-19 Social Distancing

• Xuan Rong Zane Ho
• Wei Yang Bryan Lim
• Hongchao Jiang
• Jer Shyuan Ng
• Han Yu
• Zehui Xiong
• Dusit Niyato
• Chunyan Miao

As countries enter the endemic phase of COVID-19, people’s risk of exposure to the virus is greater than ever. There is a need to make more informed decisions in our daily lives on avoiding crowded places. Crowd monitoring systems typically require costly infrastructure. We propose a crowdsourced crowd monitoring platform which leverages user inputs to generate crowd counts and forecast location crowdedness. A key challenge for crowd-sourcing is a lack of incentive for users to contribute. We propose a Reinforcement Learning based dynamic incentive mechanism to optimally allocate rewards to encourage user participation.

JBHI Journal 2022 Journal Article

Dynamic Link Prediction for Discovery of New Impactful COVID-19 Research Approaches

• Xiangyu Wang
• Yuan Li
• Taiyu Ban
• Jiarun Zhu
• Lyuzhou Chen
• Muhammad Usman
• Xin Wang
• Huanhuan Chen

In fighting the COVID-19 pandemic, the main challenges include the lack of prior research and the urgency to find effective solutions. It is essential to accurately and rapidly summarize the relevant research work and explore potential solutions for diagnosis, treatment and prevention of COVID-19. It is a daunting task to summarize the numerous existing research works and to assess their effectiveness. This paper explores the discovery of new COVID-19 research approaches based on dynamic link prediction, which analyze the dynamic topological network of keywords to predict possible connections of research concepts. A dynamic link prediction method based on multi-granularity feature fusion is proposed. Firstly, a multi-granularity temporal feature fusion method is adopted to extract the temporal evolution of different order subgraphs. Secondly, a hierarchical feature weighting method is proposed to emphasize actively evolving nodes. Thirdly, a semantic repetition sampling mechanism is designed to avoid the negative effect of semantically equivalent medical entities on the real structure of the graph, and to capture the real topological structure features. Experiments are performed on the COVID-19 Open Research Dataset to assess the performance of the model. The results show that the proposed model performs significantly better than existing state-of-the-art models, thereby confirming the effectiveness of the proposed method for the discovery of new COVID-19 research approaches.

IJCAI Conference 2022 Conference Paper

Enhancing Sequential Recommendation with Graph Contrastive Learning

• Yixin Zhang
• Yong Liu
• Yonghui Xu
• Hao Xiong
• Chenyi Lei
• Wei He
• Lizhen Cui
• Chunyan Miao

The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing sequential recommendation methods only exploit the local context information of an individual interaction sequence and learn model parameters solely based on the item prediction loss. Thus, they usually fail to learn appropriate sequence representations. This paper proposes a novel recommendation framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data. Moreover, GCL4SR uses subgraphs of WITG to augment the representation of each interaction sequence. Two auxiliary learning objectives have also been proposed to maximize the consistency between augmented representations induced by the same interaction sequence on WITG, and minimize the difference between the representations augmented by the global context on WITG and the local representation of the original sequence. Extensive experiments on real-world datasets demonstrate that GCL4SR consistently outperforms state-of-the-art sequential recommendation methods.

TIST Journal 2022 Journal Article

Federated Learning for Personalized Humor Recognition

• Xu Guo
• Han Yu
• Boyang Li
• Hao Wang
• Pengwei Xing
• Siwei Feng
• Zaiqing Nie
• Chunyan Miao

Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challenge here is that human perception of humorous content is highly subjective. The same joke may receive different funniness ratings from different readers. This makes it highly challenging for humor recognition models to achieve personalization in practical scenarios. Existing approaches are generally designed based on the assumption that users have a consensus on whether a given text is humorous or not. Thus, they cannot handle diverse humor preferences well. In this article, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL). Extending a pre-trained language model, FedHumor guides the fine-tuning process by considering diverse distributions of humor preferences from individuals. It incorporates a diversity adaptation strategy into the FL paradigm to train a personalized humor recognition model. To the best of our knowledge, FedHumor is the first text-based personalized humor recognition model through federated learning. Extensive experiments demonstrate the advantage of FedHumor in recognizing humorous texts compared to nine state-of-the-art humor recognition approaches with superior capability for handling the diversity in humor labels produced by users with diverse preferences.

ICLR Conference 2022 Conference Paper

On Non-Random Missing Labels in Semi-Supervised Learning

• Xinting Hu
• Yulei Niu
• Chunyan Miao
• Xian-Sheng Hua 0001
• Hanwang Zhang

Semi-Supervised Learning (SSL) is fundamentally a missing label problem, in which the label Missing Not At Random (MNAR) problem is more realistic and challenging, compared to the widely-adopted yet naive Missing Completely At Random assumption where both labeled and unlabeled data share the same class distribution. Different from existing SSL solutions that overlook the role of ''class'' in causing the non-randomness, e.g., users are more likely to label popular classes, we explicitly incorporate ''class'' into SSL. Our method is three-fold: 1) We propose Class-Aware Propensity (CAP) that exploits the unlabeled data to train an improved classifier using the biased labeled data. 2) To encourage rare class training, whose model is low-recall but high-precision that discards too many pseudo-labeled data, we propose Class-Aware Imputation (CAI) that dynamically decreases (or increases) the pseudo-label assignment threshold for rare (or frequent) classes. 3) Overall, we integrate CAP and CAI into a Class-Aware Doubly Robust (CADR) estimator for training an unbiased SSL model. Under various MNAR settings and ablations, our method not only significantly outperforms existing baselines, but also surpasses other label bias removal SSL methods.

IJCAI Conference 2022 Conference Paper

SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification

• Haocong Rao
• Chunyan Miao

Recent advances in skeleton-based person re-identification (re-ID) obtain impressive performance via either hand-crafted skeleton descriptors or skeleton representation learning with deep learning paradigms. However, they typically require skeletal pre-modeling and label information for training, which leads to limited applicability of these methods. In this paper, we focus on unsupervised skeleton-based person re-ID, and present a generic Simple Masked Contrastive learning (SimMC) framework to learn effective representations from unlabeled 3D skeletons for person re-ID. Specifically, to fully exploit skeleton features within each skeleton sequence, we first devise a masked prototype contrastive learning (MPC) scheme to cluster the most typical skeleton features (skeleton prototypes) from different subsequences randomly masked from raw sequences, and contrast the inherent similarity between skeleton features and different prototypes to learn discriminative skeleton representations without using any label. Then, considering that different subsequences within the same sequence usually enjoy strong correlations due to the nature of motion continuity, we propose the masked intra-sequence contrastive learning (MIC) to capture intra-sequence pattern consistency between subsequences, so as to encourage learning more effective skeleton representations for person re-ID. Extensive experiments validate that the proposed SimMC outperforms most state-of-the-art skeleton-based methods. We further show its scalability and efficiency in enhancing the performance of existing models. Our codes are available at https: //github. com/Kali-Hac/SimMC.

AAAI Conference 2021 Conference Paper

A Hybrid Bandit Framework for Diversified Recommendation

• Qinxu Ding
• Yong Liu
• Chunyan Miao
• Fei Cheng
• Haihong Tang

The interactive recommender systems involve users in the recommendation procedure by receiving timely user feedback to update the recommendation policy. Therefore, they are widely used in real application scenarios. Previous interactive recommendation methods primarily focus on learning users’ personalized preferences on the relevance properties of an item set. However, the investigation of users’ personalized preferences on the diversity properties of an item set is usually ignored. To overcome this problem, we propose the Linear Modular Dispersion Bandit (LMDB) framework, which is an online learning setting for optimizing a combination of modular functions and dispersion functions. Specifically, LMDB employs modular functions to model the relevance properties of each item, and dispersion functions to describe the diversity properties of an item set. Moreover, we also develop a learning algorithm, called Linear Modular Dispersion Hybrid (LMDH) to solve the LMDB problem and derive a gap-free bound on its n-step regret. Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed LMDB framework in balancing the recommendation accuracy and diversity.

AAAI Conference 2021 System Paper

AI-Empowered Decision Support for COVID-19 Social Distancing

• Hongchao Jiang
• Wei Yang Bryan Lim
• Jer Shyuan Ng
• Harold Ze Chie Teng
• Han Yu
• Zehui Xiong
• Dusit Niyato
• Chunyan Miao

The COVID-19 pandemic is one of the most severe challenges the world faces today. In order to contain the transmission of COVID-19, people around the world have been advised to practise social distancing. However, maintaining social distance is a challenging problem, as we often do not know beforehand how crowded the places we intend to visit are. In this paper, we demonstrate crowded. sg, an AIempowered platform that leverages on Unmanned Aerial Vehicles (UAVs), crowdsourced images, and computer vision techniques to provide social distancing decision support.

