Qing He

EAAI Journal 2025 Journal Article

A bidirectional bi-objective graph search model for sustainable urban railway alignment optimization

• Tianlong Zhang
• Yan Gao
• Shuangting Xu
• Ting Deng
• Qing He
• Paul Schonfeld
• Yang Zou
• Dong Liang

Designing railway alignments in building-dense urban areas is a challenging task, requiring consideration of both costs and impacts on existing buildings and the environment. Achieving a viable solution necessitates the application of computer-aided techniques for three-dimensional (3D) global path searches while simultaneously optimizing multiple objectives. To tackle this challenge, this study proposes a bidirectional bi-objective graph search model. This model efficiently searches the 3D space to generate high-quality railway alignment solutions that simultaneously consider both comprehensive costs (including railway construction, ecological, and affected building costs) and carbon emissions (covering emissions from railways and buildings). It provides valuable reference solutions for designers, enhancing the design efficiency. The model includes two main innovations: (1) the ability to quickly search the entire 3D space using a graph-based strategy, generating multiple alignment solutions that meet design constraints in a single optimization process, and (2) the ability to accurately and efficiently account for the impact of railway alignments on existing buildings during optimization. Testing the model on a real-world urban case demonstrates its capability to generate multiple alternative railway alignments within minutes. The Pareto balanced solution achieves an 18. 91 % reduction in comprehensive costs and a 13. 46 % decrease in carbon emissions compared to manual design. The estimation error of affected building areas is approximately 2 %–4 % along the approximately 40 km alignment. Overall, the significance of this study lies in exploring the application of efficient graph search algorithms in the multi-objective optimization design of railway alignments in urban areas, advancing ongoing research in this field.

EAAI Journal 2025 Journal Article

Aspect-based sentiment analysis with semantic and syntactic enhanced multi-layer fusion model

• Song Jin
• Qing He
• Yuji Wang
• Nisuo Du
• Wenjing Lei

Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity of specific aspect words or phrases in a sentence. Although recent studies have used attention mechanisms or syntactic relations of dependency trees to establish links between aspect terms and sentences, these approaches are imperfect in effectively fusing syntactic and semantic contextual information. Therefore, in this paper, we propose a novel multi-layer fusion model (MLFM) based on artificial intelligence (AI) techniques to efficiently fuse semantic and syntactic information for sentiment analysis. In the model, we first propose a new bi-graph convolutional network module for aspect term-centered aspect nodal attention (Aspect-NA) to enhance Semantic and Syntactic learning. Within Aspect-NA, we introduce dependency embedding and propose a dual embedding update mechanism that pays more attention to the influence of dependency types and semantics. In addition, we propose an adaptive hierarchical cross-attention (AHCA) for fusing the semantic information of aspect term with their associated syntactic features. AHCA not only effectively fuses features between syntax and semantics of the context, but also carries out the key features. We conducted experiments on six benchmark datasets, and the results show that our proposed model outperforms most baseline methods. The code and datasets involved in this paper are provided on https: //github. com/jims-bug/MLFM. git.

AAAI Conference 2025 Conference Paper

Controlling Large Language Models Through Concept Activation Vectors

• Hanyu Zhang
• Xiting Wang
• Chengao Li
• Xiang Ao
• Qing He

As large language models (LLMs) are widely deployed across various domains, the ability to control their generated outputs has become more critical. This control involves aligning LLMs outputs with human values and ethical principles or customizing LLMs on specific topics or styles for individual users. Existing controlled generation methods either require significant computational resources and extensive trial-and-error or provide coarse-grained control. In this paper, we propose Generation with Concept Activation Vector (GCAV), a lightweight model control framework that ensures accurate control without requiring resource-extensive fine-tuning. Specifically, GCAV first trains a concept activation vector for specified concepts to be controlled, such as toxicity. During inference, GCAV steers the concept vector in LLMs, for example, by removing the toxicity concept vector from the activation layers. Control experiments from different perspectives, including toxicity reduction, sentiment control, linguistic style, and topic control, demonstrate that our framework achieves state-of-the-art performance with granular control, allowing for fine-grained adjustments of both the steering layers and the steering magnitudes for individual samples.

