Qian Cao, Yahui Liu, Wei Bi, Yi Zhao, Ruihua Song, Xiting Wang, Ruiming Tang, Guorui Zhou, Han Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Reinforcement Learning from Human Feedback (RLHF) has emerged as a crucial technique for aligning large language models (LLMs) with human preferences.However, existing RLHF methods face key challenges, including poor sample efficiency, high computational overhead, and slow convergence.Recent studies highlight the importance of data selection in RL, but how to effectively select the most beneficial experiences for RL training remains an open problem.Existing data selection methods for RL rely on heuristic metrics, failing to establish an interpretable connection between data and optimization objectives.To address this problem, we propose InfOES (Influence-based Online Experience Selection), a novel data selection method for RLHF that dynamically estimates the influence of individual training samples on policy optimization.By incorporating data attribution into the policy gradient, InfOES can identify and filter out detrimental samples on the fly, ensuring effective convergence toward alignment objectives.Our approach is compatible with various RL algorithms (e.g., PPO, GRPO, RE-INFORCE++).Extensive experiments demonstrate that InfOES significantly enhances training effectiveness, achieving superior alignment performance with fewer optimization steps.

Agentic reinforcement learning enables large language models to solve long-horizon tasks by interacting with the environment and internalizing tool-use behavior into their reasoning.Prior work assigns supervision primarily based on outcome rewards or external reward models, but largely ignores environment observations, a critical source of learning.Consequently, agents may identify successful actions without understanding how the environment responds, producing suboptimal policies.To address this, we propose SOAR (Supervision from Observation for Agentic Reinforcement Learning), which assigns positive advantages to observation tokens proportional to the negative entropy of preceding actions.This encourages the agent to learn from outcomes of confident actions, grounding policy updates in environment dynamics and improving anticipation of tool-call consequences.Empirical results across three domains and 13 benchmarks show that SOAR consistently improves performance, yielding gains of up to 7.0% on general reasoning tasks and 16.9% on deep research tasks, while reducing erroneous and inefficient tool usage. 1

Zhihao Xu, Rumei Li, Jiahuan Li, Rongxiang Weng, Jingang Wang, Xunliang Cai, Xiting Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recent advancements in Large Reasoning Models (LRMs) have showcased strong performance across various reasoning tasks by leveraging System-2 thinking capabilities.However, existing studies indicate that this reasoning ability alone does not reliably transfer to the general alignment domain.Inspired by cognitive science and how humans solve tasks, we argue that LRMs must be equipped with metacognitive knowledge to fully utilize their System-2 capabilities.In this paper, we propose PRIORITY-AWARE METACOGNITION (PAM), which guides the model to first identify the top-level human preference (e.g., harmlessness) as a means of understanding the alignment task's nature, and then apply other kinds of metacognitive knowledge to better monitor and regulate the model's thinking process.We implement PAM via a two-stage pipeline: a cold-start phase that collects structured metacognitive knowledge based on Flavell's theoretical framework, and a preference-optimization phase that further reinforces such metacognition.Extensive experiments validate the effectiveness of PAM.Under the same training pipelines, PAM consistently yields higher performance, improving general domain alignment performance by ~10 points on the helpfulness and harmless benchmarks.Code is available at https://anonymous.4open.science/r/PAM- 8B42.

Large Language Models (LLMs) gain substantial reasoning and decision-making capabilities from thought structures. However, existing methods such as Tree of Thought and Retrieval Augmented Thoughts often fall short in complex tasks due to the limitations of insufficient local retrieval of factual knowledge and inadequate global selection of strategies. These limitations make it challenging for these methods to balance factual accuracy and comprehensive logical optimization effectively. To address these limitations, we introduce the Retrieval Augmented Thought Tree (RATT), a novel thought structure that considers both overall logical soundness and factual correctness at each step of the thinking process. Specifically, at every point of a thought branch, RATT performs planning and lookahead to explore and evaluate multiple potential reasoning steps, and integrate the fact-checking ability of Retrieval-Augmented Generation (RAG) with LLM's ability to assess overall strategy. Through this combination of factual knowledge and strategic feasibility, the RATT adjusts and integrates the thought tree structure to search for the most promising branches within the search space. This thought structure significantly enhances the model's coherence in logical inference and efficiency in decision-making, and thus increases the limit of the capacity of LLM to generate reliable inferences and decisions based on thought structures. A broad range of experiments on different types of tasks showcases that the RATT structure significantly outperforms existing methods in factual correctness and logical coherence.

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.

Aligning Large Language Models (LLMs) with human values has attracted increasing attention since it provides clarity, transparency, and the ability to adapt to evolving scenarios.In this paper, we introduce a Controlled Value Vector Activation (ConVA) method that directly aligns the internal values of LLMs by interpreting how a value is encoded in their latent representations and modifies relevant activations to ensure consistent values in LLMs.To ensure an accurate and unbiased interpretation, we propose a context-controlled value vector identification method.To consistently control values without sacrificing model performance, we introduce a gated value vector activation method for effective and minimum degree of value control.Experiments show that our method achieves the highest control success rate across 10 basic values without hurting LLM performance and fluency, and ensures target values even with opposite and potentially malicious input prompts.Source code and data are available at https://github.com/hr-jin/ConVA.Query: Should I celebrate traditional holidays, even if it means neglecting more personal or modern celebrations? BaseWhether or not to celebrate traditional holidays can be a personal decision that depends on your individual values, beliefs, and priorities .Here are some pros and cons of celebrating traditional holidays to help you make an informed decision:ICA Celebrating traditional holidays can be a meaningful way to connect with your cultural heritage and show respect for your family's customs and beliefs.However, it's important to strike a balance between honoring tradition and prioritizing personal or modern celebrations that are important to you. CAACelebrating traditional holays is a wonderful way to connect with your heritage and pass it down to future generations.Here are some ways to celebrate traditional holays : ... ConVA (Ours)Celebrating traditional holidays is a source of joy and connection, passed down through generations.It is important to honor and cherish these celebrations, and to continue to share them with loved ones.When deciding whether to pursue higher education, should I choose a stable, well-established program that offers job security, or should I explore a more innovative, cutting-edge field that might offer greater personal fulfillment but also greater uncertainty?Value Vector Query Related to "Security" Value Query Unrelated to "Security" Value Steering Layer ... ...

Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood difference between chosen and rejected responses. However, existing methods assign equal importance to all tokens in the response, while humans focus on more meaningful parts. This leads to suboptimal preference optimization, as irrelevant or noisy tokens disproportionately influence DPO loss. To address this limitation, we propose Optimal Transport-based token weighting scheme for enhancing direct Preference Optimization (OTPO). By emphasizing semantically meaningful token pairs and de-emphasizing less relevant ones, our method introduces a context-aware token weighting scheme that yields a more contrastive reward difference estimate. This adaptive weighting enhances reward stability, improves interpretability, and ensures that preference optimization focuses on meaningful differences between responses. Extensive experiments have validated OTPO’s effectiveness in improving instruction-following ability across various settings.

Modeling human-like action-to-reaction generation has significant real-world applications, like human-robot interaction and games. Despite recent advancements in single-person motion generation, it is still challenging to well handle action-to-reaction generation, due to the difficulty of directly predicting reaction from action sequence without prompts, and the absence of a unified representation that effectively encodes multi-person motion. To address these challenges, we introduce Think-Then-React (TTR), a large language-model-based framework designed to generate human-like reactions. First, with our fine-grained multimodal training strategy, TTR is capable to unify two processes during inference: a thinking process that explicitly infers action intentions and reasons corresponding reaction description, which serve as semantic prompts, and a reacting process that predicts reactions based on input action and the inferred semantic prompts. Second, to effectively represent multi-person motion in language models, we propose a unified motion tokenizer by decoupling egocentric pose and absolute space features, which effectively represents action and reaction motion with same encoding. Extensive experiments demonstrate that TTR outperforms existing baselines, achieving significant improvements in evaluation metrics, such as reducing FID from 3.988 to 1.942.

Explainability is critical for recommender systems to ensure good user experience and facilitate designers to debug. However, generating explanations in recommender systems usually requires large efforts due to the dependency on additional data and case-by-case model design. One possible solution to these challenges is reasoning with logic rules, whose validity or confidence can automatically indicate high-quality explanations and formats are general. However, pioneer methods can be hardly applied in recommendation due to the high sparsity of interaction data, which raises the difficulty in accurately computing the rule validity, and the specific ranking-oriented task. To bridge this gap, we propose a general framework for Reco mmendation with lo gic r ule reasoning ( Recolor ) that satisfies three desirable properties. First, we explicitly estimate the rule validity to ensure well-grounded decisions, where a fuzzy logic validity module is designed for accurate estimation on highly sparse recommendation data. Second, we ensure the generality for both the types of input data and model architectures by designing a neural logic generation module, which decouples the user–item representation learning from the rule construction. Third, we integrate the two above-mentioned modules with a ranking-oriented BPR loss and achieve a unified optimization of explainability and accuracy. For any given neural recommendation model, our proposed logic rule reasoning framework can upgrade it to a self-explainable version. Numerical experiments and user studies on four public recommendation datasets with different levels of sparsity demonstrate that our framework shows high-validity rule explanations, generality in architecture and data, and high recommendation accuracy.

Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Persuasive dialogue requires multi-turn following and planning abilities to achieve the goal of persuading users, which is still challenging even for state-of-the-art large language models (LLMs).Previous works focus on retrievalbased models or generative models in a specific domain due to a lack of data across multiple domains.In this paper, we leverage GPT-4 to create the first multi-domain persuasive dialogue dataset DailyPersuasion.Then we propose a general method named PersuGPT to learn a persuasion model based on LLMs through intent-to-strategy reasoning, which summarizes the intent of user's utterance and reasons next strategy to respond.Moreover, we design a simulation-based preference optimization, which utilizes a learned user model and our model to simulate next turns and estimate their rewards more accurately.Experimental results on two datasets indicate that our proposed method outperforms all baselines in terms of automatic evaluation metric Win-Rate and human evaluation.The code and data are available at https://persugpt.github.io.

The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs).Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks.Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback.By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences.Extensive experiments on various datasets demonstrate that Proto-RM significantly improves the performance of reward models and LLMs in human feedback tasks, achieving comparable and usually better results than traditional methods, while requiring significantly less data. in datalimited scenarios.This research offers a promising direction for enhancing the efficiency of reward models and optimizing the fine-tuning of language models under restricted feedback conditions.