AAAI Conference 2021 Conference Paper

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

• Peixiang Zhong
• Di Wang
• Pengfei Li
• Chen Zhang
• Hao Wang
• Chunyan Miao

Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or unrelated responses. In this paper, we hypothesize that combining rationality and emotion into conversational agents can improve response quality. To test the hypothesis, we focus on one fundamental aspect of rationality, i. e. , commonsense, and propose CARE, a novel model for commonsense-aware emotional response generation. Specifically, we first propose a framework to learn and construct commonsense-aware emotional latent concepts of the response given an input message and a desired emotion. We then propose three methods to collaboratively incorporate the latent concepts into response generation. Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

AAAI Conference 2021 Conference Paper

HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks

• Yuanyuan Chen
• Boyang Li
• Han Yu
• Pengcheng Wu
• Chunyan Miao

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HY- DRA, which interprets the predictions made by DNNs as effects of their training data. Existing approaches generally estimate data contributions around the final model parameters and ignore how the training data shape the optimization trajectory. By unrolling the hypergradient of test loss w. r. t. the weights of training data, HYDRA assesses the contribution of training data toward test data points throughout the training trajectory. In order to accelerate computation, we remove the Hessian from the calculation and prove that, under moderate conditions, the approximation error is bounded. Corroborating this theoretical claim, empirical results indicate the error is indeed small. In addition, we quantitatively demonstrate that HYDRA outperforms influence functions in accurately estimating data contribution and detecting noisy data labels. The source code is available at https: //github. com/cyyever/aaai hydra.

AAAI Conference 2021 Conference Paper

Keyword-Guided Neural Conversational Model

• Peixiang Zhong
• Yong Liu
• Hao Wang
• Chunyan Miao

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e. g. , recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for next-turn keyword classification are directly extracted from conversations without human annotations, thus, they are noisy and have low correlation with human judgements, and 2) during keyword transition, the agents solely rely on the similarities between word embeddings to move closer to the target keyword, which may not reflect how humans converse. In this paper, we assume that human conversations are grounded on commonsense and propose a keyword-guided neural conversational model that can leverage external commonsense knowledge graphs (CKG) for both keyword transition and response retrieval. Automatic evaluations suggest that commonsense improves the performance of both next-turn keyword prediction and keyword-augmented response retrieval. In addition, both self-play and human evaluations show that our model produces responses with smoother keyword transition and reaches the target keyword faster than competitive baselines.

AAAI Conference 2021 Conference Paper

Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition

• Hangwei Qian
• Sinno Jialin Pan
• Chunyan Miao

In wearable-sensor-based activity recognition, it is often assumed that the training and the test samples follow the same data distribution. This assumption neglects practical scenarios where the activity patterns inevitably vary from person to person. To solve this problem, transfer learning and domain adaptation approaches are often leveraged to reduce the gaps between different participants. Nevertheless, these approaches require additional information (i. e. , labeled or unlabeled data, meta-information) from the target domain during the training stage. In this paper, we introduce a novel method named Generalizable Independent Latent Excitation (GILE) for human activity recognition, which greatly enhances the cross-person generalization capability of the model. Our proposed method is superior to existing methods in the sense that it does not require any access to the target domain information. Besides, this novel model can be directly applied to various target domains without re-training or fine-tuning. Specifically, the proposed model learns to automatically disentangle domain-agnostic and domain-specific features, the former of which are expected to be invariant across various persons. To further remove correlations between the two types of features, a novel Independent Excitation mechanism is incorporated in the latent feature space. Comprehensive experimental evaluations are conducted on three benchmark datasets to demonstrate the superiority of the proposed method over state-ofthe-art solutions.

AAAI Conference 2021 System Paper

Mobile-based Clock Drawing Test for Detecting Early Signs of Dementia

• Hongchao Jiang
• Yanci Zhang
• Zhiwei Zeng
• Jun Ji
• Yu Wang
• Ying Chi
• Chunyan Miao

Dementia is one of the major causes of disability and dependency among older people. Early detection is the key for preserving the quality of life of the patients and reducing caring costs. The Clock Drawing Test (CDT) is commonly used by clinicians to screen for early signs of dementia. We build an automated CDT that runs on mobile platforms, enabling convenient and frequent self-monitoring and testing at minimal costs. Our system combines both a spatial-temporal approach and a purely image-based deep learning approach to analyze and evaluate the hand-drawn clocks based on established clinical criteria. Our system produces scores that are highly correlated with expert human raters.

IJCAI Conference 2021 Conference Paper

Predictive Analytics for COVID-19 Social Distancing

• Harold Ze Chie Teng
• Hongchao Jiang
• Xuan Rong Zane Ho
• Wei Yang Bryan Lim
• Jer Shyuan Ng
• Han Yu
• Zehui Xiong
• Dusit Niyato

The COVID-19 pandemic has disrupted the lives of millions across the globe. In Singapore, promoting safe distancing by managing crowds in public areas have been the cornerstone of containing the community spread of the virus. One of the most important solutions to maintain social distancing is to monitor the crowdedness of indoor and outdoor points of interest. Using Nanyang Technological University (NTU) as a testbed, we develop and deploy a platform that provides live and predicted crowd counts for key locations on campus to help users plan their trips in an informed manner, so as to mitigate the risk of community transmission.

AAAI Conference 2021 System Paper

Proof of Learning (PoLe): Empowering Machine Learning with Consensus Building on Blockchains (Demo)

• Yixiao Lan
• Yuan Liu
• Boyang Li
• Chunyan Miao

The consensus algorithm is the core component of a blockchain system, which determines the efficiency, security, and scalability of the blockchain network. The representative consensus algorithm is the proof of work (PoW) proposed in Bitcoin, where the consensus process consumes large amount of compute in solving meaningless Hash puzzel. Meanwhile, the deep learning (DL) has brought unprecedented performance gains at heavy computate cost. In this demo, we channels the otherwise wasted computational power to the practical purpose of training neural network models, through the proposed proof of learning (PoLe) consensus algorithm. In PoLe, the training/testing data are released to the entire blockchain network (BCN) and the consensus nodes train NN models on the data, which serves as the proof of learning. When the consensus on the BCN considers a NN model to be valid, a new block is appended to the blockchain. Through our system, we investigate the potential of enpowering machine learning with consensus building on blockchains.

AIJ Journal 2021 Journal Article

Weakly-supervised sensor-based activity segmentation and recognition via learning from distributions

• Hangwei Qian
• Sinno Jialin Pan
• Chunyan Miao

Sensor-based activity recognition aims to recognize users' activities from multi-dimensional streams of sensor readings received from ubiquitous sensors. It has been shown that data segmentation and feature extraction are two crucial steps in developing machine learning-based models for sensor-based activity recognition. However, most previous studies were only focused on the latter step by assuming that data segmentation is done in advance. In practice, on the one hand, doing data segmentation on sensory streams is very challenging. On the other hand, if data segmentation is considered as a pre-process, the errors in data segmentation may be propagated to latter steps. Therefore, in this paper, we propose a unified weakly-supervised framework based on kernel embedding of distributions to jointly segment sensor streams, extract powerful features from each segment, and train a final classifier for activity recognition. We further offer an accelerated version for large-scale data by utilizing the technique of random Fourier features. We conduct experiments on four benchmark datasets to verify the effectiveness and scalability of our proposed framework.

IJCAI Conference 2020 Conference Paper

A Gamified Assessment Platform for Predicting the Risk of Dementia +Parkinson’s disease (DPD) Co-Morbidity

• Zhiwei Zeng
• Hongchao Jiang
• Yanci Zhang
• Zhiqi Shen
• Jun Ji
• Martin J. McKeown
• Jing Jih Chin
• Cyril Leung

Population aging is becoming an increasingly important issue around the world. As people live longer, they also tend to suffer from more challenging medical conditions. Currently, there is a lack of a holistic technology-powered solution for providing quality care at affordable cost to patients suffering from co-morbidity. In this paper, we demonstrate a novel AI-powered solution to provide early detection of the onset of Dementia + Parkinson's disease (DPD) co-morbidity, a condition which severely limits a senior's ability to live actively and independently. We investigate useful in-game behaviour markers which can support machine learning-based predictive analytics on seniors' risk of developing DPD co-morbidity.

IJCAI Conference 2020 Conference Paper

A Testbed for Studying COVID-19 Spreading in Ride-Sharing Systems

• Harrison Jun Yong Wong
• Zichao Deng
• Han Yu
• Jianqiang Huang
• Cyril Leung
• Chunyan Miao

Order dispatch is an important area where artificial intelligence (AI) can benefit ride-sharing systems (e. g. , Grab, Uber), which has become an integral part of our public transport network. In this paper, we present a multi-agent testbed to study the spread of infectious diseases through such a system. It allows users to vary the parameters of the disease and behaviours to study the interaction effect between technology, disease and people's behaviours in such a complex environment.