AAAI Conference 2025 Conference Paper

Dynamic Graph Learning with Static Relations for Credit Risk Assessment

• Qi Yuan
• Yang Liu
• Yateng Tang
• Xinhuan Chen
• Xuehao Zheng
• Qing He
• Xiang Ao

Credit risk assessment has increasingly become a prominent research field due to the dramatically increased incidents of financial default. Traditional graph-based methods have been developed to detect defaulters within user-merchant commercial payment networks. However, these methods face challenges in detecting complex risks, primarily due to their neglect of user-to-user fund transfer interactions and the under-utilization of temporal information. In this paper, we propose a novel framework named Dynamic Graph Neural Network with Static Relations (DGNN-SR) for credit risk assessment, which can encode the dynamic transaction graph and the static fund transfer graph simultaneously. To fully harness the temporal information, DGNN-SR employs a multi-view time encoder to explore the semantics of both relative and absolute time. To enhance the dynamic representations with static relations, we devise an adaptive re-weighting strategy to incorporate the static relations into the dynamic representations of time encoder, which extracts more discriminative features for risk assessment. Extensive experiments on two real-world business datasets demonstrate that our proposed method achieves a 0.85% - 2.5% improvement over existing SOTA methods.

AAAI Conference 2024 Conference Paper

Online Conversion Rate Prediction via Multi-Interval Screening and Synthesizing under Delayed Feedback

• Qiming Liu
• Xiang Ao
• Yuyao Guo
• Qing He

Due to the widespread adoption of the cost-per-action(CPA) display strategy that demands a real-time conversion rate prediction(CVR), delayed feedback is becoming one of the major challenges in online advertising. As the true labels of a significant quantity of samples are only available after long delays, the observed training data are usually biased, harming the performance of models. Recent studies show integrating models with varying waiting windows to observe true labels is beneficial, but the aggregation framework remains far from reaching a consensus. In this work, we propose the Multi-Interval Screening and Synthesizing model (MISS for short) for online CVR prediction. We first design a multi-interval screening model with various output heads to produce accurate and distinctive estimates. Then a light-weight synthesizing model with an assembled training pipeline is applied to thoroughly exploit the knowledge and relationship among heads, obtaining reliable predictions. Extensive experiments on two real-world advertising datasets validate the effectiveness of our model.

YNICL Journal 2024 Journal Article

Structural connectivity from DTI to predict mild cognitive impairment in de novo Parkinson’s disease

• Xiaofei Huang
• Qing He
• Xiuhang Ruan
• Yuting Li
• Zhanyu Kuang
• Mengfan Wang
• Riyu Guo
• Shuwen Bu

BACKGROUND: Early detection of Parkinson's disease (PD) patients at high risk for mild cognitive impairment (MCI) can help with timely intervention. White matter structural connectivity is considered an early and sensitive indicator of neurodegenerative disease. OBJECTIVES: To investigate whether baseline white matter structural connectivity features from diffusion tensor imaging (DTI) of de novo PD patients can help predict PD-MCI conversion at an individual level using machine learning methods. METHODS: We included 90 de novo PD patients who underwent DTI and 3D T1-weighted imaging. Elastic net-based feature consensus ranking (ENFCR) was used with 1000 random training sets to select clinical and structural connectivity features. Linear discrimination analysis (LDA), support vector machine (SVM), K-nearest neighbor (KNN) and naïve Bayes (NB) classifiers were trained based on features selected more than 500 times. The area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN) and specificity (SPE) were used to evaluate model performance. RESULTS: A total of 57 PD patients were classified as PD-MCI nonconverters, and 33 PD patients were classified as PD-MCI converters. The models trained with clinical data showed moderate performance (AUC range: 0.62-0.68; ACC range: 0.63-0.77; SEN range: 0.45-0.66; SPE range: 0.64-0.84). Models trained with structural connectivity (AUC range, 0.81-0.84; ACC range, 0.75-0.86; SEN range, 0.77-0.91; SPE range, 0.71-0.88) performed similar to models that were trained with both clinical and structural connectivity data (AUC range, 0.81-0.85; ACC range, 0.74-0.85; SEN range, 0.79-0.91; SPE range, 0.70-0.89). CONCLUSIONS: Baseline white matter structural connectivity from DTI is helpful in predicting future MCI conversion in de novo PD patients.

