Can Wang

JBHI Journal 2026 Journal Article

DF-DiffVSR: Deformable Field-Driven Diffusion Model for Inter-Slice Continuity Enhancement in Medical Volume Super-Resolution

• Can Wang
• Min Liu
• Qinghao Liu
• Yuehao Zhu
• Xiang Chen
• Licheng Liu
• Yaonan Wang
• Erik Meijering

Medical volumetric imaging is crucial for precise diagnosis, but limited by equipment and acquisition constraints, anisotropic resolution leads to challenges in detecting small lesions and 3D visualization. While volumetric super-resolution methods can mitigate this issue, existing techniques suffer from limited receptive fields, failing to fully exploit inter-slice correlations and resulting in compromised inter-slice continuity. To address this limitation, we propose DF-DiffVSR, a novel deformable field-enhanced diffusion model for medical volume super resolution. The proposed method integrates optical flow principles with diffusion models through a Deformable Field Extraction (DFE) module, which explicitly learns inter slice motion information to enhance structural continuity in the through-plane direction. Furthermore, we design a Multiscale Large Kernel Convolution (MLKC) module that employs striped convolutions with varying kernel sizes to expand the receptive field and capture global anatomical context. Evaluated on RPLHR-CT and IXI-T2 datasets, DF DiffVSR achieves state-of-the-art (SOTA) performance, surpassing the sub-optimal method by 0. 732 dB and 0. 214 dB in PSNR, respectively, demonstrating superior capabilities in preserving inter-slice continuity and recovering fine grained details.

AAAI Conference 2026 Conference Paper

DICE: Distilling Classifier-Free Guidance into Text Embeddings

• Zhenyu Zhou
• Defang Chen
• Can Wang
• Chun Chen
• Siwei Lyu

Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely with the given text prompts. Classifier-free guidance (CFG) is a popular and effective technique for improving text-image alignment in the generative process. However, CFG introduces significant computational overhead. In this paper, we present DIstilling CFG by sharpening text Embeddings (DICE) that replaces CFG in the sampling process with half the computational complexity while maintaining similar generation quality. DICE distills a CFG-based text-to-image diffusion model into a CFG-free version by refining text embeddings to replicate CFG-based directions. In this way, we avoid the computational drawbacks of CFG, enabling high-quality, well-aligned image generation at a fast sampling speed. Furthermore, examining the enhancement pattern, we identify the underlying mechanism of DICE that sharpens specific components of text embeddings to preserve semantic information while enhancing fine-grained details. Extensive experiments on multiple Stable Diffusion v1.5 variants, SDXL, and PixArt-\alpha demonstrate the effectiveness of our method.

AAAI Conference 2026 Conference Paper

SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning

• Xiaoda Yang
• Shenzhou Gao
• Can Wang
• Jiahe Zhang
• Menglan Tang
• Jingyang Xue
• Sheng Liu
• Peijian Zhang

Vision-Language Models (VLMs) have made significant progress in static perception, but their ability to understand dynamic task-oriented reasoning remains unclear. Existing benchmarks mainly focus on static spatial relationships and lack systematic assessment of dynamic reasoning capabilities. To this end, we propose SpatialLogic-Bench, a novel benchmark designed to evaluate VLMs’ understanding of spatiotemporal logic and their ability to assess task progress. The benchmark assesses two critical capabilities: first, fine-grained visual discrimination to accurately perceive subtle physical changes between state frames; second, the logical capacity to connect these changes to task goals and judge whether they indicate progress. To mitigate temporal dependency biases, we introduce a dual-task paradigm, presenting image pairs in both chronological and reversed orders while keeping task descriptions consistent. We construct a multi-scale evaluation system by varying time intervals between frames: smaller intervals test the model's fine-grained perception, while larger intervals demand more sophisticated logical inference. Empirical evaluation reveals that most VLMs experience significant performance degradation on tasks presented in inverse chronological order, indicating an over-reliance on temporal cues rather than robust reasoning abilities. SpatialLogic-Bench clearly exposes critical limitations in current models and provides valuable guidance for improving dynamic spatial perception capabilities.