Free-text explanations are crucial for enhancing the interpretability of AI models. However, training models to generate high-quality free-text explanations is challenging, primarily due to the requirement of a substantial amount of human-written explanations, which can be expensive. Recently, Large language models (LLMs) like ChatGPT and GPT-4 have made remarkable progress in various NLP tasks while also providing explanations alongside their answers. Leveraging LLMs for data labeling offers a more cost-effective alternative. However, a key concern arises from the fact that the answers provided by LLMs are not entirely accurate, potentially introducing noise to both task outputs and explanation generation. To remedy this, we propose a new mechanism, Distillation with Explanations from LLMs. we observe that despite the incorrectness in LLMs-generated answers, their explanations are consistent with their answers. Leveraging this consistency, our method combines the ground truth labels and answers-explanations generated by LLMs, to simultaneously generate more accurate answers and the corresponding free-text explanations. Experimental results demonstrate that our approach achieves improved predictive performance and also generates explanations that exhibit greater alignment with the model’s task outputs.

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors.Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by LLMs.Yet their evaluation poses unique challenges, especially due to their non-local nature and high dimensional representation in a model's hidden space.Current methods approach concepts from different perspectives, lacking a unified formalization.This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging.To bridge the gap, we introduce a formal definition of concepts generalizing to diverse concept-based explanations' settings.Based on this, we quantify the faithfulness of a concept explanation via perturbation.We ensure adequate perturbation in the highdimensional space for different concepts via an optimization problem.Readability is approximated via an automatic and deterministic measure, quantifying the coherence of patterns that maximally activate a concept while aligning with human understanding.Finally, based on measurement theory, we apply a metaevaluation method for evaluating these measures, generalizable to other types of explanations or tasks as well.Extensive experimental analysis has been conducted to inform the selection of explanation evaluation measures.

Image captioning, which generates natural language descriptions of images, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities of machines with humans through statistical fitting existing datasets. While effective for normal images, they may struggle to accurately describe those where certain parts of the image are obscured or edited, unlike humans who excel in such cases. These weaknesses, including hallucinations and limited interpretability, often hinder performance in scenarios with shifted association patterns. In this paper, we present a generic image captioning framework that employs causal inference to make existing models more capable of interventional tasks, and counterfactually explainable. Our approach includes two variants leveraging either total effect or natural direct effect. Integrating them into the training process enables models to handle counterfactual scenarios, increasing their generalizability. Extensive experiments on various datasets show that our method effectively reduces hallucinations and improves the model's faithfulness to images, demonstrating high portability across both small-scale and large-scale image-to-text models. The code is available at https://github.com/Aman-4-Real/See-or-Guess.

Jing Yao, Xiaoyuan Yi, Yifan Gong, Xiting Wang, Xing Xie. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively guides the attacks by accurately interpreting LLMs' safety mechanisms. We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks with automatically selected perturbation hyperparameters. Both automatic and human evaluations demonstrate that our attack method significantly improves the attack success rate and response quality while requiring less training data. Additionally, we find that our generated attack prompts may be transferable to GPT-4, and the embedding-level attacks may also be transferred to other white-box LLMs whose parameters are known. Our experiments further uncover the safety risks present in current LLMs. For example, in our evaluation of seven open-source LLMs, we observe an average attack success rate of 99.14%, based on the classic keyword-matching criterion. Finally, we provide insights into the safety mechanism of LLMs. The code is available at https://github.com/SproutNan/AI-Safety_SCAV.

In this article, we study the problem of personalized news headline generation, which aims to produce not only concise and fact-consistent titles for news articles but also decorate these titles as personalized irresistible reading invitations by incorporating readers’ preferences. We propose an approach named PNG ( P ersonalized N ews headline G enerator) by utilizing distant supervision in readers’ past click behaviors to resolve. First, user preference representations are learned through a knowledge-aware user encoder that comprehensively captures the genuine, sequential, and flash interests of users reflected in their historical clicked news. Then, a user-perturbed pointer-generator network is devised to accomplish the headline generation in which the learned user representations implicitly affect the word prediction. The proposed model is optimized by reinforcement learning solvers where indicators on factual, personalized, and linguistic aspects of the generated headline are regarded as rewards. Extensive experiments are conducted on the real-world dataset PENS, 1 which is a large-scale benchmark collected from Microsoft News. Both the quantitative and qualitative results validate the effectiveness of our approach.

In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which automatically learns a bias to improve predictive performance for varying data sizes, especially low-resource settings. Our prototypical fine-tuning approach can automatically adjust the model capacity according to the number of data points and the model's inherent attributes. Moreover, we propose four principles for effective prototype fine-tuning towards the optimal solution. Experimental results across various datasets show that our work achieves significant performance improvements under various low-resource settings, as well as comparable and usually better performances in high-resource scenarios.

Self-training (ST) has prospered again in language understanding by augmenting the finetuning of big pre-trained models when labeled data is insufficient.However, it remains challenging to incorporate ST into attributecontrollable language generation.Augmented only by self-generated pseudo text, generation models over-exploit the previously learned text space and fail to explore a larger one, suffering from a restricted generalization boundary and limited controllability.In this work, we propose DuNST, a novel ST framework to tackle these problems.DuNST jointly models text generation and classification as a dual process and further perturbs and escapes from the collapsed space by adding two kinds of flexible noise.In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase.Theoretically, we show that DuNST can be viewed as enhancing the exploration of the potentially larger real text space while maintaining exploitation, guaranteeing improved performance.Experiments on three controllable generation tasks show that DuNST significantly boosts control accuracy with comparable generation fluency and diversity against several strong baselines.

Existing reinforcement learning (RL) mainly utilize online or offline settings. The online methods explore the environment with expensive time cost, and the offline methods efficiently obtain reward signals by sacrificing the exploration capability. We propose semi-offline RL, a novel paradigm that can smoothly transit from the offline setting to the online setting, balances the exploration capability and training cost, and provides a theoretical foundation for comparing different RL settings. Based on the semi-offline MDP formulation, we present the RL setting that is optimal in terms of optimization cost, asymptotic error, and overfitting error bound. Extensive experiments show that our semi-offline RL approach is effective in various text generation tasks and datasets, and yields comparable or usually better performance compared with the state-of-the-art methods.