AAAI Conference 2023 Conference Paper

Gradient-Adaptive Pareto Optimization for Constrained Reinforcement Learning

• Zixian Zhou
• Mengda Huang
• Feiyang Pan
• Jia He
• Xiang Ao
• Dandan Tu
• Qing He

Constrained Reinforcement Learning (CRL) burgeons broad interest in recent years, which pursues maximizing long-term returns while constraining costs. Although CRL can be cast as a multi-objective optimization problem, it is still facing the key challenge that gradient-based Pareto optimization methods tend to stick to known Pareto-optimal solutions even when they yield poor returns (e.g., the safest self-driving car that never moves) or violate the constraints (e.g., the record-breaking racer that crashes the car). In this paper, we propose Gradient-adaptive Constrained Policy Optimization (GCPO for short), a novel Pareto optimization method for CRL with two adaptive gradient recalibration techniques. First, to find Pareto-optimal solutions with balanced performance over all targets, we propose gradient rebalancing which forces the agent to improve more on under-optimized objectives at every policy iteration. Second, to guarantee that the cost constraints are satisfied, we propose gradient perturbation that can temporarily sacrifice the returns for costs. Experiments on the SafetyGym benchmarks show that our method consistently outperforms previous CRL methods in reward while satisfying the constraints.

AAAI Conference 2022 Conference Paper

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

• Fuwei Zhang
• Zhao Zhang
• Xiang Ao
• Dehong Gao
• Fuzhen Zhuang
• Yi Wei
• Qing He

Cross-Lingual Information Retrieval (CLIR) aims to rank the documents written in a language different from the user’s query. The intrinsic gap between different languages is an essential challenge for CLIR. In this paper, we introduce the multilingual knowledge graph (KG) to the CLIR task due to the sufficient information of entities in multiple languages. It is regarded as a “silver bullet” to simultaneously perform explicit alignment between queries and documents and also broaden the representations of queries. And we propose a model named CLIR with hierarchical knowledge enhancement (HIKE) for our task. The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism. Particularly, HIKE first integrates the entities and their neighborhood in KG into query representations with a knowledge-level fusion, then combines the knowledge from both source and target languages to further mitigate the linguistic gap with a language-level fusion. Finally, experimental results demonstrate that HIKE achieves substantial improvements over state-ofthe-art competitors.

IJCAI Conference 2021 Conference Paper

AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction

• Hao Chen
• Fuzhen Zhuang
• Li Xiao
• Ling Ma
• Haiyan Liu
• Ruifang Zhang
• Huiqin Jiang
• Qing He

Recently, Graph Convolutional Networks (GCNs) have proven to be a powerful mean for Computer Aided Diagnosis (CADx). This approach requires building a population graph to aggregate structural information, where the graph adjacency matrix represents the relationship between nodes. Until now, this adjacency matrix is usually defined manually based on phenotypic information. In this paper, we propose an encoder that automatically selects the appropriate phenotypic measures according to their spatial distribution, and uses the text similarity awareness mechanism to calculate the edge weights between nodes. The encoder can automatically construct the population graph using phenotypic measures which have a positive impact on the final results, and further realizes the fusion of multimodal information. In addition, a novel graph convolution network architecture using multi-layer aggregation mechanism is proposed. The structure can obtain deep structure information while suppressing over-smooth, and increase the similarity between the same type of nodes. Experimental results on two databases show that our method can significantly improve the diagnostic accuracy for Autism spectrum disorder and breast cancer, indicating its universality in leveraging multimodal data for disease prediction.

NeurIPS Conference 2021 Conference Paper

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

• Ying Sun
• Hengshu Zhu
• Chuan Qin
• Fuzhen Zhuang
• Qing He
• Hui Xiong

Neural network based deep learning techniques have shown great success for numerous applications. While it is expected to understand their intrinsic decision-making processes, these deep neural networks often work in a black-box way. To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN). Specifically, instead of relying on massive feature combinations, VOTEN creatively models expressive single-valued voting functions between explicitly modeled latent concepts to achieve high fitting ability. Along this line, we first theoretically analyze the major components of VOTEN and prove the relationship and advantages of VOTEN compared with Multi-Layer Perceptron (MLP), the basic structure of deep neural networks. Moreover, we design efficient algorithms to improve the model usability by explicitly showing the decision processes of VOTEN. Finally, extensive experiments on multiple real-world datasets clearly validate the performances and explainability of VOTEN.