AAAI Conference 2025 Conference Paper

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution

• Shengjia Zhang
• Jiawei Chen
• Changdong Li
• Sheng Zhou
• Qihao Shi
• Yan Feng
• Chun Chen
• Can Wang

Loss functions play a pivotal role in optimizing recommendation models. Among various loss functions, Softmax Loss (SL) and Cosine Contrastive Loss (CCL) are particularly effective. Their theoretical connections and differences warrant in-depth exploration. This work conducts comprehensive analyses of these losses, yielding significant insights: 1) Common strengths --- both can be viewed as augmentations of traditional losses with Distributional Robust Optimization (DRO), enhancing robustness to distributional shifts; 2) Respective limitations --- stemming from their use of different distribution distance metrics in DRO optimization, SL exhibits high sensitivity to false negative instances, whereas CCL suffers from low data utilization. To address these limitations, this work proposes a new loss function, DrRL, which generalizes SL and CCL by leveraging Rényi-divergence in DRO optimization. DrRL incorporates the advantageous structures of both SL and CCL, and can be demonstrated to effectively mitigate their limitations. Extensive experiments have been conducted to validate the superiority of DrRL on both recommendation accuracy and robustness.

IROS Conference 2025 Conference Paper

Automated Dual-Micropipette Coordination Microinjection for Batch Zebrafish Larvae Based on Pose Estimation

• Can Wang
• Rongxin Liu
• Huiying Gong
• Zengshuo Wang
• Lu Zhou
• Yaowei Liu
• Xin Zhao 0010
• Mingzhu Sun

Zebrafish are widely used in the biomedical field, as an ideal model for microinjection. In automated zebrafish microinjection, posture adjustment is the first and key step, which takes a lot of skill, and injection success assessment is a challenging task. Constrained by these two aspects, it is difficult to further enhance the efficiency and success rate of injection. In this study, we propose an automated dual-micropipette coordination microinjection system. Zebrafish are randomly arranged in our system, reducing the operational difficulty, and the yolk is positioned using a pose estimation algorithm, followed by injection accomplished with dual-micropipette. Due to the reduction of posture adjustment time by half, the proposed system achieves the shortest injection time of 15. 2s. Moreover, the simplicity of the system and the ease of operation contribute to the clinical feasibility of our system.

EAAI Journal 2025 Journal Article

Calculating of stomatal index for tomato and lettuce based on You Only Look Once version 8 and improved High-Resolution Network

• Yang Xu
• Li Du
• Qingrui Zhu
• Can Wang
• Liyuan Zhang
• Yaxiao Niu
• Qi Li
• Danyan Chen

TMLR Journal 2025 Journal Article

Conditional Image Synthesis with Diffusion Models: A Survey

• Zheyuan Zhan
• Defang Chen
• Jian-Ping Mei
• Zhenghe Zhao
• Jiawei Chen
• Chun Chen
• Siwei Lyu
• Can Wang

Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis, leading to exponential growth in the literature. However, the complexity of diffusion-based modeling, the wide range of image synthesis tasks, and the diversity of conditioning mechanisms present significant challenges for researchers to keep up with rapid developments and to understand the core concepts on this topic. In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i.e., the denoising network and the sampling process. We specifically highlight the underlying principles, advantages, and potential challenges of various conditioning approaches during the training, re-purposing, and specialization stages to construct a desired denoising network. We also summarize six mainstream conditioning mechanisms in the sampling process. All discussions are centered around popular applications. Finally, we pinpoint several critical yet still unsolved problems and suggest some possible solutions for future research.

TMLR Journal 2025 Journal Article

Lie Symmetry Net: Preserving Conservation Laws in Modelling Financial Market Dynamics via Differential Equations

• Xuelian Jiang
• Tongtian Zhu
• Yingxiang Xu
• Can Wang
• Yeyu Zhang
• Fengxiang He

This paper employs a novel Lie symmetries-based framework to model the intrinsic symmetries within financial market. Specifically, we introduce Lie symmetry net (LSN), which characterises the Lie symmetries of the differential equations (DE) estimating financial market dynamics, such as the Black-Scholes equation. To simulate these differential equations in a symmetry-aware manner, LSN incorporates a Lie symmetry risk derived from the conservation laws associated with the Lie symmetry operators of the target differential equations. This risk measures how well the Lie symmetries are realised and guides the training of LSN under the structural risk minimisation framework. Extensive numerical experiments demonstrate that LSN effectively realises the Lie symmetries and achieves an error reduction of more than one order of magnitude compared to state-of-the-art methods. The code is available at https://github.com/Jxl163/LSN_code.