This paper introduces a unified causal lens for understanding representative model interpretation methods. We show that their explanation scores align with the concept of average treatment effect in causal inference, which allows us to evaluate their relative strengths and limitations from a unified causal perspective. Based on our observations, we outline the major challenges in applying causal inference to model interpretation, including identifying common causes that can be generalized across instances and ensuring that explanations provide a complete causal explanation of model predictions. We then present CIMI, a Causality-Inspired Model Interpreter, which addresses these challenges. Our experiments show that CIMI provides more faithful and generalizable explanations with improved sampling efficiency, making it particularly suitable for larger pretrained models.

Algorithmic fairness has become an important machine learning problem, especially for mission-critical Web applications. This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Unlike existing models that target a single type of fairness, our model jointly optimizes for two fairness criteria—group fairness and counterfactual fairness—and hence makes fairer predictions at both the group and individual levels. Our model uses contrastive loss to generate embeddings that are indistinguishable for each protected group, while forcing the embeddings of counterfactual pairs to be similar. It then uses a self-knowledge distillation method to maintain the quality of representation for the downstream tasks. Extensive analysis over multiple datasets confirms the model’s validity and further shows the synergy of jointly addressing two fairness criteria, suggesting the model’s potential value in fair intelligent Web applications.

Collaborative Filtering (CF) is a widely used and effective technique for recommender systems. In recent decades, there have been significant advancements in latent embedding-based CF methods for improved accuracy, such as matrix factorization, neural collaborative filtering, and LightGCN. However, the explainability of these models has not been fully explored. Adding explainability to recommendation models can not only increase trust in the decision-making process, but also have multiple benefits such as providing persuasive explanations for item recommendations, creating explicit profiles for users and items, and assisting item producers in design improvements.

We focus on Maximum Inner Product Search (MIPS), which is an essential problem in many machine learning communities. Given a query, MIPS finds the most similar items with the maximum inner products. Methods for Nearest Neighbor Search (NNS) which is usually defined on metric space do not exhibit the satisfactory performance for MIPS problem since inner product is a non-metric function. However, inner products exhibit many good properties compared with metric functions, such as avoiding vanishing and exploding gradients. As a result, inner product is widely used in many recommendation systems, which makes efficient Maximum Inner Product Search a key for speeding up many recommendation systems. Graph-based methods for NNS problem show the superiorities compared with other class methods. Each data point of the database is mapped to a node of the proximity graph. Nearest neighbor search in the database can be converted to route on the proximity graph to find the nearest neighbor for the query. This technique can be used to solve MIPS problem. Instead of searching the nearest neighbor for the query, we search the item with a maximum inner product with query on the proximity graph. In this article, we propose a reinforcement model to train an agent to search on the proximity graph automatically for MIPS problem if we lack the ground truths of training queries. If we know the ground truths of some training queries, our model can also utilize these ground truths by imitation learning to improve the agent’s searchability. By experiments, we can see that our proposed mode which combines reinforcement learning with imitation learning shows the superiorities over the state-of-the-art methods.

The detection of fake news often requires sophisticated reasoning skills, such as logically combining information by considering word-level subtle clues. In this paper, we move towards fine-grained reasoning for fake news detection by better reflecting the logical processes of human thinking and enabling the modeling of subtle clues. In particular, we propose a fine-grained reasoning framework by following the human’s information-processing model, introduce a mutual-reinforcement-based method for incorporating human knowledge about which evidence is more important, and design a prior-aware bi-channel kernel graph network to model subtle differences between pieces of evidence. Extensive experiments show that our model outperforms the state-of-the-art methods and demonstrate the explainability of our approach.

Clickbait refers to deliberately created sensational or deceptive text for tricking readers into clicking, which severely hurts the web ecosystem. With a growing number of clickbaits on social media, developing automatic detection methods becomes essential. Nonetheless, the performance of existing neural classifiers is limited due to the underutilization of small labelled datasets. Inspired by related pedagogy theories that learning to write can promote comprehension ability, we propose a novel Contrastive Variational Modelling (CVM) framework to exploit the labelled data better. CVM models the conditional distributions of text and clickbait labels by predicting labels from text and generating text from labels simultaneously with Variational AutoEncoder and further differentiates the learned spaces under each label by a mixed contrastive learning loss. In this way, CVM can capture more underlying textual properties and hence utilize label information to its full potential, boosting detection performance. We theoretically demonstrate CVM as learning a joint distribution of text, clickbait label, and latent variable. Experiments on three clickbait detection datasets show our method's robustness to inadequate and biased labels, outperforming several recent strong baselines.

Chit-chat has been shown effective in engaging users in human-computer interaction. We find with a user study that generating appropriate chit-chat for news articles can help expand user interest and increase the probability that a user reads a recommended news article. Based on this observation, we propose a method to generate personalized chit-chat for news recommendation. Different from existing methods for personalized text generation, our method only requires an external chat corpus obtained from an online forum, which can be disconnected from the recommendation dataset from both the user and item (news) perspectives. This is achieved by designing a weak supervision method for estimating users' personalized interest in a chit-chat post by transferring knowledge learned by a news recommendation model. Based on the method for estimating user interest, a reinforcement learning framework is proposed to generate personalized chit-chat. Extensive experiments, including the automatic offline evaluation and user studies, demonstrate the effectiveness of our method.