AAAI Conference 2021 Conference Paper

Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection

• Dongbo Xi
• Bowen Song
• Fuzhen Zhuang
• Yongchun Zhu
• Shuai Chen
• Tianyi Zhang
• Yuan Qi
• Qing He

With the explosive growth of e-payment industry, online transaction fraud has become one of the biggest challenges for the business. The historical behavior information of users provides rich information for digging into the users’ fraud risk. While considerable efforts have been made in this direction, a long-standing challenge is how to effectively exploit user’s behavioral information and provide explainable prediction results. In fact, the value variations of same field from different events and the interactions of different fields within one event have proven to be strong indicators of fraudulent behaviors. In this paper, we propose the Dual Importanceaware Factorization Machines (DIFM), which exploits the inter- and intra-event information among users’ behavior sequence from dual perspectives, i. e. , field value variations and field interactions simultaneously for fraud detection. The proposed model is deployed in Alipay’s risk management system, which provides real-time fraud detection service for ecommerce platforms. Experimental results on industrial data under various scenarios in the platform clearly demonstrate that our model achieves significant improvements compared with various state-of-the-art baseline models. Moreover, the DIFM could also give an insight into the explanation of the prediction results from dual perspectives.

AAAI Conference 2020 Conference Paper

Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion

• Zhao Zhang
• Fuzhen Zhuang
• Hengshu Zhu
• Zhiping Shi
• Hui Xiong
• Qing He

The rapid proliferation of knowledge graphs (KGs) has changed the paradigm for various AI-related applications. Despite their large sizes, modern KGs are far from complete and comprehensive. This has motivated the research in knowledge graph completion (KGC), which aims to infer missing values in incomplete knowledge triples. However, most existing KGC models treat the triples in KGs independently without leveraging the inherent and valuable information from the local neighborhood surrounding an entity. To this end, we propose a Relational Graph neural network with Hierarchical ATtention (RGHAT) for the KGC task. The proposed model is equipped with a two-level attention mechanism: (i) the first level is the relation-level attention, which is inspired by the intuition that different relations have different weights for indicating an entity; (ii) the second level is the entity-level attention, which enables our model to highlight the importance of different neighboring entities under the same relation. The hierarchical attention mechanism makes our model more effective to utilize the neighborhood information of an entity. Finally, we extensively validate the superiority of RGHAT against various state-of-the-art baselines.

NeurIPS Conference 2020 Conference Paper

Trust the Model When It Is Confident: Masked Model-based Actor-Critic

• Feiyang Pan
• Jia He
• Dandan Tu
• Qing He

It is a popular belief that model-based Reinforcement Learning (RL) is more sample efficient than model-free RL, but in practice, it is not always true due to overweighed model errors. In complex and noisy settings, model-based RL tends to have trouble using the model if it does not know when to trust the model. In this work, we find that better model usage can make a huge difference. We show theoretically that if the use of model-generated data is restricted to state-action pairs where the model error is small, the performance gap between model and real rollouts can be reduced. It motivates us to use model rollouts only when the model is confident about its predictions. We propose Masked Model-based Actor-Critic (M2AC), a novel policy optimization algorithm that maximizes a model-based lower-bound of the true value function. M2AC implements a masking mechanism based on the model's uncertainty estimation to decide whether the model should be used or not. Consequently, the new algorithm tends to give robust policy improvements. Experiments on continuous control benchmarks demonstrate that M2AC has strong performance even when using long model rollouts in very noisy environments, and significantly outperforms previous state-of-the-art methods.

TIST Journal 2019 Journal Article

Large-Scale Frequent Episode Mining from Complex Event Sequences with Hierarchies

• Xiang Ao
• Haoran Shi
• Jin Wang
• Luo Zuo
• Hongwei Li
• Qing He

Frequent Episode Mining (FEM), which aims at mining frequent sub-sequences from a single long event sequence, is one of the essential building blocks for the sequence mining research field. Existing studies about FEM suffer from unsatisfied scalability when faced with complex sequences as it is an NP-complete problem for testing whether an episode occurs in a sequence. In this article, we propose a scalable, distributed framework to support FEM on “big” event sequences. As a rule of thumb, “big” illustrates an event sequence is either very long or with masses of simultaneous events. Meanwhile, the events in this article are arranged in a predefined hierarchy. It derives some abstractive events that can form episodes that may not directly appear in the input sequence. Specifically, we devise an event-centered and hierarchy-aware partitioning strategy to allocate events from different levels of the hierarchy into local processes. We then present an efficient special-purpose algorithm to improve the local mining performance. We also extend our framework to support maximal and closed episode mining in the context of event hierarchy, and to the best of our knowledge, we are the first attempt to define and discover hierarchy-aware maximal and closed episodes. We implement the proposed framework on Apache Spark and conduct experiments on both synthetic and real-world datasets. Experimental results demonstrate the efficiency and scalability of the proposed approach and show that we can find practical patterns when taking event hierarchies into account.