IJCAI Conference 2025 Conference Paper

M^2LLM: Multi-view Molecular Representation Learning with Large Language Models

• Jiaxin Ju
• Yizhen Zheng
• Huan Yee Koh
• Can Wang
• Shirui Pan

Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose M^2LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that M^2LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.

IS Journal 2025 Journal Article

Point-of-Interest Recommendations and Large Language Models: A Powerful Combination

• Tianxing Wang
• Can Wang

Point-of-interest (POI) recommendation systems have become a cornerstone of personalized user experiences in various applications, such as navigation, tourism, and retail. Recent advancements in artificial intelligence, particularly the integration of large language models (LLMs), have opened new possibilities for building a more powerful and comprehensive POI recommendation system. This work first reviews the latest research outcomes that leverage LLMs for POI recommendation, highlighting their contribution to dealing with the long-standing challenges of POI recommendation systems. Furthermore, we identify untapped potentials of LLM-based POI recommenders across the recommendation pipeline, encompassing multimodal feature augmentation, unified encoding, hybrid task learning for scoring and ranking, and dynamic user interaction. By exploring these opportunities, future research can transform POI recommendation systems into adaptive, user-centric assistants, delivering seamless, scalable, and personalized experiences. This article aims to provide a comprehensive overview of recent advancements and propose future directions for leveraging LLMs to redefine the next generation of POI recommendation systems.

JBHI Journal 2024 Journal Article

An Eye Movement Classification Method Based on Cascade Forest

• Can Wang
• Ruimin Wang
• Yue Leng
• Keiji Iramina
• Yuankui Yang
• Sheng Ge

Eye tracking technology has become increasingly important in scientific research and practical applications. In the field of eye tracking research, analysis of eye movement data is crucial, particularly for classifying raw eye movement data into eye movement events. Current classification methods exhibit considerable variation in adaptability across different participants, and it is necessary to address the issues of class imbalance and data scarcity in eye movement classification. In the current study, we introduce a novel eye movement classification method based on cascade forest (EMCCF), which comprises two modules: 1) a feature extraction module that employs a multi-scale time window method to extract features from raw eye movement data; 2) a classification module that innovatively employs a layered ensemble architecture, integrating the cascade forest structure with ensemble learning principles, specifically for eye movement classification. Consequently, EMCCF not only enhanced the accuracy and efficiency of eye movement classification but also represents an advancement in applying ensemble learning techniques within this domain. Furthermore, experimental results indicated that EMCCF outperformed existing deep learning-based classification models in several metrics and demonstrated robust performance across different datasets and participants.

IS Journal 2024 Journal Article

Embracing LLMs for Point-of-Interest Recommendations

• Tianxing Wang
• Can Wang

A point-of-interest (POI) recommendation becomes the core function of location-based services. Unlike a traditional item recommendation, a POI recommendation has distinct features, such as geographical influences, complex mobility patterns, and a balance between local and global user preferences. Past POI recommendation system research has focused mainly on integrating deep learning models like convolutional neural networks, recurrent neural networks, and attention-based architectures, demonstrating their effectiveness in addressing the dynamic nature of spatial–temporal data in POI recommendation areas. In recent years, with the rise of large language models (LLMs), POI recommendation has produced a number of promising directions. This article first discusses the characteristics and state-of-the-art solutions of POI recommendation, then it introduces potential research directions by integrating the latest LLMs.