IJCAI Conference 2020 Conference Paper

An AI-empowered Visual Storyline Generator

• Chang Liu
• Zhao Yong Lim
• Han Yu
• Zhiqi Shen
• Ian Dixon
• Zhanning Gao
• Pan Wang
• Peiran Ren

Video editing is currently a highly skill- and time-intensive process. One of the most important tasks in video editing is to compose the visual storyline. This paper outlines Visual Storyline Generator (VSG), an artificial intelligence (AI)-empowered system that automatically generates visual storylines based on a set of images and video footages provided by the user. It is designed to produce engaging and persuasive promotional videos with an easy-to-use interface. In addition, users can be involved in refining the AI-generated visual storylines. The editing results can be used as training data to further improve the AI algorithms in VSG.

UAI Conference 2020 Conference Paper

Differentially Private Top-k Selection via Stability on Unknown Domain

• Ricardo Silva Carvalho
• Ke Wang 0001
• Lovedeep Gondara
• Chunyan Miao

We propose a new method that satisfies approximate differential privacy for top-$k$ selection with unordered output in the unknown data domain setting, not relying on the full knowledge of the domain universe. Our algorithm only requires looking at the top-$\bar{k}$ elements for any given $\bar{k} \geq k$, thus, enforcing the principle of minimal privilege. Unlike previous methods, our privacy parameter $\varepsilon$ does not scale with $k$, giving improved applicability for scenarios of very large $k$. Moreover, our novel construction, which combines the sparse vector technique and stability efficiently, can be applied as a general framework to any type of query, thus being of independent interest. We extensively compare our algorithm to previous work of top-$k$ selection on the unknown domain, and show, both analytically and on experiments, settings where we outperform the current state-of-the-art.

AAAI Conference 2020 Conference Paper

Diversified Interactive Recommendation with Implicit Feedback

• Yong Liu
• Yingtai Xiao
• Qiong Wu
• Chunyan Miao
• Juyong Zhang
• Binqiang Zhao
• Haihong Tang

Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attention. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsatisfying user experiences. In this paper, we propose a novel diversified recommendation model, named Diversified Contextual Combinatorial Bandit (DC2 B), for interactive recommendation with users’ implicit feedback. Specifically, DC2 B employs determinantal point process in the recommendation procedure to promote diversity of the recommendation results. To learn the model parameters, a Thompson sampling-type algorithm based on variational Bayesian inference is proposed. In addition, theoretical regret analysis is also provided to guarantee the performance of DC2 B. Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed method in balancing the recommendation accuracy and diversity.

KR Conference 2020 System Paper

Explainable and Argumentation-based Decision Making with Qualitative Preferences for Diagnostics and Prognostics of Alzheimer's Disease

• Zhiwei Zeng
• Zhiqi Shen
• Benny Toh Hsiang Tan
• Jing Jih Chin
• Cyril Leung
• Yu Wang
• Ying Chi
• Chunyan Miao

Argumentation has gained traction as a formalism to make more transparent decisions and provide formal explanations recently. In this paper, we present an argumentation-based approach to decision making that can support modelling and automated reasoning about complex qualitative preferences and offer dialogical explanations for the decisions made. We first propose Qualitative Preference Decision Frameworks (QPDFs). In a QPDF, we use contextual priority to represent the relative importance of combinations of goals in different contexts and define associated strategies for deriving decision preferences based on prioritized goal combinations. To automate the decision computation, we map QPDFs to Assumption-based Argumentation (ABA) frameworks so that we can utilize existing ABA argumentative engines for our implementation. We implemented our approach for two tasks, diagnostics and prognostics of Alzheimer's Disease (AD), and evaluated it with real-world datasets. For each task, one of our models achieves the highest accuracy and good precision and recall for all classes compared to common machine learning models. Moreover, we study how to formalize argumentation dialogues that give contrastive, focused and selected explanations for the most preferred decisions selected in given contexts.

AAAI Conference 2020 Short Paper

Generating Engaging Promotional Videos for E-commerce Platforms (Student Abstract)

• Chang Liu
• Han Yu
• Yi Dong
• Zhiqi Shen
• Yingxue Yu
• Ian Dixon
• Zhanning Gao
• Pan Wang

There is an emerging trend for sellers to use videos to promote their products on e-commerce platforms such as Taobao. com. Current video production workflow includes the production of visual storyline by human directors. We propose a system to automatically generate visual storyline based on the input set of visual materials (e. g. video clips or still images) and then produce a promotional video. In particular, we propose an algorithm called Shot Composition, Selection and Plotting (ShotCSP), which generates visual storylines leveraging film-making principles to improve viewing experience and perceived persuasiveness.

IJCAI Conference 2020 Conference Paper

Learning Personalized Itemset Mapping for Cross-Domain Recommendation

• Yinan Zhang
• Yong Liu
• Peng Han
• Chunyan Miao
• Lizhen Cui
• Baoli Li
• Haihong Tang

Cross-domain recommendation methods usually transfer knowledge across different domains implicitly, by sharing model parameters or learning parameter mappings in the latent space. Differing from previous studies, this paper focuses on learning explicit mapping between a user's behaviors (i. e. interaction itemsets) in different domains during the same temporal period. In this paper, we propose a novel deep cross-domain recommendation model, called Cycle Generation Networks (CGN). Specifically, CGN employs two generators to construct the dual-direction personalized itemset mapping between a user's behaviors in two different domains over time. The generators are learned by optimizing the distance between the generated itemset and the real interacted itemset, as well as the cycle-consistent loss defined based on the dual-direction generation procedure. We have performed extensive experiments on real datasets to demonstrate the effectiveness of the proposed model, comparing with existing single-domain and cross-domain recommendation methods.

AAAI Conference 2020 Conference Paper

Multi-Label Causal Feature Selection

• Xingyu Wu
• Bingbing Jiang
• Kui Yu
• Huanhuan Chen
• Chunyan Miao

Multi-label feature selection has received considerable attentions during the past decade. However, existing algorithms do not attempt to uncover the underlying causal mechanism, and individually solve different types of variable relationships, ignoring the mutual effects between them. Furthermore, these algorithms lack of interpretability, which can only select features for all labels, but cannot explain the correlation between a selected feature and a certain label. To address these problems, in this paper, we theoretically study the causal relationships in multi-label data, and propose a novel Markov blanket based multi-label causal feature selection (MB-MCF) algorithm. MB-MCF mines the causal mechanism of labels and features first, to obtain a complete representation of information about labels. Based on the causal relationships, MB- MCF then selects predictive features and simultaneously distinguishes common features shared by multiple labels and label-specific features owned by single labels. Experiments on real-world data sets validate that MB-MCF could automatically determine the number of selected features and simultaneously achieve the best performance compared with state-of-the-art methods. An experiment in Emotions data set further demonstrates the interpretability of MB-MCF.

IJCAI Conference 2019 Conference Paper

A Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition

• Hangwei Qian
• Sinno Jialin Pan
• Bingshui Da
• Chunyan Miao

Feature-engineering-based machine learning models and deep learning models have been explored for wearable-sensor-based human activity recognition. For both types of methods, one crucial research issue is how to extract proper features from the partitioned segments of multivariate sensor readings. Existing methods have different drawbacks: 1) feature-engineering-based methods are able to extract meaningful features, such as statistical or structural information underlying the segments, but usually require manual designs of features for different applications, which is time consuming, and 2) deep learning models are able to learn temporal and/or spatial features from the sensor data automatically, but fail to capture statistical information. In this paper, we propose a novel deep learning model to automatically learn meaningful features including statistical features, temporal features and spatial correlation features for activity recognition in a unified framework. Extensive experiments are conducted on four datasets to demonstrate the effectiveness of our proposed method compared with state-of-the-art baselines.

TIST Journal 2019 Journal Article

A Survey of Zero-Shot Learning

• Wei Wang
• Vincent W. Zheng
• Han Yu
• Chunyan Miao

Most machine-learning methods focus on classifying instances whose classes have already been seen in training. In practice, many applications require classifying instances whose classes have not been seen previously. Zero-shot learning is a powerful and promising learning paradigm, in which the classes covered by training instances and the classes we aim to classify are disjoint. In this paper, we provide a comprehensive survey of zero-shot learning. First of all, we provide an overview of zero-shot learning. According to the data utilized in model optimization, we classify zero-shot learning into three learning settings. Second, we describe different semantic spaces adopted in existing zero-shot learning works. Third, we categorize existing zero-shot learning methods and introduce representative methods under each category. Fourth, we discuss different applications of zero-shot learning. Finally, we highlight promising future research directions of zero-shot learning.