AAAI Conference 2019 Conference Paper

Modelling of Bi-Directional Spatio-Temporal Dependence and Users’ Dynamic Preferences for Missing POI Check-In Identification

• Dongbo Xi
• Fuzhen Zhuang
• Yanchi Liu
• Jingjing Gu
• Hui Xiong
• Qing He

Human mobility data accumulated from Point-of-Interest (POI) check-ins provides great opportunity for user behavior understanding. However, data quality issues (e. g. , geolocation information missing, unreal check-ins, data sparsity) in real-life mobility data limit the effectiveness of existing POIoriented studies, e. g. , POI recommendation and location prediction, when applied to real applications. To this end, in this paper, we develop a model, named Bi-STDDP, which can integrate bi-directional spatio-temporal dependence and users’ dynamic preferences, to identify the missing POI check-in where a user has visited at a specific time. Specifically, we first utilize bi-directional global spatial and local temporal information of POIs to capture the complex dependence relationships. Then, target temporal pattern in combination with user and POI information are fed into a multi-layer network to capture users’ dynamic preferences. Moreover, the dynamic preferences are transformed into the same space as the dependence relationships to form the final model. Finally, the proposed model is evaluated on three large-scale real-world datasets and the results demonstrate significant improvements of our model compared with state-of-the-art methods. Also, it is worth noting that the proposed model can be naturally extended to address POI recommendation and location prediction tasks with competitive performances.

AAAI Conference 2019 Conference Paper

Policy Optimization with Model-Based Explorations

• Feiyang Pan
• Qingpeng Cai
• An-Xiang Zeng
• Chun-Xiang Pan
• Qing Da
• Hualin He
• Qing He
• Pingzhong Tang

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning methods that learn the transition dynamics are more sample efficient, but they often suffer from the bias of the transition estimation. How to make use of both model-based and model-free learning is a central problem in reinforcement learning. In this paper, we present a new technique to address the tradeoff between exploration and exploitation, which regards the difference between model-free and model-based estimations as a measure of exploration value. We apply this new technique to the PPO algorithm and arrive at a new policy optimization method, named Policy Optimization with Modelbased Explorations (POME). POME uses two components to predict the actions’ target values: a model-free one estimated by Monte-Carlo sampling and a model-based one which learns a transition model and predicts the value of the next state. POME adds the error of these two target estimations as the additional exploration value for each state-action pair, i. e, encourages the algorithm to explore the states with larger target errors which are hard to estimate. We compare POME with PPO on Atari 2600 games, and it shows that POME outperforms PPO on 33 games out of 49 games.

IJCAI Conference 2019 Conference Paper

Unsupervised Neural Aspect Extraction with Sememes

• Ling Luo
• Xiang Ao
• Yan Song
• Jinyao Li
• Xiaopeng Yang
• Qing He
• Dong Yu

Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts. To enhance the performance on aspect extraction, leveraging lexical semantic resources is a possible solution to such challenge. In this paper, we present an unsupervised neural framework that leverages sememes to enhance lexical semantics. The overall framework is analogous to an autoenoder which reconstructs sentence representations and learns aspects by latent variables. Two models that form sentence representations are proposed by exploiting sememes via (1) a hierarchical attention; (2) a context-enhanced attention. Experiments on two real-world datasets demonstrate the validity and the effectiveness of our models, which significantly outperforms existing baselines.