YNICL Journal 2024 Journal Article

Neuroimaging of motor recovery after ischemic stroke − functional reorganization of motor network

• Pei Yu
• Ruoyu Dong
• Xiao Wang
• Yuqi Tang
• Yaning Liu
• Can Wang
• Ling Zhao

NeurIPS Conference 2024 Conference Paper

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

• Weiqin Yang
• Jiawei Chen
• Xin Xin
• Sheng Zhou
• Binbin Hu
• Yan Feng
• Chun Chen
• Can Wang

Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant limitations: 1) the relationship between SL and conventional ranking metrics like DCG is not sufficiently tight; 2) SL is highly sensitive to false negative instances. Our analysis indicates that these limitations are primarily due to the use of the exponential function. To address these issues, this work extends SL to a new family of loss functions, termed Pairwise Softmax Loss (PSL), which replaces the exponential function in SL with other appropriate activation functions. While the revision is minimal, we highlight three merits of PSL: 1) it serves as a tighter surrogate for DCG with suitable activation functions; 2) it better balances data contributions; and 3) it acts as a specific BPR loss enhanced by Distributionally Robust Optimization (DRO). We further validate the effectiveness and robustness of PSL through empirical experiments. The code is available at https: //github. com/Tiny-Snow/IR-Benchmark.

NeurIPS Conference 2024 Conference Paper

Simple and Fast Distillation of Diffusion Models

• Zhenyu Zhou
• Defang Chen
• Can Wang
• Chun Chen
• Siwei Lyu

Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based accelerated sampling methods have been developed recently. However, they generally require time-consuming fine tuning with elaborate designs to achieve satisfactory performance in a specific number of function evaluation (NFE), making them difficult to employ in practice. To address this issue, we propose **S**imple and **F**ast **D**istillation (SFD) of diffusion models, which simplifies the paradigm used in existing methods and largely shortens their fine-tuning time up to $1000\times$. We begin with a vanilla distillation-based sampling method and boost its performance to state of the art by identifying and addressing several small yet vital factors affecting the synthesis efficiency and quality. Our method can also achieve sampling with variable NFEs using a single distilled model. Extensive experiments demonstrate that SFD strikes a good balance between the sample quality and fine-tuning costs in few-step image generation task. For example, SFD achieves 4. 53 FID (NFE=2) on CIFAR-10 with only **0. 64 hours** of fine-tuning on a single NVIDIA A100 GPU.

NeurIPS Conference 2023 Conference Paper

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

• Zhiyao Zhou
• Sheng Zhou
• Bochao Mao
• Xuanyi Zhou
• Jiawei Chen
• Qiaoyu Tan
• Daochen Zha
• Yan Feng

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptimal nature of node connections, resulting from the complex and contingent formation process of graphs, presents significant challenges in modeling them effectively. To tackle this issue, Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models. Despite the proposal of numerous GSL methods, the progress in this field remains unclear due to inconsistent experimental protocols, including variations in datasets, data processing techniques, and splitting strategies. In this paper, we introduce OpenGSL, the first comprehensive benchmark for GSL, aimed at addressing this gap. OpenGSL enables a fair comparison among state-of-the-art GSL methods by evaluating them across various popular datasets using uniform data processing and splitting strategies. Through extensive experiments, we observe that existing GSL methods do not consistently outperform vanilla GNN counterparts. We also find that there is no significant correlation between the homophily of the learned structure and task performance, challenging the common belief. Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption. We hope that our open-sourced library will facilitate rapid and equitable evaluation and inspire further innovative research in this field. The code of the benchmark can be found in https: //github. com/OpenGSL/OpenGSL.

AAAI Conference 2023 Conference Paper

Robust Sequence Networked Submodular Maximization

• Qihao Shi
• Bingyang Fu
• Can Wang
• Jiawei Chen
• Sheng Zhou
• Yan Feng
• Chun Chen

In this paper, we study the Robust optimization for sequence Networked submodular maximization (RoseNets) problem. We interweave the robust optimization with the sequence networked submodular maximization. The elements are connected by a directed acyclic graph and the objective function is not submodular on the elements but on the edges in the graph. Under such networked submodular scenario, the impact of removing an element from a sequence depends both on its position in the sequence and in the network. This makes the existing robust algorithms inapplicable and calls for new robust algorithms. In this paper, we take the first step to study the RoseNets problem. We design a robust greedy algorithms, which is robust against the removal of an arbitrary subset of the selected elements. The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology. We further conduct experiments on real applications of recommendation and link prediction. The experimental results demonstrate the effectiveness of the proposed algorithm.