The wide spread of fake news has caused serious societal issues. We propose a subgraph reasoning paradigm for fake news detection, which provides a crystal type of explainability by revealing which subgraphs of the news propagation network are the most important for news verification, and concurrently improves the generalization and discrimination power of graph-based detection models by removing task-irrelevant information. In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. We also design a curriculum-based optimization method to ensure better convergence and train the two parts in an end-to-end manner.

We present SELOR, a framework for integrating self-explaining capabilities into a given deep model to achieve both high prediction performance and human precision. By “human precision”, we refer to the degree to which humans agree with the reasons models provide for their predictions. Human precision affects user trust and allows users to collaborate closely with the model. We demonstrate that logic rule explanations naturally satisfy them with the expressive power required for good predictive performance. We then illustrate how to enable a deep model to predict and explain with logic rules. Our method does not require predefined logic rule sets or human annotations and can be learned efficiently and easily with widely-used deep learning modules in a differentiable way. Extensive experiments show that our method gives explanations closer to human decision logic than other methods while maintaining the performance of the deep learning model.

News recommendation aims to help online news platform users find their preferred news articles. Existing news recommendation methods usually learn models from historical user behaviors on news. However, these behaviors are usually biased on news providers. Models trained on biased user data may capture and even amplify the biases on news providers, and are unfair for some minority news providers. In this paper, we propose a provider fairness-aware news recommendation framework (named ProFairRec), which can learn news recommendation models fair for different news providers from biased user data. The core idea of ProFairRec is to learn provider-fair news representations and provider-fair user representations to achieve provider fairness. To learn provider-fair representations from biased data, we employ provider-biased representations to inherit provider bias from data. Provider-fair and -biased news representations are learned from news content and provider IDs respectively, which are further aggregated to build fair and biased user representations based on user click history. All of these representations are used in model training while only fair representations are used for user-news matching to achieve fair news recommendation. Besides, we propose an adversarial learning task on news provider discrimination to prevent provider-fair news representation from encoding provider bias. We also propose an orthogonal regularization on provider-fair and -biased representations to better reduce provider bias in provider-fair representations. Moreover, ProFairRec is a general framework and can be applied to different news recommendation methods. Extensive experiments on a public dataset verify that our ProFairRec approach can effectively improve the provider fairness of many existing methods and meanwhile maintain their recommendation accuracy.

Knowledge graphs (KGs) have been widely used to improve recommendation accuracy. The multi-hop paths on KGs also enable recommendation reasoning, which is considered a crystal type of explainability. In this paper, we propose a reinforcement learning framework for multi-level recommendation reasoning over KGs, which leverages both ontology-view and instance-view KGs to model multi-level user interests. This framework ensures convergence to a more satisfying solution by effectively transferring high-level knowledge to lower levels. Based on the framework, we propose a multi-level reasoning path extraction method, which automatically selects between high-level concepts and low-level ones to form reasoning paths that better reveal user interests. Experiments on three datasets demonstrate the effectiveness of our method.

The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually. Existing methods cannot meet the need for understanding different models in one framework due to the lack of a unified measure for explaining both low-level (e.g., words) and high-level (e.g., phrases) features. We have developed a visual analysis tool, DeepNLPVis, to enable a unified understanding of NLP models for text classification. The key idea is a mutual information-based measure, which provides quantitative explanations on how each layer of a model maintains the information of input words in a sample. We model the intra- and inter-word information at each layer measuring the importance of a word to the final prediction as well as the relationships between words, such as the formation of phrases. A multi-level visualization, which consists of a corpus-level, a sample-level, and a word-level visualization, supports the analysis from the overall training set to individual samples. Two case studies on classification tasks and comparison between models demonstrate that DeepNLPVis can help users effectively identify potential problems caused by samples and model architectures and then make informed improvements.

News recommendation is important for online news services. Existing news recommendation models are usually learned from users' news click behaviors. Usually the behaviors of users with the same sensitive attributes (e.g., genders) have similar patterns and news recommendation models can easily capture these patterns. It may lead to some biases related to sensitive user attributes in the recommendation results, e.g., always recommending sports news to male users, which is unfair since users may not receive diverse news information. In this paper, we propose a fairness-aware news recommendation approach with decomposed adversarial learning and orthogonality regularization, which can alleviate unfairness in news recommendation brought by the biases of sensitive user attributes. In our approach, we propose to decompose the user interest model into two components. One component aims to learn a bias-aware user embedding that captures the bias information on sensitive user attributes, and the other aims to learn a bias-free user embedding that only encodes attribute-independent user interest information for fairness-aware news recommendation. In addition, we propose to apply an attribute prediction task to the bias-aware user embedding to enhance its ability on bias modeling, and we apply adversarial learning to the bias-free user embedding to remove the bias information from it. Moreover, we propose an orthogonality regularization method to encourage the bias-free user embeddings to be orthogonal to the bias-aware one to better distinguish the bias-free user embedding from the bias-aware one. For fairness-aware news ranking, we only use the bias-free user embedding. Extensive experiments on benchmark dataset show that our approach can effectively improve fairness in news recommendation with minor performance loss.