IJCAI Conference 2018 Conference Paper

Beyond Polarity: Interpretable Financial Sentiment Analysis with Hierarchical Query-driven Attention

• Ling Luo
• Xiang Ao
• Feiyang Pan
• Jin Wang
• Tong Zhao
• Ningzi Yu
• Qing He

Sentiment analysis has played a significant role in financial applications in recent years. The informational and emotive aspects of news texts may affect the prices, volatilities, volume of trades, and even potential risks of financial subjects. Previous studies in this field mainly focused on identifying polarity~(e. g. positive or negative). However, as financial decisions broadly require justifications, only plausible polarity cannot provide enough evidence during the decision making processes of humanity. Hence an explainable solution is in urgent demand. In this paper, we present an interpretable neural net framework for financial sentiment analysis. First, we design a hierarchical model to learn the representation of a document from multiple granularities. In addition, we propose a query-driven attention mechanism to satisfy the unique characteristics of financial documents. With the domain specified questions provided by the financial analysts, we can discover different spotlights for queries from different aspects. We conduct extensive experiments on a real-world dataset. The results demonstrate that our framework can learn better representation of the document and unearth meaningful clues on replying different users? preferences. It also outperforms the state-of-the-art methods on sentiment prediction of financial documents.

AAAI Conference 2018 Conference Paper

Elastic Responding Machine for Dialog Generation with Dynamically Mechanism Selecting

• Ganbin Zhou
• Ping Luo
• Yijun Xiao
• Fen Lin
• Bo Chen
• Qing He

Neural models aiming at generating meaningful and diverse response is attracting increasing attention over recent years. For a given post, the conventional encoder-decoder models tend to learn high-frequency but trivial responses, or are dif- ficult to determine which speaking styles are suitable to generate responses. To address this issue, we propose the elastic responding machine (ERM), which is based on a proposed encoder-diverter-filter-decoder framework. ERM models the multiple responding mechanisms to not only generate acceptable responses for a given post but also improve the diversity of responses. Here, the mechanisms could be regraded as some latent variables, and for a given post different responses may be generated by different mechanisms. The experiments demonstrate the quality and diversity of the generated responses, intuitively show how the learned model controls response mechanism when responding, and reveal some underlying relationship between mechanism and language style.

AAAI Conference 2018 Conference Paper

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

• Ganbin Zhou
• Ping Luo
• Rongyu Cao
• Yijun Xiao
• Fen Lin
• Bo Chen
• Qing He

Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentencetree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2TREE framework outperforms baseline methods over 11. 15% increase of acceptance ratio.

AAAI Conference 2017 Conference Paper

Mechanism-Aware Neural Machine for Dialogue Response Generation

• Ganbin Zhou
• Ping Luo
• Rongyu Cao
• Fen Lin
• Bo Chen
• Qing He

To the same utterance, people’s responses in everyday dialogue may be diverse largely in terms of content semantics, speaking styles, communication intentions and so on. Previous generative conversational models ignore these 1-to-n relationships between a post to its diverse responses, and tend to return high-frequency but meaningless responses. In this study we propose a mechanism-aware neural machine for dialogue response generation. It assumes that there exists some latent responding mechanisms, each of which can generate different responses for a single input post. With this assumption we model different responding mechanisms as latent embeddings, and develop a encoder-diverter-decoder framework to train its modules in an end-to-end fashion. With the learned latent mechanisms, for the first time these decomposed modules can be used to encode the input into mechanism-aware context, and decode the responses with the controlled generation styles and topics. Finally, the experiments with human judgements, intuitive examples, detailed discussions demonstrate the quality and diversity of the generated responses with 9. 80% increase of acceptable ratio over the best of six baseline methods.

IJCAI Conference 2017 Conference Paper

Nonlinear Maximum Margin Multi-View Learning with Adaptive Kernel

• Jia He
• Changying Du
• Changde Du
• Fuzhen Zhuang
• Qing He
• Guoping Long

Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning. Apart from the huge consumption of manpower, computation and memory resources, most of these models seek point estimation of their parameters, and are prone to overfitting to small training data. This paper presents an adaptive kernel nonlinear max-margin multi-view learning model under the Bayesian framework. Specifically, we regularize the posterior of an efficient multi-view latent variable model by explicitly mapping the latent representations extracted from multiple data views to a random Fourier feature space where max-margin classification constraints are imposed. Assuming these random features are drawn from Dirichlet process Gaussian mixtures, we can adaptively learn shift-invariant kernels from data according to Bochners theorem. For inference, we employ the data augmentation idea for hinge loss, and design an efficient gradient-based MCMC sampler in the augmented space. Having no need to compute the Gram matrix, our algorithm scales linearly with the size of training set. Extensive experiments on real-world datasets demonstrate that our method has superior performance.