IJCAI Conference 2019 Conference Paper

Agent-based Decision Support for Pain Management in Primary Care Settings

• Xu Guo
• Han Yu
• Chunyan Miao
• Yiqiang Chen

The lack of systematic pain management training and support among primary care physicians (PCPs) limits their ability to provide quality care for patients with pain. Here, we demonstrate an Agent-based Clinical Decision Support System to empower PCPs to leverage knowledge from pain specialists. The system learns a general-purpose representation space on patients, automatically diagnoses pain, recommends therapy and medicine, and suggests a referral program to PCPs in their decision-making tasks.

AAAI Conference 2019 Conference Paper

An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss

• Peixiang Zhong
• Di Wang
• Chunyan Miao

Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention due to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only textual information in order to classify whether a given premise entails, contradicts, or is neutral with respect to a given hypothesis. Surprisingly, the use of methods based on structured knowledge – a central topic in artificial intelligence – has not received much attention vis-a-vis the NLI problem. While there are many open knowledge bases that contain various types of reasoning information, their use for NLI has not been well explored. To address this, we present a combination of techniques that harness external knowledge to improve performance on the NLI problem in the science questions domain. We present the results of applying our techniques on text, graph, and text-and-graph based models; and discuss the implications of using external knowledge to solve the NLI problem. Our model achieves close to state-of-the-art performance for NLI on the SciTail science questions dataset.

IJCAI Conference 2019 Conference Paper

An Online Intelligent Visual Interaction System

• Anxiang Zeng
• Han Yu
• Xin Gao
• Kairi Ou
• Zhenchuan Huang
• Peng Hou
• Mingli Song
• Jingshu Zhang

This paper proposes an Online Intelligent Visual Interactive System (OIVIS), which can be applied to various live video broadcast and short video scenes to provide an interactive user experience. In the live video broadcast, the anchor can issue various commands by using pre-defined gestures, and can trigger real-time background replacement to create an immersive atmosphere. To support such dynamic interactivity, we implemented algorithms including real-time gesture recognition and real-time video portrait segmentation, developed a deep network inference framework, and a real-time rendering framework AI Gender at the front end to create a complete set of visual interaction solutions for use in resource constrained mobile.

AAAI Conference 2019 Short Paper

Computing Argumentative Explanations in Bipolar Argumentation Frameworks

• Zhiwei Zeng
• Chunyan Miao
• Cyril Leung
• Zhiqi Shen
• Jing Jih Chin

The process of arguing is also the process of justifying and explaining. Here, we focus on argumentative explanations in Abstract Bipolar Argumentation. We propose new defence and acceptability semantics, which operates on both attack and support relations, and use them to formalize two types of explanations, concise and strong explanations. We also show how to compute the explanations with Bipolar Dispute Trees.

AAAI Conference 2019 Conference Paper

Distribution-Based Semi-Supervised Learning for Activity Recognition

• Hangwei Qian
• Sinno Jialin Pan
• Chunyan Miao

Supervised learning methods have been widely applied to activity recognition. The prevalent success of existing methods, however, has two crucial prerequisites: proper feature extraction and sufficient labeled training data. The former is important to differentiate activities, while the latter is crucial to build a precise learning model. These two prerequisites have become bottlenecks to make existing methods more practical. Most existing feature extraction methods highly depend on domain knowledge, while labeled data requires intensive human annotation effort. Therefore, in this paper, we propose a novel method, named Distribution-based Semi-Supervised Learning, to tackle the aforementioned limitations. The proposed method is capable of automatically extracting powerful features with no domain knowledge required, meanwhile, alleviating the heavy annotation effort through semi-supervised learning. Specifically, we treat data stream of sensor readings received in a period as a distribution, and map all training distributions, including labeled and unlabeled, into a reproducing kernel Hilbert space (RKHS) using the kernel mean embedding technique. The RKHS is further altered by exploiting the underlying geometry structure of the unlabeled distributions. Finally, in the altered RKHS, a classifier is trained with the labeled distributions. We conduct extensive experiments on three public datasets to verify the effectiveness of our method compared with state-of-the-art baselines.

IJCAI Conference 2019 Conference Paper

Intelligent Decision Support for Improving Power Management

• Yongqing Zheng
• Han Yu
• Kun Zhang
• Yuliang Shi
• Cyril Leung
• Chunyan Miao

With the development and adoption of the electricity information tracking system in China, real-time electricity consumption big data have become available to enable artificial intelligence (AI) to help power companies and the urban management departments to make demand side management decisions. We demonstrate the Power Intelligent Decision Support (PIDS) platform, which can generate Orderly Power Utilization (OPU) decision recommendations and perform Demand Response (DR) implementation management based on a short-term load forecasting model. It can also provide different users with query and application functions to facilitate explainable decision support.

AAAI Conference 2019 Conference Paper

Modelling Autobiographical Memory Loss across Life Span

• Di Wang
• Ah-Hwee Tan
• Chunyan Miao
• Ahmed A. Moustafa

Neurocomputational modelling of long-term memory is a core topic in computational cognitive neuroscience, which is essential towards self-regulating brain-like AI systems. In this paper, we study how people generally lose their memories and emulate various memory loss phenomena using a neurocomputational autobiographical memory model. Specifically, based on prior neurocognitive and neuropsychology studies, we identify three neural processes, namely overload, decay and inhibition, which lead to memory loss in memory formation, storage and retrieval, respectively. For model validation, we collect a memory dataset comprising more than one thousand life events and emulate the three key memory loss processes with model parameters learnt from memory recall behavioural patterns found in human subjects of different age groups. The emulation results show high correlation with human memory recall performance across their life span, even with another population not being used for learning. To the best of our knowledge, this paper is the first research work on quantitative evaluations of autobiographical memory loss using a neurocomputational model.

IJCAI Conference 2019 Conference Paper

PD-GAN: Adversarial Learning for Personalized Diversity-Promoting Recommendation

• Qiong Wu
• Yong Liu
• Chunyan Miao
• Binqiang Zhao
• Yin Zhao
• Lu Guan

This paper proposes Personalized Diversity-promoting GAN (PD-GAN), a novel recommendation model to generate diverse, yet relevant recommendations. Specifically, for each user, a generator recommends a set of diverse and relevant items by sequentially sampling from a personalized Determinantal Point Process (DPP) kernel matrix. This kernel matrix is constructed by two learnable components: the general co-occurrence of diverse items and the user's personal preference to items. To learn the first component, we propose a novel pairwise learning paradigm using training pairs, and each training pair consists of a set of diverse items and a set of similar items randomly sampled from the observed data of all users. The second component is learnt through adversarial training against a discriminator which strives to distinguish between recommended items and the ground-truth sets randomly sampled from the observed data of the target user. Experimental results show that PD-GAN is superior to generate recommendations that are both diverse and relevant.

IJCAI Conference 2018 Conference Paper

Building Ethics into Artificial Intelligence

• Han Yu
• Zhiqi Shen
• Chunyan Miao
• Cyril Leung
• Victor R. Lesser
• Qiang Yang

As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI research community, this topic remains less familiar to many researchers. In this paper, we complement existing surveys, which largely focused on the psychological, social and legal discussions of the topic, with an analysis of recent advances in technical solutions for AI governance. By reviewing publications in leading AI conferences including AAAI, AAMAS, ECAI and IJCAI, we propose a taxonomy which divides the field into four areas: 1) exploring ethical dilemmas; 2) individual ethical decision frameworks; 3) collective ethical decision frameworks; and 4) ethics in human-AI interactions. We highlight the intuitions and key techniques used in each approach, and discuss promising future research directions towards successful integration of ethical AI systems into human societies.

AAAI Conference 2018 Short Paper

Building More Explainable Artificial Intelligence With Argumentation

• Zhiwei Zeng
• Chunyan Miao
• Cyril Leung
• Jing Jih Chin

Currently, much of machine learning is opaque, just like a “black box”. However, in order for humans to understand, trust and effectively manage the emerging AI systems, an AI needs to be able to explain its decisions and conclusions. In this paper, I propose an argumentation-based approach to explainable AI, which has the potential to generate more comprehensive explanations than existing approaches.

AAMAS Conference 2018 Conference Paper

Context-based and Explainable Decision Making with Argumentation

• Zhiwei Zeng
• Xiuyi Fan
• Chunyan Miao
• Cyril Leung
• Chin Jing Jih
• Ong Yew Soon

Argumentation-based approaches to decision making have gained considerable research interest, due to their ability to select and justify decisions. In order to make better decisions, context is a key piece of information that needs to be considered. However, most existing argumentation-based models and frameworks have not modelled or reasoned with context explicitly. In this paper, we present a new argumentation-based approach for making context-based and explainable decisions. We propose a graphical representation for modelling decision problems involving varying contexts, Decision Graphs with Context (DGC), and a reasoning mechanism for making context-based decisions which relies on the Assumption-based Argumentation formalism. Based on these constructs, we introduce two types of explanations, argument explanation and context explanation, identifying the reasons for the decisions made from an argument-view and a context-view respectively.