ICLR Conference 2022 Conference Paper

Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization

• Can Wang
• Sheng Jin 0007
• Yingda Guan
• Wentao Liu 0002
• Chen Qian 0006
• Ping Luo 0002
• Wanli Ouyang

Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an ever-growing interest in semi-supervised learning (SSL), which leverages a small set of labeled data along with a large set of unlabeled data. Among these SSL approaches, pseudo-labeling (PL) is one of the most popular. PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively. The key to the success of PL is the selection of high-quality pseudo-labeled samples. Previous works mostly select training samples by manually setting a single confidence threshold. We propose to automatically select reliable pseudo-labeled samples with a series of dynamic thresholds, which constitutes a learning curriculum.Extensive experiments on five keypoint localization benchmark datasets demonstrate that the proposed approach significantly outperforms the previous state-of-the-art SSL approaches.

AAAI Conference 2021 Conference Paper

Cross-Layer Distillation with Semantic Calibration

• Defang Chen
• Jian-Ping Mei
• Yuan Zhang
• Can Wang
• Zhe Wang
• Yan Feng
• Chun Chen

Recently proposed knowledge distillation approaches based on feature-map transfer validate that intermediate layers of a teacher model can serve as effective targets for training a student model to obtain better generalization ability. Existing studies mainly focus on particular representation forms for knowledge transfer between manually specified pairs of teacher-student intermediate layers. However, semantics of intermediate layers may vary in different networks and manual association of layers might lead to negative regularization caused by semantic mismatch between certain teacherstudent layer pairs. To address this problem, we propose Semantic Calibration for Cross-layer Knowledge Distillation (SemCKD), which automatically assigns proper target layers of the teacher model for each student layer with an attention mechanism. With a learned attention distribution, each student layer distills knowledge contained in multiple layers rather than a single fixed intermediate layer from the teacher model for appropriate cross-layer supervision in training. Consistent improvements over state-of-the-art approaches are observed in extensive experiments with various network architectures for teacher and student models, demonstrating the effectiveness and flexibility of the proposed attention based soft layer association mechanism for cross-layer distillation.

IS Journal 2021 Journal Article

Learning Complex Couplings and Interactions

• Can Wang
• Fosca Giannotti
• Longbing Cao

This special issue on learning complex couplings and interactions aims to encourage deep research in the above areas and beyond, with a focus on the latest advancements in modeling complex couplings and interactions in big data, complex behaviors, and systems.

TCS Journal 2021 Journal Article

Profit maximization for competitive social advertising

• Qihao Shi
• Can Wang
• Deshi Ye
• Jiawei Chen
• Sheng Zhou
• Yan Feng
• Chun Chen
• Yanhao Huang

NeurIPS Conference 2020 Conference Paper

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

• Lei Bai
• Lina Yao
• Can Li
• Xianzhi Wang
• Can Wang

Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.

AAAI Conference 2020 Conference Paper

DGE: Deep Generative Network Embedding Based on Commonality and Individuality

• Sheng Zhou
• Xin Wang
• Jiajun Bu
• Martin Ester
• Pinggang Yu
• Jiawei Chen
• Qihao Shi
• Can Wang

Network embedding plays a crucial role in network analysis to provide effective representations for a variety of learning tasks. Existing attributed network embedding methods mainly focus on preserving the observed node attributes and network topology in the latent embedding space, with the assumption that nodes connected through edges will share similar attributes. However, our empirical analysis of real-world datasets shows that there exist both commonality and individuality between node attributes and network topology. On the one hand, similar nodes are expected to share similar attributes and have edges connecting them (commonality). On the other hand, each information source may maintain individual differences as well (individuality). Simultaneously capturing commonality and individuality is very challenging due to their exclusive nature and existing work fail to do so. In this paper, we propose a deep generative embedding (DGE) framework which simultaneously captures commonality and individuality between network topology and node attributes in a generative process. Stochastic gradient variational Bayesian (SGVB) optimization is employed to infer model parameters as well as the node embeddings. Extensive experiments on four real-world datasets show the superiority of our proposed DGE framework in various tasks including node classification and link prediction.

AAAI Conference 2020 Conference Paper

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

• Jiawei Chen
• Can Wang
• Sheng Zhou
• Qihao Shi
• Jingbang Chen
• Yan Feng
• Chun Chen

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user’s preference; or adaptively infer personalized con- fidence weights but suffer from low efficiency. To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batchbased learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on realworld datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.