TIST Journal 2017 Journal Article

Supervised Representation Learning with Double Encoding-Layer Autoencoder for Transfer Learning

• Fuzhen Zhuang
• Xiaohu Cheng
• Ping Luo
• Sinno Jialin Pan
• Qing He

Transfer learning has gained a lot of attention and interest in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different domains such that the divergence between domains can be reduced with the new representation. Recently, deep learning has been proposed to learn more robust or higher-level features for transfer learning. In this article, we adapt the autoencoder technique to transfer learning and propose a supervised representation learning method based on double encoding-layer autoencoder. The proposed framework consists of two encoding layers: one for embedding and the other one for label encoding. In the embedding layer, the distribution distance of the embedded instances between the source and target domains is minimized in terms of KL-Divergence. In the label encoding layer, label information of the source domain is encoded using a softmax regression model. Moreover, to empirically explore why the proposed framework can work well for transfer learning, we propose a new effective measure based on autoencoder to compute the distribution distance between different domains. Experimental results show that the proposed new measure can better reflect the degree of transfer difficulty and has stronger correlation with the performance from supervised learning algorithms (e.g., Logistic Regression), compared with previous ones, such as KL-Divergence and Maximum Mean Discrepancy. Therefore, in our model, we have incorporated two distribution distance measures to minimize the difference between source and target domains in the embedding representations. Extensive experiments conducted on three real-world image datasets and one text data demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.

IJCAI Conference 2016 Conference Paper

Browsing Regularities in Hedonic Content Systems

• Ping Luo
• Ganbin Zhou
• Jiaxi Tang
• Rui Chen
• Zhongjie Yu
• Qing He

Various hedonic content systems (e. g. mobile apps for video, music, news, jokes, pictures, social networks etc. ) increasingly dominate people's daily spare life. This paper studies common regularities of browsing behaviors in these systems, based on a large data set of user logs. We found that despite differences in visit time and user types, the distribution over browsing length for a visit can be described by the inverse Gaussian form with a very high precision. It indicates that the choice threshold model of decision making on continuing browsing or leave does exist. Also, We found that the stimulus intensity, in terms of the amount of recent enjoyed items, affects the probability of continuing browsing in a curve of inverted-U shape. We discuss the possible origin of this curve based on a proposed Award-Aversion Contest model. This hypothesis is supported by the empirical study, which shows that the proposed model can successfully recover the original inverse Gaussian distribution for the browsing length. These browsing regularities can be used to develop better organization of hedonic content, which helps to attract more user dwell time in these systems.

IJCAI Conference 2016 Conference Paper

Online Bayesian Max-Margin Subspace Multi-View Learning

• Jia He
• Changying Du
• Fuzhen Zhuang
• Xin Yin
• Qing He
• Guoping Long

Last decades have witnessed a number of studies devoted to multi-view learning algorithms, however, few efforts have been made to handle online multi-view learning scenarios. In this paper, we propose an online Bayesian multi-view learning algorithm to learn predictive subspace with max-margin principle. Specifically, we first define the latent margin loss for classification in the subspace, and then cast the learning problem into a variational Bayesian framework by exploiting the pseudo-likelihood and data augmentation idea. With the variational approximate posterior inferred from the past samples, we can naturally combine historical knowledge with new arrival data, in a Bayesian Passive-Aggressive style. Experiments on various classification tasks show that our model have superior performance.

AAAI Conference 2015 Conference Paper

Bayesian Maximum Margin Principal Component Analysis

• Changying Du
• Shandian Zhe
• Fuzhen Zhuang
• Yuan Qi
• Qing He
• Zhongzhi Shi

Supervised dimensionality reduction has shown great advantages in finding predictive subspaces. Previous methods rarely consider the popular maximum margin principle and are prone to overfitting to usually small training data, especially for those under the maximum likelihood framework. In this paper, we present a posterior-regularized Bayesian approach to combine Principal Component Analysis (PCA) with the maxmargin learning. Based on the data augmentation idea for max-margin learning and the probabilistic interpretation of PCA, our method can automatically infer the weight and penalty parameter of max-margin learning machine, while finding the most appropriate PCA subspace simultaneously under the Bayesian framework. We develop a fast mean-field variational inference algorithm to approximate the posterior. Experimental results on various classification tasks show that our method outperforms a number of competitors.