AAAI Conference 2018 Conference Paper

DyETC: Dynamic Electronic Toll Collection for Traffic Congestion Alleviation

• Haipeng Chen
• Bo An
• Guni Sharon
• Josiah Hanna
• Peter Stone
• Chunyan Miao
• Yeng Soh

To alleviate traffic congestion in urban areas, electronic toll collection (ETC) systems are deployed all over the world. Despite the merits, tolls are usually pre-determined and fixed from day to day, which fail to consider traffic dynamics and thus have limited regulation effect when traffic conditions are abnormal. In this paper, we propose a novel dynamic ETC (DyETC) scheme which adjusts tolls to traffic conditions in realtime. The DyETC problem is formulated as a Markov decision process (MDP), the solution of which is very challenging due to its 1) multi-dimensional state space, 2) multidimensional, continuous and bounded action space, and 3) time-dependent state and action values. Due to the complexity of the formulated MDP, existing methods cannot be applied to our problem. Therefore, we develop a novel algorithm, PG-β, which makes three improvements to traditional policy gradient method by proposing 1) time-dependent value and policy functions, 2) Beta distribution policy function and 3) state abstraction. Experimental results show that, compared with existing ETC schemes, DyETC increases traffic volume by around 8%, and reduces travel time by around 14. 6% during rush hour. Considering the total traffic volume in a traffic network, this contributes to a substantial increase to social welfare.

AAAI Conference 2018 Conference Paper

Sensor-Based Activity Recognition via Learning From Distributions

• Hangwei Qian
• Sinno Pan
• Chunyan Miao

Sensor-based activity recognition aims to predict users’ activities from multi-dimensional streams of various sensor readings received from ubiquitous sensors. To use machine learning techniques for sensor-based activity recognition, previous approaches focused on composing a feature vector to represent sensor-reading streams received within a period of various lengths. With the constructed feature vectors, e. g. , using predefined orders of moments in statistics, and their corresponding labels of activities, standard classification algorithms can be applied to train a predictive model, which will be used to make predictions online. However, we argue that in this way some important information, e. g. , statistical information captured by higher-order moments, may be discarded when constructing features. Therefore, in this paper, we propose a new method, denoted by SMMAR, based on learning from distributions for sensor-based activity recognition. Specifically, we consider sensor readings received within a period as a sample, which can be represented by a feature vector of infinite dimensions in a Reproducing Kernel Hilbert Space (RKHS) using kernel embedding techniques. We then train a classifier in the RKHS. To scale-up the proposed method, we further offer an accelerated version by utilizing an explicit feature map instead of using a kernel function. We conduct experiments on four benchmark datasets to verify the effectiveness and scalability of our proposed method.

AAAI Conference 2018 Conference Paper

SmartHS: An AI Platform for Improving Government Service Provision

• Yongqing Zheng
• Han Yu
• Lizhen Cui
• Chunyan Miao
• Cyril Leung
• Qiang Yang

Over the years, government service provision in China has been plagued by inefficiencies. Previous attempts to address this challenge following a toolbox e-government system model in China were not effective. In this paper, we report on a successful experience in improving government service provision in the domain of social insurance in Shandong Province, China. Through standardization of service work- flows following the Complete Contract Theory (CCT) and the infusion of an artificial intelligence (AI) engine to maximize the expected quality of service while reducing waiting time, the Smart Human-resource Services (SmartHS) platform transcends organizational boundaries and improves system efficiency. Deployments in 3 cities involving 2, 000 participating civil servants and close to 3 million social insurance service cases over a 1 year period demonstrated that SmartHS significantly improves user experience with roughly a third of the original front desk staff. This new AI-enhanced mode of operation is useful for informing current policy discussions in many domains of government service provision.

AAAI Conference 2017 Short Paper

A Computational Assessment Model for the Adaptive Level of Rehabilitation Exergames for the Elderly

• Hao Zhang
• Chunyan Miao
• Han Yu
• Cyril Leung

Rehabilitation exergames can engage the elderly in physical activities and help them recover part of their deteriorating capabilities. However, most existing exergames lack measures of how suitable they are to specific individuals. In this paper, we propose the Computational Person-Environment Fit model to evaluate the adaptability of the exergames to each individual elderly user.

IJCAI Conference 2017 Conference Paper

Online Multitask Relative Similarity Learning

• Shuji Hao
• Peilin Zhao
• Yong Liu
• Steven C. H. Hoi
• Chunyan Miao

Relative similarity learning~(RSL) aims to learn similarity functions from data with relative constraints. Most previous algorithms developed for RSL are batch-based learning approaches which suffer from poor scalability when dealing with real-world data arriving sequentially. These methods are often designed to learn a single similarity function for a specific task. Therefore, they may be sub-optimal to solve multiple task learning problems. To overcome these limitations, we propose a scalable RSL framework named OMTRSL (Online Multi-Task Relative Similarity Learning). Specifically, we first develop a simple yet effective online learning algorithm for multi-task relative similarity learning. Then, we also propose an active learning algorithm to save the labeling cost. The proposed algorithms not only enjoy theoretical guarantee, but also show high efficacy and efficiency in extensive experiments on real-world datasets.

AAMAS Conference 2017 Conference Paper

Two Forms of Explanations in Computational Assumption-based Argumentation

• Xiuyi Fan
• Siyuan Liu
• Huiguo Zhang
• Chunyan Miao
• Cyril Leung

Computational Assumption-based Argumentation (CABA) has been introduced to model argumentation with numerical data processing. To realize the “explanation power” of CABA, we study two forms of argumentative explanations, argument explanations and CU explanations representing diagnosis and repair, resp.

AAAI Conference 2016 Conference Paper

A Fraud Resilient Medical Insurance Claim System

• Yuliang Shi
• Chenfei Sun
• Qingzhong Li
• Lizhen Cui
• Han Yu
• Chunyan Miao

As many countries in the world start to experience population aging, there are an increasing number of people relying on medical insurance to access healthcare resources. Medical insurance frauds are causing billions of dollars in losses for public healthcare funds. The detection of medical insurance frauds is an important and difficult challenge for the artificial intelligence (AI) research community. This paper outlines HFDA, a hybrid AI approach to effectively and efficiently identify fraudulent medical insurance claims which has been tested in an online medical insurance claim system in China.

AAMAS Conference 2016 Conference Paper

A Hybrid Approach for Detecting Fraudulent Medical Insurance Claims (Extended Abstract)

• Chenfei Sun
• Yuliang Shi
• Qingzhong Li
• Lizhen Cui
• Han Yu
• Chunyan Miao

Medical insurance frauds are causing huge losses for public healthcare funds in many countries. Detecting medical insurance frauds is an important and difficult challenge. Because of the complex granularity of data, existing fraud detection approaches tend to be less effective in terms of recalling fraudulent claim behaviours. In this paper, we propose a Hybrid Fraud Detection Approach (HFDA) to address this problem, which is compared with four state-of-the-art approaches using a real-world dataset. Extensive experiment results show that the proposed approach is significantly more effective and efficient.

AAMAS Conference 2016 Conference Paper

A Kinect-based Interactive Game to Improve the Cognitive Inhibition of the Elderly (Demonstration)

• Siyuan Liu
• Zhiqi Shen
• Han Yu
• Han Lin
• Zhengjin Guo
• Zhengxiang Pan
• Chunyan Miao
• Cryil Leung

Cognitive abilities, including cognitive inhibition, degenerate with the aging process. In this demonstration, we present a Kinect-based interactive game which aims to improve the cognitive inhibition ability of the elderly. The game is designed in the table tennis theme, and the adoption of Kinect makes it convenient for the elderly to use. The players’ in-game behaviour data are recorded for the health advisor agent to conduct personalization, analysis, and decision making. A pilot study has been conducted to investigate the relationship between the players’ cognitive inhibition abilities and their in-game performance. The study results suggest that the in-game performance can reflect a player’s cognitive inhibition ability, and indicate that the game can be used to improve the cognitive inhibition ability of the elderly in the future.

AAMAS Conference 2016 Conference Paper

Coalitional Security Games

• Qingyu Guo
• Bo An
• Yevgeniy Vorobeychik
• Long Tran-Thanh
• Jiarui Gan
• Chunyan Miao

Game theoretic models of security, and associated computational methods, have emerged as critical components of security posture across a broad array of domains, including airport security and coast guard. These approaches consider terrorists as motivated but independent entities. There is, however, increasing evidence that attackers, be it terrorists or cyber attackers, communicate extensively and form coalitions that can dramatically increase their ability to achieve malicious goals. To date, such cooperative decision making among attackers has been ignored in the security games literature. To address the issue of cooperation among attackers, we introduce a novel coalitional security game (CSG) model. A CSG consists of a set of attackers connected by a (communication or trust) network who can form coalitions as connected subgraphs of this network so as to attack a collection of targets. A defender in a CSG can delete a set of edges, incurring a cost for deleting each edge, with the goal of optimally limiting the attackers’ ability to form effective coalitions (in terms of successfully attacking high value targets). We first show that a CSG is, in general, hard to approximate. Nevertheless, we develop a novel branch and price algorithm, leveraging a combination of column generation, relaxation, greedy approximation, and stabilization methods to enable scalable high-quality approximations of CSG solutions on realistic problem instances.