AAAI Conference 2020 Conference Paper

Online Knowledge Distillation with Diverse Peers

• Defang Chen
• Jian-Ping Mei
• Can Wang
• Yan Feng
• Chun Chen

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate predictions of multiple student models as targets to train each student model. Although group-derived targets give a good recipe for teacher-free distillation, group members are homogenized quickly with simple aggregation functions, leading to early saturated solutions. In this work, we propose Online Knowledge Distillation with Diverse peers (OKDDip), which performs two-level distillation during training with multiple auxiliary peers and one group leader. In the first-level distillation, each auxiliary peer holds an individual set of aggregation weights generated with an attention-based mechanism to derive its own targets from predictions of other auxiliary peers. Learning from distinct target distributions helps to boost peer diversity for effectiveness of group-based distillation. The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i. e. , the model used for inference. Experimental results show that the proposed framework consistently gives better performance than state-of-the-art approaches without sacrificing training or inference complexity, demonstrating the effectiveness of the proposed two-level distillation framework.

IJCAI Conference 2018 Conference Paper

A Comparative Study of Transactional and Semantic Approaches for Predicting Cascades on Twitter

• Yunwei Zhao
• Can Wang
• Chi-Hung Chi
• Kwok-Yan Lam
• Sen Wang

The availability of massive social media data has enabled the prediction of people’s future behavioral trends at an unprecedented large scale. Information cascades study on Twitter has been an integral part of behavior analysis. A number of methods based on the transactional features (such as keyword frequency) and the semantic features (such as sentiment) have been proposed to predict the future cascading trends. However, an in-depth understanding of the pros and cons of semantic and transactional models is lacking. This paper conducts a comparative study of both approaches in predicting information diffusion with three mechanisms: retweet cascade, url cascade, and hashtag cascade. Experiments on Twitter data show that the semantic model outperforms the transactional model, if the exterior pattern is less directly observable (i. e. hashtag cascade). When it becomes more directly observable (i. e. retweet and url cascades), the semantic method yet delivers approximate accuracy (i. e. url cascade) or even worse accuracy (i. e. retweet cascade). Further, we demonstrate that the transactional and semantic models are not independent, and the performance gets greatly enhanced when combining both.

AAAI Conference 2018 Short Paper

A Novel Embedding Method for News Diffusion Prediction

• Ruoran Liu
• Qiudan Li
• Can Wang
• Lei Wang
• Daniel Zeng

News diffusion prediction aims to predict a sequence of news sites which will quote a particular piece of news. Most of previous propagation models make efforts to estimate propagation probabilities along observed links and ignore the characteristics of news diffusion processes, and they fail to capture the implicit relationships between news sites. In this paper, we propose an algorithm to model the news diffusion processes in a continuous space and take the attributes of news into account. Experiments performed on a real-world news dataset show that our model can take advantage of news’ attributes and predict news diffusion accurately.

IJCAI Conference 2018 Conference Paper

ANRL: Attributed Network Representation Learning via Deep Neural Networks

• Zhen Zhang
• Hongxia Yang
• Jiajun Bu
• Sheng Zhou
• Pinggang Yu
• Jianwei Zhang
• Martin Ester
• Can Wang

Network representation learning (RL) aims to transform the nodes in a network into low-dimensional vector spaces while preserving the inherent properties of the network. Though network RL has been intensively studied, most existing works focus on either network structure or node attribute information. In this paper, we propose a novel framework, named ANRL, to incorporate both the network structure and node attribute information in a principled way. Specifically, we propose a neighbor enhancement autoencoder to model the node attribute information, which reconstructs its target neighbors instead of itself. To capture the network structure, attribute-aware skip-gram model is designed based on the attribute encoder to formulate the correlations between each node and its direct or indirect neighbors. We conduct extensive experiments on six real-world networks, including two social networks, two citation networks and two user behavior networks. The results empirically show that ANRL can achieve relatively significant gains in node classification and link prediction tasks.