JBHI Journal 2015 Journal Article

Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation

• Snehashis Roy
• Qing He
• Elizabeth Sweeney
• Aaron Carass
• Daniel S. Reich
• Jerry L. Prince
• Dzung L. Pham

Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

IJCAI Conference 2015 Conference Paper

Supervised Representation Learning: Transfer Learning with Deep Autoencoders

• Fuzhen Zhuang
• Xiaohu Cheng
• Ping Luo
• Sinno Jialin Pan
• Qing He

Transfer learning has attracted a lot of attention in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different domains such that the divergence between domains can be reduced with the new representation. Recently, deep learning has been proposed to learn more robust or higherlevel features for transfer learning. However, to the best of our knowledge, most of the previous approaches neither minimize the difference between domains explicitly nor encode label information in learning the representation. In this paper, we propose a supervised representation learning method based on deep autoencoders for transfer learning. The proposed deep autoencoder consists of two encoding layers: an embedding layer and a label encoding layer. In the embedding layer, the distance in distributions of the embedded instances between the source and target domains is minimized in terms of KL-Divergence. In the label encoding layer, label information of the source domain is encoded using a softmax regression model. Extensive experiments conducted on three real-world image datasets demonstrate the effectiveness of our proposed method compared with several state-of-theart baseline methods.

IJCAI Conference 2013 Conference Paper

Concept Learning for Cross-Domain Text Classification: A General Probabilistic Framework

• Fuzhen Zhuang
• Ping Luo
• Peifeng Yin
• Qing He
• Zhongzhi Shi

Cross-domain learning targets at leveraging the knowledge from source domains to train accurate models for the test data from target domains with different but related data distributions. To tackle the challenge of data distribution difference in terms of raw features, previous works proposed to mine high-level concepts (e. g. , word clusters) across data domains, which shows to be more appropriate for classification. However, all these works assume that the same set of concepts are shared in the source and target domains in spite that some distinct concepts may exist only in one of the data domains. Thus, we need a general framework, which can incorporate both shared and distinct concepts, for cross-domain classification. To this end, we develop a probabilistic model, by which both the shared and distinct concepts can be learned by the EM process which optimizes the data likelihood. To validate the effectiveness of this model we intentionally construct the classification tasks where the distinct concepts exist in the data domains. The systematic experiments demonstrate the superiority of our model over all compared baselines, especially on those much more challenging tasks.

ICRA Conference 2012 Conference Paper

A novel correspondence searching strategy in multiocular vision

• Ning Wei
• Baopu Li
• Qing He
• Chao Hu
• Max Q. -H. Meng

Correspondence searching among different images is a fundamental problem in computer vision. It is important to find correspondences correctly and rapidly, especially for real-time tracking systems. Therefore, the definition of search areas in images is crucial. Traditional epipolar constraint is not noise-enduring; some reformative methods lack explicit geometric meanings. All of them cannot help defining rational search areas under noises. This paper proposes two new binocular imaging constraints with clear geometric meanings and strong restraining forces. Based on them, a novel searching strategy among multiimages is developed which can define optimal search areas with smallest sizes but best reliability. Practical algorithms for implementation are presented and experiments with real images are performed, validating the effectiveness of the proposed strategy.

IJCAI Conference 2011 Conference Paper

Combining Supervised and Unsupervised Models via Unconstrained Probabilistic Embedding

• Xudong Ma
• Ping Luo
• Fuzhen Zhuang
• Qing He
• Zhongzhi Shi
• Zhiyong Shen

Ensemble learning with output from multiple supervised and unsupervised models aims to improvethe classification accuracy of supervised model ensembleby jointly considering the grouping results from unsupervised models. In this paper we cast this ensemble task as an unconstrained probabilistic embedding problem. Specifically, we assume both objects and classes/clusters have latent coordinates without constraints in a D-dimensional Euclidean space, and consider the mapping from the embedded space into the space of results from supervised and unsupervised models as a probabilistic generative process. The prediction of an objectis then determined by the distances between the objectand the classes in the embedded space. A solution of this embedding can be obtained using the quasi-Newton method, resulting in the objects and classes/clusters with high co-occurrence weights being embedded close. We demonstrate the benefits of this unconstrained embedding method by three real applications.

AAAI Conference 2010 Conference Paper

Nonparametric Curve Extraction Based on Ant Colony System

• Qing Tan
• Qing He
• Zhongzhi Shi