AAAI Conference 2016 Conference Paper

Efficient Collaborative Crowdsourcing

• Zhengxiang Pan
• Han Yu
• Chunyan Miao
• Cyril Leung

We consider the problem of making efficient quality-timecost trade-offs in collaborative crowdsourcing systems in which different skills from multiple workers need to be combined to complete a task. We propose CrowdAsm - an approach which helps collaborative crowdsourcing systems determine how to combine the expertise of available workers to maximize the expected quality of results while minimizing the expected delays. Analysis proves that CrowdAsm can achieve close to optimal profit for workers in a given crowdsourcing system if they follow the recommendations.

ECAI Conference 2016 Conference Paper

Explained Activity Recognition with Computational Assumption-Based Argumentation

• Xiuyi Fan
• Siyuan Liu 0003
• Huiguo Zhang
• Cyril Leung
• Chunyan Miao

Activity recognition is a key problem in multi-sensor systems. In this work, we introduce Computational Assumption-based Argumentation, an argumentation approach that seamlessly combines sensor data processing with high-level inference. Our method gives classification results comparable to machine learning based approaches with reduced training time while also giving explanations.

ECAI Conference 2016 Conference Paper

Identifying and Rewarding Subcrowds in Crowdsourcing

• Siyuan Liu 0003
• Xiuyi Fan
• Chunyan Miao

Identifying and rewarding truthful workers are key to the sustainability of crowdsourcing platforms. In this paper, we present a clustering based rewarding mechanism that rewards workers based on their truthfulness while accommodating the differences in workers' preferences. Experimental results show that the proposed approach can effectively discover subcrowds under various conditions, and truthful workers are better rewarded than less truthful ones.

AAMAS Conference 2016 Conference Paper

Modeling Autobiographical Memory in Human-Like Autonomous Agents

• Di Wang
• Ah-Hwee Tan
• Chunyan Miao

Although autobiographical memory is an important part of the human mind, there has been little effort on modeling autobiographical memory in autonomous agents. With the motivation of developing human-like intelligence, in this paper, we delineate our approach to enable an agent to maintain memories of its own and to wander in mind. Our model, named Autobiographical Memory-Adaptive Resonance Theory network (AM-ART), is designed to capture autobiographical memories, comprising pictorial snapshots of one’s life experiences together with the associated context, namely time, location, people, activity, and emotion. In terms of both network structure and dynamics, AM-ART coincides with the autobiographical memory model established by the psychologists, which has been supported by neural imaging evidence. Specifically, the bottomup memory search and the top-down memory readout operations of AM-ART replicate how the brain encodes and retrieves autobiographical memories. Furthermore, the wandering in reminiscence function of AM-ART mimics how human wanders in mind. For evaluations, we conducted experiments on a data set collected from the public domain to test the performance of AM-ART in response to exact, partial, and noisy memory retrieval cues. Moreover, our statistical analysis shows that AM-ART can simulate the phenomenon of wandering in reminiscence.

AAAI Conference 2016 Conference Paper

Multi-Agent System Development MADE Easy

• Zhiqi Shen
• Han Yu
• Chunyan Miao
• Siyao Li
• Yiqiang Chen

Agent-Oriented Software Engineering (AOSE) is an emerging software engineering paradigm that advocates the application of best practices in the development of Multi-Agent Systems (MAS) through the use of agents and organizations of agents. This paper outlines the MADE system, which provides an interactive platform for people who are not wellversed in AOSE to contribute to the rapid prototyping of MASs with ease.

IJCAI Conference 2016 Conference Paper

Optimal Interdiction of Illegal Network Flow

• Qingyu Guo
• Bo An
• Yair Zick
• Chunyan Miao

Large scale smuggling of illegal goods is a long-standing problem, with $1. 4b and thousands of agents assigned to protect the borders from such activity in the US-Mexico border alone. Illegal smuggling activities are usually blocked via inspection stations or ad-hoc checkpoints/roadblocks. Security resources are insufficient to man all stations at all times; furthermore, smugglers regularly conduct surveillance activities. This paper makes several contributions toward the challenging task of optimally interdicting an illegal network flow: i) A new Stackelberg game model for network flow interdiction; ii) A novel Column and Constraint Generation approach for computing the optimal defender strategy; iii) Complexity analysis of the column generation subproblem; iv) Compact convex nonlinear programs for solving the subproblems; v) Novel greedy and heuristic approaches for subproblems with good approximation guarantee. Experimental evaluation shows that our approach can obtain a robust enough solution outperforming the existing methods and heuristic baselines significantly and scale up to realistic-sized problems.

AAMAS Conference 2016 Conference Paper

Optimal Pricing for Efficient Electric Vehicle Charging Station Management

• Yanhai Xiong
• Jiarui Gan
• Bo An
• Chunyan Miao
• Yeng Chai Soh

The rapid development of Electric Vehicles (EVs) seen in recent years has been drawing increasing attentions from the public, markets, decision-makers, and academia. Notwithstanding the progress, issues still remain. Because of the widely complained disadvantages of limited battery capacity and long charging time, charging convenience has become a top concern that greatly hinders the adoption of EVs. Specialized EV charging station, which provides more than 10 times faster charging speed than domestic charging, is therefore a critical element for successful EV promotion. While most existing researches focus on optimizing spatial placement of charging stations, they are inflexible and inefficient against rapidly changing urban structure and traffic pattern. Therefore, this paper approaches the management of EV charging stations from the pricing perspective as a more flexible and adaptive complement to established charging station placement. In this paper, we build a realistic pricing model in consideration of residential travel pattern and EV drivers’ self-interested charging behavior, traffic congestion, and operating expense of charging stations. We formulate the pricing problem as a mixed integer non-convex optimization problem, and propose a scalable algorithm to solve it. Experiments on both mock and real data are also conducted, which show scalability of our algorithm as well as our solution’s significant improvement over existing approaches.

AAAI Conference 2016 Conference Paper

Productive Aging through Intelligent Personalized Crowdsourcing

• Han Yu
• Chunyan Miao
• Siyuan Liu
• Zhengxiang Pan
• Nur Syahidah Khalid
• Zhiqi Shen
• Cyril Leung

The current generation of senior citizens are enjoying unparalleled levels of good health than previous generations. The need for personal fulfilment after retirement has driven many of them to participate in productive aging activities such as volunteering. This paper outlines the Silver Productive (SP) mobile app, a system powered by the RTS-P intelligent personalized task sub-delegation approach with dynamic worker effort pricing functions. It provides an algorithmic crowdsourcing platform to enable seniors to contribute their effort through productive aging activities and help organizations ef- ficiently utilize seniors’ collective productivity.

IJCAI Conference 2015 Conference Paper

A Boosting Algorithm for Item Recommendation with Implicit Feedback

• Yong Liu
• Peilin Zhao
• Aixin Sun
• Chunyan Miao

Many recommendation tasks are formulated as top-N item recommendation problems based on users’ implicit feedback instead of explicit feedback. Here explicit feedback refers to users’ ratings to items while implicit feedback is derived from users’ interactions with items, e. g. , number of times a user plays a song. In this paper, we propose a boosting algorithm named AdaBPR (Adaptive Boosting Personalized Ranking) for top-N item recommendation using users’ implicit feedback. In the proposed framework, multiple homogeneous component recommenders are linearly combined to create an ensemble model, for better recommendation accuracy. The component recommenders are constructed based on a fixed collaborative filtering algorithm by using a re-weighting strategy, which assigns a dynamic weight distribution on the observed user-item interactions. AdaBPR demonstrates its effectiveness on three datasets compared with strong baseline algorithms.

TIST Journal 2015 Journal Article

Accurate and Robust Moving-Object Segmentation for Telepresence Systems

• Meiyu Huang
• Yiqiang Chen
• Wen Ji
• Chunyan Miao

Moving-object segmentation is the key issue of Telepresence systems. With monocular camera--based segmentation methods, desirable segmentation results are hard to obtain in challenging scenes with ambiguous color, illumination changes, and shadows. Approaches based on depth sensors often cause holes inside the object and missegmentations on the object boundary due to inaccurate and unstable estimation of depth data. This work proposes an adaptive multi-cue decision fusion method based on Kinect (which integrates a depth sensor with an RGB camera). First, the algorithm obtains an initial foreground mask based on the depth cue. Second, the algorithm introduces a postprocessing framework to refine the segmentation results, which consists of two main steps: (1) automatically adjusting the weight of two weak decisions to identify foreground holes based on the color and contrast cue separately; and (2) refining the object boundary by integrating the motion probability weighted temporal prior, color likelihood, and smoothness constraint. The extensive experiments we conducted demonstrate that our method can segment moving objects accurately and robustly in various situations in real time.