IJCAI Conference 2018 Conference Paper

Multi-modality Sensor Data Classification with Selective Attention

• Xiang Zhang
• Lina Yao
• Chaoran Huang
• Sen Wang
• Mingkui Tan
• Guodong Long
• Can Wang

Multimodel wearable sensor data classificationplays an important role in ubiquitous computingand has a wide range of applications in variousscenarios from healthcare to entertainment. How-ever, most of the existing work in this field em-ploys domain-specific approaches and is thus inef-fective in complex situations where multi-modalitysensor data is collected. Moreover, the wearablesensor data is less informative than the conven-tional data such as texts or images. In this paper, to improve the adaptability of such classificationmethods across different application contexts, weturn this classification task into a game and applya deep reinforcement learning scheme to dynami-cally deal with complex situations. We also intro-duce a selective attention mechanism into the rein-forcement learning scheme to focus on the crucialdimensions of the data. This mechanism helps tocapture extra information from the signal, and canthus significantly improve the discriminative powerof the classifier. We carry out several experimentson three wearable sensor datasets, and demonstratecompetitive performance of the proposed approachcompared to several state-of-the-art baselines.

AAAI Conference 2015 Conference Paper

Coupled Interdependent Attribute Analysis on Mixed Data

• Can Wang
• Chi-Hung Chi
• Wei Zhou
• Raymond Wong

In the real-world applications, heterogeneous interdependent attributes that consist of both discrete and numerical variables can be observed ubiquitously. The usual representation of these data sets is an information table, assuming the independence of attributes. However, very often, they are actually interdependent on one another, either explicitly or implicitly. Limited research has been conducted in analyzing such attribute interactions, which causes the analysis results to be more local than global. This paper proposes the coupled heterogeneous attribute analysis to capture the interdependence among mixed data by addressing coupling context and coupling weights in unsupervised learning. Such global couplings integrate the interactions within discrete attributes, within numerical attributes and across them to form the coupled representation for mixed-type objects based on dimension conversion and feature selection. This work makes one step forward towards explicitly modeling the interdependence of heterogeneous attributes among mixed data, verified by the applications in data structure analysis, data clustering evaluation, and density comparison. Substantial experiments on 12 UCI data sets show that our approach can effectively capture the global couplings of heterogeneous attributes and outperforms the state-of-the-art methods, supported by statistical analysis.

IS Journal 2014 Journal Article

Behavior Informatics: A New Perspective

• Longbing Cao
• Thorsten Joachims
• Can Wang
• Eric Gaussier
• Jinjiu Li
• Yuming Ou
• Dan Luo
• Reza Zafarani

This installment of Trends & Controversies provides an array of perspectives on the latest research in behavior informatics. Longbing Cao introduces the work in "Behavior Informatics: A New Perspective. " Then, in "Behavior Computing, " Longbing Cao and Thorsten Joachims provide a basic overview of the topic. Next is "Coupled Behavior Representation, Modeling, Analysis, and Reasoning" by Can Wang, Longbing Cao, Eric Gaussier, Jinjiu Li, Yuming Ou, and Dan Luo. The fourth article is "Behavior Analysis in Social Media, " by Reza Zafarani and Huan Liu. The fifth article is "Group Recommendation and Behavior, " by Guandong Xu and Zhiang Wu. Gabriella Pasi wrote the sixth article, "Web Search and Behavior. " The seventh article, "Behaviors of IPTV Users, " is by Ya Zhang, Xiaokang Yang, and Hongyuan Zha. Finally, "Should Behavioral Models of Terror Groups Be Disclosed? " is by Edoardo Serra and V. S. Subrahmanian.

IJCAI Conference 2013 Conference Paper

Coupled Attribute Analysis on Numerical Data

• Can Wang
• Zhong She
• Longbing Cao

The usual representation of quantitative data is to formalize it as an information table, which assumes the independence of attributes. In real-world data, attributes are more or less interacted and coupled via explicit or implicit relationships. Limited research has been conducted on analyzing such attribute interactions, which only describe a local picture of attribute couplings in an implicit way. This paper proposes a framework of the coupled attribute analysis to capture the global dependency of continuous attributes. Such global couplings integrate the intra-coupled interaction within an attribute (i. e. the correlations between attributes and their own powers) and inter-coupled interaction among different attributes (i. e. the correlations between attributes and the powers of others) to form a coupled representation for numerical objects by the Taylor-like expansion. This work makes one step forward towards explicitly addressing the global interactions of continuous attributes, verified by the applications in data structure analysis, data clustering, and data classification. Substantial experiments on 13 UCI data sets demonstrate that the coupled representation can effectively capture the global couplings of attributes and outperforms the traditional way, supported by statistical analysis.