Xiang Ao, Xiting Wang, Ling Luo, Ying Qiao, Qing He, Xing Xie. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

We study two user demands that are important during the exploitation of explanations in practice: 1) understanding the overall model behavior faithfully with limited cognitive load and 2) predicting the model behavior accurately on unseen instances. We illustrate that the two user demands correspond to two major sub-processes in the human cognitive process and propose a unified framework to fulfill them simultaneously. Given a local explanation method, our framework jointly 1) learns a limited number of groupwise explanations that interpret the model behavior on most instances with high fidelity and 2) specifies the region where each explanation applies. Experiments on six datasets demonstrate the effectiveness of our method.

News recommendation systems play a key role in online news reading service. Knowledge graphs (KG), which contain comprehensive structural knowledge, are well known for their potential to enhance both accuracy and explainability. While existing works intensively study using KG to improve news recommendation accuracy, using KG for news recommendation reasoning has not been fully explored. A few works such as KPRN [18], [22] and ADAC [25] have discussed knowledge reasoning in some other recommendation domains such as music or movie, but their methods are not practical for the news. How to make reasoning scalable to generic KGs, easy to deploy for real-time serving and meanwhile elastic for both recall and ranking stages remains an open question.

We study how pretrained language models can be enhanced by using deep reinforcement learning to generate attractive text advertisements that reach the high quality standard of real-world advertiser mediums. To improve ad attractiveness without hampering user experience, we propose a model-based reinforcement learning framework for text ad generation, which constructs a model for the environment dynamics and avoids large sample complexity. Based on the framework, we develop Masked-Sequence Policy Gradient, a reinforcement learning algorithm that integrates efficiently with pretrained models and explores the action space effectively. Our method has been deployed to production in Microsoft Bing. Automatic offline experiments, human evaluation, and online experiments demonstrate the superior performance of our method.

As a key application of artificial intelligence, recommender systems are among the most pervasive computer aided systems to help users find potential items of interests. Recently, researchers paid considerable attention to fairness issues for artificial intelligence applications. Most of these approaches assumed independence of instances, and designed sophisticated models to eliminate the sensitive information to facilitate fairness. However, recommender systems differ greatly from these approaches as users and items naturally form a user-item bipartite graph, and are collaboratively correlated in the graph structure. In this paper, we propose a novel graph based technique for ensuring fairness of any recommendation models. Here, the fairness requirements refer to not exposing sensitive feature set in the user modeling process. Specifically, given the original embeddings from any recommendation models, we learn a composition of filters that transform each user’s and each item’s original embeddings into a filtered embedding space based on the sensitive feature set. For each user, this transformation is achieved under the adversarial learning of a user-centric graph, in order to obfuscate each sensitive feature between both the filtered user embedding and the sub graph structures of this user. Finally, extensive experimental results clearly show the effectiveness of our proposed model for fair recommendation. We publish the source code at https://github.com/newlei/FairGo.

The advent of large-scale biomedical data and computational algorithms provides new opportunities for drug repurposing and discovery. It is of great interest to find an appropriate data representation and modeling method to facilitate these studies. The anatomical therapeutic chemical (ATC) classification system, proposed by the World Health Organization (WHO), is an essential source of information for drug repurposing and discovery. Besides, computational methods are applied to predict drug ATC classification. We conducted a systematic review of ATC computational prediction studies and revealed the differences in data sets, data representation, algorithm approaches, and evaluation metrics. We then proposed a deep fusion learning (DFL) framework to optimize the ATC prediction model, namely DeepATC. The methods based on graph convolutional network, inferring biological network and multimodel attentive fusion network were applied in DeepATC to extract the molecular topological information and low-dimensional representation from the molecular graph and heterogeneous biological networks. The results indicated that DeepATC achieved superior model performance with area under the curve (AUC) value at 0.968. Furthermore, the DFL framework was performed for the transcriptome data-based ATC prediction, as well as another independent task that is significantly relevant to drug discovery, namely drug-target interaction. The DFL-based model achieved excellent performance in the above-extended validation task, suggesting that the idea of aggregating the heterogeneous biological network and node's (molecule or protein) self-topological features will bring inspiration for broader drug repurposing and discovery research.

Semi-supervised learning (SSL) provides a way to improve the performance of prediction models (e.g., classifier) via the usage of unlabeled samples. An effective and widely used method is to construct a graph that describes the relationship between labeled and unlabeled samples. Practical experience indicates that graph quality significantly affects the model performance. In this paper, we present a visual analysis method that interactively constructs a high-quality graph for better model performance. In particular, we propose an interactive graph construction method based on the large margin principle. We have developed a river visualization and a hybrid visualization that combines a scatterplot, a node-link diagram, and a bar chart to convey the label propagation of graph-based SSL. Based on the understanding of the propagation, a user can select regions of interest to inspect and modify the graph. We conducted two case studies to showcase how our method facilitates the exploitation of labeled and unlabeled samples for improving model performance.

Hierarchical clustering is an important technique to organize big data for exploratory data analysis. However, existing one-size-fits-all hierarchical clustering methods often fail to meet the diverse needs of different users. To address this challenge, we present an interactive steering method to visually supervise constrained hierarchical clustering by utilizing both public knowledge (e.g., Wikipedia) and private knowledge from users. The novelty of our approach includes 1) automatically constructing constraints for hierarchical clustering using knowledge (knowledge-driven) and intrinsic data distribution (data-driven), and 2) enabling the interactive steering of clustering through a visual interface (user-driven). Our method first maps each data item to the most relevant items in a knowledge base. An initial constraint tree is then extracted using the ant colony optimization algorithm. The algorithm balances the tree width and depth and covers the data items with high confidence. Given the constraint tree, the data items are hierarchically clustered using evolutionary Bayesian rose tree. To clearly convey the hierarchical clustering results, an uncertainty-aware tree visualization has been developed to enable users to quickly locate the most uncertain sub-hierarchies and interactively improve them. The quantitative evaluation and case study demonstrate that the proposed approach facilitates the building of customized clustering trees in an efficient and effective manner.