IJCAI Conference 2015 Conference Paper

An Adaptive Computational Model for Personalized Persuasion

• Yilin Kang
• Ah-Hwee Tan
• Chunyan Miao

While a variety of persuasion agents have been created and applied in different domains such as marketing, military training and health industry, there is a lack of a model which can provide a unified framework for different persuasion strategies. Specifically, persuasion is not adaptable to the individuals’ personal states in different situations. Grounded in the Elaboration Likelihood Model (ELM), this paper presents a computational model called Model for Adaptive Persuasion (MAP) for virtual agents. MAP is a semi-connected network model which enables an agent to adapt its persuasion strategies through feedback. We have implemented and evaluated a MAP-based virtual nurse agent who takes care and recommends healthy lifestyle habits to the elderly. Our experimental results show that the MAP-based agent is able to change the others’ attitudes and behaviors intentionally, interpret individual differences between users, and adapt to user’s behavior for effective persuasion.

AAAI Conference 2015 Conference Paper

Efficient Task Sub-Delegation for Crowdsourcing

• Han Yu
• Chunyan Miao
• Zhiqi Shen
• Cyril Leung
• Yiqiang Chen
• Qiang Yang

Reputation-based approaches allow a crowdsourcing system to identify reliable workers to whom tasks can be delegated. In crowdsourcing systems that can be modeled as multi-agent trust networks consist of resource constrained trustee agents (i. e. , workers), workers may need to further sub-delegate tasks to others if they determine that they cannot complete all pending tasks before the stipulated deadlines. Existing reputation-based decision-making models cannot help workers decide when and to whom to sub-delegate tasks. In this paper, we proposed a reputation aware task sub-delegation (RTS) approach to bridge this gap. By jointly considering a worker’s reputation, workload, the price of its effort and its trust relationships with others, RTS can be implemented as an intelligent agent to help workers make sub-delegation decisions in a distributed manner. The resulting task allocation maximizes social welfare through efficient utilization of the collective capacity of a crowd, and provides provable performance guarantees. Experimental comparisons with state-of-the-art approaches based on the Epinions trust network demonstrate significant advantages of RTS under high workload conditions.

IJCAI Conference 2015 Conference Paper

Optimal Electric Vehicle Charging Station Placement

• Yanhai Xiong
• Jiarui Gan
• Bo An
• Chunyan Miao
• Ana L. C. Bazzan

Many countries like Singapore are planning to introduce Electric Vehicles (EVs) to replace traditional vehicles to reduce air pollution and improve energy efficiency. The rapid development of EVs calls for efficient deployment of charging stations both for the convenience of EVs and maintaining the efficiency of the road network. Unfortunately, existing work makes unrealistic assumption on EV drivers’ charging behaviors and focus on the limited mobility of EVs. This paper studies the Charging Station PLacement (CSPL) problem, and takes into consideration 1) EV drivers’ strategic behaviors to minimize their charging cost, and 2) the mutual impact of EV drivers’ strategies on the traffic conditions of the road network and service quality of charging stations. We first formulate the CSPL problem as a bilevel optimization problem, which is subsequently converted to a single-level optimization problem by exploiting structures of the EV charging game. Properties of CSPL problem are analyzed and an algorithm called OCEAN is proposed to compute the optimal allocation of charging stations. We further propose a heuristic algorithm OCEAN-C to speed up OCEAN. Experimental results show that the proposed algorithms significantly outperform baseline methods.

AAAI Conference 2014 Conference Paper

Learning Relative Similarity by Stochastic Dual Coordinate Ascent

• Pengcheng Wu
• Yi Ding
• Peilin Zhao
• Chunyan Miao
• Steven Hoi

Learning relative similarity from pairwise instances is an important problem in machine learning and has a wide range of applications. Despite being studied for years, some existing methods solved by Stochastic Gradient Descent (SGD) techniques generally suffer from slow convergence. In this paper, we investigate the application of Stochastic Dual Coordinate Ascent (SDCA) technique to tackle the optimization task of relative similarity learning by extending from vector to matrix parameters. Theoretically, we prove the optimal linear convergence rate for the proposed SDCA algorithm, beating the well-known sublinear convergence rate by the previous best metric learning algorithms. Empirically, we conduct extensive experiments on both standard and large-scale data sets to validate the effectiveness of the proposed algorithm for retrieval tasks.

AAAI Conference 2014 Conference Paper

RepRev: Mitigating the Negative Effects of Misreported Ratings

• Yuan Liu
• Siyuan Liu
• Jie Zhang
• Hui Fang
• Han Yu
• Chunyan Miao

Reputation models depend on the ratings provided by buyers to gauge the reliability of sellers in multi-agent based e-commerce environment. However, there is no prevention for the cases in which a buyer misjudges a seller, and provides a negative rating to an original satisfactory transaction. In this case, how should the seller get his reputation repaired and utility loss recovered? In this work, we propose a mechanism to mitigate the negative effect of the misreported ratings. It temporarily inflates the reputation of the victim seller with a certain value for a period of time. This allows the seller to recover his utility loss due to lost opportunities caused by the misreported ratings. Experiments demonstrate the necessity and effectiveness of the proposed mechanism.

AAAI Conference 2014 Conference Paper

Reputation-Aware Continuous Double Auction

• Yuan Liu
• Jie Zhang
• Han Yu
• Chunyan Miao

Truthful bidding is a desirable property for continuous double auctions (CDAs). Many incentive mechanisms have been proposed to elicit truthful bids. However, existing truthful CDA mechanisms often overlook the possibility that sellers may choose not to deliver the auctioned items to buyers as promised. In this situation, buyers may become unwilling to bid their true valuations in the future to compensate for their risks of being cheated, thereby rendering CDAs ineffective. In this paper, we propose a novel reputation-aware CDA (named RCDA) mechanism to consider the honesty of auction participants. It dynamically adjusts bids and asks according to the reputation of participants to reflect the risks involved in the transactions. Theoretical analysis proves that RCDA is effective in eliciting truthful bids from buyers and sellers in the presence of possible dishonest behavior from both buyers and sellers.

IJCAI Conference 2013 Conference Paper

A Reputation Management Approach for Resource Constrained Trustee Agents

• Han Yu
• Chunyan Miao
• Bo An
• Cyril Leung
• Victor R. Lesser

Trust is an important mechanism enabling agents to self-police open and dynamic multi-agent systems (ODMASs). Trusters evaluate the reputation of trustees based on their past observed performance, and use this information to guide their future interaction decisions. Existing trust models tend to concentrate trusters’ interactions on a small number of highly reputable trustees to minimize risk exposure. When a trustee’s servicing capacity is limited, such an approach may cause long delays for trusters and subsequently damage the reputation of trustees. To mitigate this problem, we propose a reputation management approach for trustee agents based on distributed constraint optimization. It helps a trustee to make situation-aware decisions on which incoming requests to serve and prevent the resulting reputation score from being affected by factors out of the trustee’s control. The approach is evaluated through theoretical analysis and within a simulated, highly dynamic multi-agent environment. The results show that it can achieve close to optimally efficient utilization of the trustee agents’ collective capacity in an ODMAS, promotes fair treatment of trustee agents based on their behavior, and significantly outperforms related work in enhancing social welfare.

AAMAS Conference 2013 Conference Paper

A Reputation-aware Decision-making Approach for Improving the Efficiency of Crowdsourcing Systems

• Han Yu
• Zhiqi Shen
• Chunyan Miao
• Bo An

A crowdsourcing system is a useful platform for utilizing the intelligence and skills of the mass. Nevertheless, like any open system that involves the exchange of things of value, selfish and malicious behaviors exist in crowdsourcing systems and need to be mitigated. Trust management has been proven to be a viable solution in many systems. However, a major difference between crowdsourcing systems and existing trust models designed for multi-agent systems is that human trustees have limited task processing capacity per unit time compared to an intelligent agent program. This paper recognizes a problem in current trust-aware decision-making methods for task assignment in crowdsourcing platforms. On the one hand, trust-based methods over-assign tasks to trusted workers, while on the other hand, workload-based solutions do not give sufficient guarantees on the quality of work. The proposed solution, the social welfare optimizing reputation-aware decision-making (SWORD) approach, strikes a balance between the two and is shown through extensive simulations to significantly improve social welfare of crowdsourcing platforms compared to related work.

AAMAS Conference 2013 Conference Paper

The Innovative Application of Learning Companions in Virtual Singapura

• Qiong Wu
• Xiaogang Han
• Han Yu
• Zhiqi Shen
• Chunyan Miao

Virtual Singapura (VS) is a virtual world based learning environment designed to facilitate learning of the plant transport system. During field studies of VS, we observed that students in virtual world tend to be attracted by visual and auditorial stimuli and be distracted from learning objectives. Also, intensive cognitive load can affect students’ learning experience. To address these issues, we propose two types of companion agent, namely curious companion and remembrance companion. Results collected from the field studies indicate advantages of learning companion augmented virtual world in enhancing students’ learning experience.