AAAI Conference 2012 Conference Paper

CCE: A Coupled Framework of Clustering Ensembles

• Zhong She
• Can Wang
• Longbing Cao

Clustering ensemble mainly relies on the pairwise similarity to capture the consensus function. However, it usually considers each base clustering independently, and treats the similarity measure roughly with either 0 or 1. To address these two issues, we propose a coupled framework of clustering ensembles CCE, and exemplify it with the coupled version CCSPA for CSPA. Experiments demonstrate the superiority of CCSPA over baseline approaches in terms of the clustering accuracy.

AAAI Conference 2012 Conference Paper

Document Summarization Based on Data Reconstruction

• Zhanying He
• Chun Chen
• Jiajun Bu
• Can Wang
• Lijun Zhang
• Deng Cai
• Xiaofei He

Document summarization is of great value to many real world applications, such as snippets generation for search results and news headlines generation. Traditionally, document summarization is implemented by extracting sentences that cover the main topics of a document with a minimum redundancy. In this paper, we take a different perspective from data reconstruction and propose a novel framework named Document Summarization based on Data Reconstruction (DSDR). Specifically, our approach generates a summary which consist of those sentences that can best reconstruct the original document. To model the relationship among sentences, we introduce two objective functions: (1) linear reconstruction, which approximates the document by linear combinations of the selected sentences; (2) nonnegative linear reconstruction, which allows only additive, not subtractive, linear combinations. In this framework, the reconstruction error becomes a natural criterion for measuring the quality of the summary. For each objective function, we develop an efficient algorithm to solve the corresponding optimization problem. Extensive experiments on summarization benchmark data sets DUC 2006 and DUC 2007 demonstrate the effectiveness of our proposed approach.

AAAI Conference 2010 Conference Paper

G-Optimal Design with Laplacian Regularization

• Chun Chen
• Zhengguang Chen
• Jiajun Bu
• Can Wang
• Lijun Zhang
• Cheng Zhang

In many real world applications, labeled data are usually expensive to get, while there may be a large amount of unlabeled data. To reduce the labeling cost, active learning attempts to discover the most informative data points for labeling. Recently, Optimal Experimental Design (OED) techniques have attracted an increasing amount of attention. OED is concerned with the design of experiments that minimizes variances of a parameterized model. Typical design criteria include D-, A-, and E-optimality. However, all these criteria are based on an ordinary linear regression model which aims to minimize the empirical error whereas the geometrical structure of the data space is not well respected. In this paper, we propose a novel optimal experimental design approach for active learning, called Laplacian G-Optimal Design (LapGOD), which considers both discriminating and geometrical structures. By using Laplacian Regularized Least Squares which incorporates manifold regularization into linear regression, our proposed algorithm selects those data points that minimizes the maximum variance of the predicted values on the data manifold. We also extend our algorithm to nonlinear case by using kernel trick. The experimental results on various image databases have shown that our proposed LapGOD active learning algorithm can significantly enhance the classification accuracy if the selected data points are used as training data.

AAAI Conference 2010 Conference Paper

Modeling Dynamic Multi-Topic Discussions in Online Forums

• Hao Wu
• Jiajun Bu
• Chun Chen
• Can Wang
• Guang Qiu
• Lijun Zhang
• Jianfeng Shen

In the form of topic discussions, users interact with each other to share knowledge and exchange information in online forums. Modeling the evolution of topic discussion reveals how information propagates on Internet and can thus help understand sociological phenomena and improve the performance of applications such as recommendation systems. In this paper, we argue that a user’s participation in topic discussions is motivated by either her friends or her own preferences. Inspired by the theory of information flow, we propose dynamic topic discussion models by mining influential relationships between users and individual preferences. Reply relations of users are exploited to construct the fundamental influential social network. The property of discussed topics and time lapse factor are also considered in our modeling. Furthermore, we propose a novel measure called ParticipationRank to rank users according to how important they are in the social network and to what extent they prefer to participate in the discussion of a certain topic. The experiments show our model can simulate the evolution of topic discussions well and predict the tendency of user’s participation accurately.