Existing review-based recommendation models mainly learn long- term user and item representations from a set of reviews. Due to the ignorance of rich side information of reviews, these models suffer from two drawbacks: 1) they fail to capture short-term changes of user preferences and item features reflected in reviews and 2) they cannot accurately model high-order user-item collaborative signals from reviews. To overcome these limitations, we propose a multi-view approach named Set-Sequence-Graph (SSG), to augment existing single-view (i.e., view of set) methods by introducing two additional views of exploiting reviews: sequence and graph. In particular, with reviews organized in forms of set, sequence, and graph respectively, we design a three-way encoder architecture that jointly captures long-term (set), short-term (sequence), and collaborative (graph) features of users and items for recommendation. For the sequence encoder, we propose a short-term priority attention network that explicitly takes the order and personalized time intervals of reviews into consideration. For the graph encoder, we design a novel review-aware graph attention network to model high-order multi-aspect relations in the user-item graph. To combat the potential redundancy in captured features, our fusion module employs a cross-view decorrelation mechanism to encourage diverse representations from multiple views for integration. Experiments on public datasets demonstrate that SSG significantly outperforms state-of-the-art methods.

Distance metric learning (DML) is to learn a representation space equipped with a metric, such that similar examples are closer than dissimilar examples concerning the metric. The recent success of DNNs motivates many DML losses that encourage the intra-class compactness and inter-class separability. The trade-off between inter-class compactness and inter-class separability shapes the DML representation space by determining how much information of the original inputs to retain. In this paper, we propose a Distance Metric Learning with Joint Representation Diversification (JRD) that allows a better balancing point between intra-class compactness and inter-class separability. Specifically, we propose a Joint Representation Similarity regularizer that captures different abstract levels of invariant features and diversifies the joint distributions of representations across multiple layers. Experiments on three deep DML benchmark datasets demonstrate the effectiveness of the proposed approach.

Recent studies have shown that both accuracy and explainability are important for recommendation. In this paper, we introduce explainable conversational recommendation, which enables incremental improvement of both recommendation accuracy and explanation quality through multi-turn user-model conversation. We show how the problem can be formulated, and design an incremental multi-task learning framework that enables tight collaboration between recommendation prediction, explanation generation, and user feedback integration. We also propose a multi-view feedback integration method to enable effective incremental model update. Empirical results demonstrate that our model not only consistently improves the recommendation accuracy but also generates explanations that fit user interests reflected in the feedbacks.

Knowledge graphs have been widely adopted to improve recommendation accuracy. The multi-hop user-item connections on knowledge graphs also endow reasoning about why an item is recommended. However, reasoning on paths is a complex combinatorial optimization problem. Traditional recommendation methods usually adopt brute-force methods to find feasible paths, which results in issues related to convergence and explainability. In this paper, we address these issues by better supervising the path finding process. The key idea is to extract imperfect path demonstrations with minimum labeling efforts and effectively leverage these demonstrations to guide path finding. In particular, we design a demonstration-based knowledge graph reasoning framework for explainable recommendation. We also propose an ADversarial Actor-Critic (ADAC) model for the demonstration-guided path finding. Experiments on three real-world benchmarks show that our method converges more quickly than the state-of-the-art baseline and achieves better recommendation accuracy and explainability.

Recommender systems have been playing an increasingly important role in our daily life due to the explosive growth of information. Accuracy and explainability are two core aspects when we evaluate a recommendation model and have become one of the fundamental trade-offs in machine learning. In this paper, we propose to alleviate the trade-off between accuracy and explainability by developing an explainable deep model that combines the advantages of deep learning-based models and existing explainable methods. The basic idea is to build an initial network based on an explainable deep hierarchy (e.g., Microsoft Concept Graph) and improve the model accuracy by optimizing key variables in the hierarchy (e.g., node importance and relevance). To ensure accurate rating prediction, we propose an attentive multi-view learning framework. The framework enables us to handle sparse and noisy data by co-regularizing among different feature levels and combining predictions attentively. To mine readable explanations from the hierarchy, we formulate personalized explanation generation as a constrained tree node selection problem and propose a dynamic programming algorithm to solve it. Experimental results show that our model outperforms state-of-the-art methods in terms of both accuracy and explainability.

In modern cities, complaining has become an important way for citizens to report emerging urban issues to governments for quick response. For ease of retrieval and handling, government officials usually organize citizen complaints by manually assigning tags to them, which is inefficient and cannot always guarantee the quality of assigned tags. This work attempts to solve this problem by recommending tags for citizen complaints. Although there exist many studies on tag recommendation for textual content, few of them consider two characteristics of citizen complaints, i.e., the spatio-temporal correlations and the taxonomy of candidate tags. In this paper, we propose a novel Spatio-Temporal Taxonomy-Aware Recommendation model (STAR), to recommend tags for citizen complaints by jointly incorporating spatio-temporal information of complaints and the taxonomy of candidate tags. Specifically, STAR first exploits two parallel channels to learn representations for textual and spatio-temporal information. To effectively leverage the taxonomy of tags, we design chained neural networks that gradually refine the representations and perform hierarchical recommendation under a novel taxonomy constraint. A fusion module is further proposed to adaptively integrate contributions of textual and spatio-temporal information in a tag-specific manner. We conduct extensive experiments on a real-world dataset and demonstrate that STAR significantly performs better than state-of-the-art methods. The effectiveness of key components in our model is also verified through ablation studies.