AAMAS Conference 2012 Conference Paper

A Dempster-Shafer Theory Based Witness Trustworthiness Model

• Siyuan Liu
• Alex C. Kot
• Chunyan Miao
• Yin-Leng Theng

The problem of unfair testimonies remains to be a big concern in reputation systems. To address this problem, we propose a witness trustworthiness model based on Dempster- Shafer theory for reputation systems using multi-nominal testimonies. The proposed approach uses Dempster-Shafer theory to model a witness’s trustworthiness from both personal and public aspects. Experimental evaluation demonstrates promising results of the proposed approach in modeling witnesses’ trustworthiness and adapting to the buyer specified subjective difference tolerance level.

AAAI Conference 2012 Conference Paper

A Mouse-Trajectory Based Model for Predicting Query-URL Relevance

• Song Hengjie
• Ruoxue Liao
• Xiangliang Zhang
• Chunyan Miao
• Qiang Yang

For the learning to ranking algorithms used in commercial search engines, a conventional way to generate the training examples is to employ professional annotators to label the relevance of query url pairs. Since label quality depends on the expertise of annotators to a large extent, this process is time consuming and labor intensive. Automatically generating labels from click through data has been well studied to have comparable or better performance than human judges. Click through data present users’ action and imply their satisfaction on search results, but exclude the interactions between users and search results beyond the page view level (e. g. , eye and mouse movements). This paper proposes a novel approach to comprehensively consider the information underlying mouse trajectory and click through data so as to describe user behaviors more objectively and achieve a better understanding of the user experience. By integrating multi sources data, the proposed approach reveals that the relevance labels of query url pairs are related to positions of urls and users’ behavioral features. Based on their correlations, query url pairs can be labeled more accurately and search results are more satisfactory to users. The experiments that are conducted on the most popular Chinese commercial search engine (Baidu) validated the rationality of our research motivation and proved that the proposed approach outperformed the state of the art methods.

AAMAS Conference 2012 Conference Paper

Virtual Characters in Agent-Augmented Co-Space

• Yi-Lin Kang
• Budhitama Subagdja
• Ah-Hwee Tan
• Yew-Soon Ong
• Chunyan Miao

Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nanyang Technological University (NTU) Co-Space populated with virtual human characters. In order to create realistic virtual humans, we have designed a brain-inspired agent architecture with the properties of goal-directed autonomy, natural interactivity and human-like personification. The demo will show how the virtual characters may enhance the interactivity and playability of the virtual worlds.

AAMAS Conference 2011 Conference Paper

A Simple Curious Agent to Help People be Curious

• Han Yu
• Zhiqi Shen
• Chunyan Miao
• Ah-Hwee Tan

Curiosity is an innately rewarding state of mind that, over the millennia, has driven the human race to explore and discover. Many researches in pedagogical science have confirmed the importance of being curious to the students' cognitive development. However, in the newly popular virtual world-based learning environments (VLEs), there is currently a lack of attention being paid to enhancing the learning experience by stimulating the learners' curiosity. In this paper, we propose a simple model for curious agents (CAs) which can be used to stimulate learners' curiosity in VLEs. Potential future research directions will be discussed.

AAAI Conference 2011 Conference Paper

Generating True Relevance Labels in Chinese Search Engine Using Clickthrough Data

• Hengjie Song
• Chunyan Miao
• Zhiqi Shen

In current search engines, ranking functions are learned from a large number of labeled pairs in which the labels are assigned by human judges, describing how well the URLs match the different queries. However in commercial search engines, collecting high quality labels is time-consuming and labor-intensive. To tackle this issue, this paper studies how to produce the true relevance labels for pairs using clickthrough data. By analyzing the correlations between query frequency, true relevance labels and users’ behaviors, we demonstrate that the users who search the queries with similar frequency have similar search intents and behavioral characteristics. Based on such properties, we propose an efficient discriminative parameter estimation in a multiple instance learning algorithm (MIL) to automatically produce true relevance labels for pairs. Furthermore, we test our approach using a set of real world data extracted from a Chinese commercial search engine. Experimental results not only validate the effectiveness of the proposed approach, but also indicate that our approach is more likely to agree with the aggregation of the multiple judgments when strong disagreements exist in the panel of judges. In the event that the panel of judges is consensus, our approach provides more accurate automatic label results. In contrast with other models, our approach effectively improves the correlation between automatic labels and manual labels.

AAMAS Conference 2011 Conference Paper

Genetic Algorithm Aided Optimization of Hierarchical Multiagent System Organization

• Ling Yu
• Zhiqi Shen
• Chunyan Miao
• Victor Lesser

In this paper, we propose a genetic algorithm aided optimization scheme for designing the organization of hierarchical multiagent systems. We introduce the hierarchical genetic algorithm, in which hierarchical crossover with a repair strategy and mutation of small perturbation are used. The phenotypic hierarchical structure space is translated to the genome-like array representation space, which makes the algorithm genetic-operator-literate. Our experiments show that competitive structures can be found by the proposed algorithm. Compared with traditional operators, the new operators produced better organizations of higher utility more consistently. The proposed algorithm extends the search processes of the state-of-the-art multiagent organization design methodologies, and is more computationally efficient in a large search space.

AAMAS Conference 2011 Conference Paper

iCLUB: An Integrated Clustering-Based Approach to Improve the Robustness of Reputation Systems

• Siyuan Liu
• Jie Zhang
• Chunyan Miao
• Yin-Leng Theng
• Alex C. Kot

The problem of unfair testimonies has to be addressed effectively to improve the robustness of reputation systems. We propose an integrated CLU stering- B ased approach called iCLUB to filter unfair testimonies for reputation systems using multi-nominal testimonies, in multiagent-based electronic commerce. It adopts clustering and considers buying agents' local and global knowledge about selling agents. Experimental evaluation demonstrates promising results of our approach in filtering various types of unfair testimonies.

AAMAS Conference 2010 Conference Paper

A Clustering Approach to Filtering Unfair Testimonies for Reputation Systems

• Siyuan Liu
• Chunyan Miao
• Yin-Leng Theng
• Alex Kot

The problem of unfair testimonies remains an open issuein reputation systems for online trading communities. Acommon attempt is to use binary ratings to model sellers'reputation. However, this attempt leads to that the researchof tackling unfair testimonies also focuses on reputation systems using binary ratings. In this extended abstract, wepropose a two-stage clustering approach to filter unfair testimonies for reputation systems using multi-nominal ratings. The proposed approach uses clustering to identify unfair testimonies and further contributes to providing buyers a moreaccurate reputation evaluation regarding the target seller.

ECAI Conference 2010 Conference Paper

Predicting Responsiveness of BDI Agent

• Huiliang Zhang
• Zhiqi Shen 0001
• Shell-Ying Huang
• Chunyan Miao

A performance mark of a BDI agent is how fast it can react to and process incoming event sequences. To the best of our knowledge, few papers have been published about predicting an agent's average response time for an event sequence before the agent is applied in a real project. In this paper, we first introduce a simulation method. In simulation, a sequence of events with attributes, such as priorities and amounts of time needed to process the events, is input to the agent at designed insertion time. The events are processed by the agent according to the attributes. The statistics of processing time can be recorded. Then we make some theoretical analysis to estimate the average response time when an agent processes a sequence of events based on probability and queueing theory. Comparison experiments show that the results from analysis are quite matching with the results from simulation experiments. The analysis suggests a way to quickly estimate the performance of an agent if the attributes of the incoming event sequence are known in advance. The predicted average response time can help construct efficient BDI agents for various environments.

IJCAI Conference 2007 Conference Paper

• Bo An
• Chunyan Miao
• Zhiqi Shen

Although there are some research efforts toward resource allocation in multi-agent systems (MAS), most of these work assume that each agent has complete information about other agents. This research investigates interactions among selfish, rational, and autonomous agents in resource allocation, each with incomplete information about other entities, and each seeking to maximize its expected utility. This paper presents a proportional resource allocation mechanism and gives a game theoretical analysis of the optimal strategies and the analysis shows the existence of equilibrium in the incomplete information setting. By augmenting the resource allocation mechanism with a deal optimization mechanism, trading agents can be programmed to optimize resource allocation results by updating beliefs and resubmitting bids. Experimental results showed that by having a deal optimization stage, the resource allocation mechanism produced generally optimistic outcomes (close to market equilibrium).

AAMAS Conference 2006 Conference Paper

Trust-based Agent Community for Collaborative Recommendation

• Jianshu Weng
• Chunyan Miao
• Angela Goh