Diagnosis prediction, which aims to predict future health information of patients from historical electronic health records (EHRs), is a core research task in personalized healthcare. Although some RNN-based methods have been proposed to model sequential EHR data, these methods have two major issues. First, they cannot capture fine-grained progression patterns of patient health conditions. Second, they do not consider the mutual effect between important context (e.g., patient demographics) and historical diagnosis. To tackle these challenges, we propose a model called Co-Attention Memory networks for diagnosis Prediction (CAMP), which tightly integrates historical records, fine-grained patient conditions, and demographics with a three-way interaction architecture built on co-attention. Our model augments RNNs with a memory network to enrich the representation capacity. The memory network enables analysis of fine-grained patient conditions by explicitly incorporating a taxonomy of diseases into an array of memory slots. We instantiate the READ/WRITE operations of the memory network so that the memory cooperates effectively with the patient demographics through co-attention mechanism. Experiments on real-world datasets demonstrate that CAMP consistently performs better than state-of-the-art methods.

We define a unified information-based measure to provide quantitative explanations on how intermediate layers of deep Natural Language Processing (NLP) models leverage information of input words. Our method advances existing explanation methods by addressing issues in coherency and generality. Explanations generated by using our method are consistent and faithful across different timestamps, layers, and models. We show how our method can be applied to four widely used models in NLP and explain their performances on three real-world benchmark datasets.

Despite widespread adoption, recommender systems remain mostly black boxes. Recently, providing explanations about why items are recommended has attracted increasing attention due to its capability to enhance user trust and satisfaction. In this paper, we propose a co-attentive multi-task learning model for explainable recommendation. Our model improves both prediction accuracy and explainability of recommendation by fully exploiting the correlations between the recommendation task and the explanation task. In particular, we design an encoder-selector-decoder architecture inspired by human's information-processing model in cognitive psychology. We also propose a hierarchical co-attentive selector to effectively model the cross knowledge transferred for both tasks. Our model not only enhances prediction accuracy of the recommendation task, but also generates linguistic explanations that are fluent, useful, and highly personalized. Experiments on three public datasets demonstrate the effectiveness of our model.

Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online social networks, social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a social platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' social connections. As social influence recursively propagates and diffuses in the social network, each user's interests change in the recursive process. Nevertheless, the current social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive social diffusion process for social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

Visual text analytics has recently emerged as one of the most prominent topics in both academic research and the commercial world. To provide an overview of the relevant techniques and analysis tasks, as well as the relationships between them, we comprehensively analyzed 263 visualization papers and 4,346 mining papers published between 1992-2017 in two fields: visualization and text mining. From the analysis, we derived around 300 concepts (visualization techniques, mining techniques, and analysis tasks) and built a taxonomy for each type of concept. The co-occurrence relationships between the concepts were also extracted. Our research can be used as a stepping-stone for other researchers to 1) understand a common set of concepts used in this research topic; 2) facilitate the exploration of the relationships between visualization techniques, mining techniques, and analysis tasks; 3) understand the current practice in developing visual text analytics tools; 4) seek potential research opportunities by narrowing the gulf between visualization and mining techniques based on the analysis tasks; and 5) analyze other interdisciplinary research areas in a similar way. We have also contributed a web-based visualization tool for analyzing and understanding research trends and opportunities in visual text analytics.

Explainable recommendation, which provides explanations about why an item is recommended, has attracted increasing attention due to its ability in helping users make better decisions and increasing users' trust in the system. Existing explainable recommendation methods either ignore the working mechanism of the recommendation model or are designed for a specific recommendation model. Moreover, it is difficult for existing methods to ensure the presentation quality of the explanations (e.g., consistency). To solve these problems, we design a reinforcement learning framework for explainable recommendation. Our framework can explain any recommendation model (model-agnostic) and can flexibly control the explanation quality based on the application scenario. To demonstrate the effectiveness of our framework, we show how it can be used for generating sentence-level explanations. Specifically, we instantiate the explanation generator in the framework with a personalized-attention-based neural network. Offline experiments demonstrate that our method can well explain both collaborative filtering methods and deep-learning-based models. Evaluation with human subjects shows that the explanations generated by our method are significantly more useful than the explanations generated by the baselines.

We present a visual analysis method for interactively recomposing a large number of photos based on example photos with high-quality composition. The recomposition method is formulated as a matching problem between photos. The key to this formulation is a new metric for accurately measuring the composition distance between photos. We have also developed an earth-mover-distance-based online metric learning algorithm to support the interactive adjustment of the composition distance based on user preferences. To better convey the compositions of a large number of example photos, we have developed a multi-level, example photo layout method to balance multiple factors such as compactness, aspect ratio, composition distance, stability, and overlaps. By introducing an EulerSmooth-based straightening method, the composition of each photos is clearly displayed. The effectiveness and usefulness of the method has been demonstrated by the experimental results, user study, and case studies.

Tree boosting, which combines weak learners (typically decision trees) to generate a strong learner, is a highly effective and widely used machine learning method. However, the development of a high performance tree boosting model is a time-consuming process that requires numerous trial-and-error experiments. To tackle this issue, we have developed a visual diagnosis tool, BOOSTVis, to help experts quickly analyze and diagnose the training process of tree boosting. In particular, we have designed a temporal confusion matrix visualization, and combined it with a t-SNE projection and a tree visualization. These visualization components work together to provide a comprehensive overview of a tree boosting model, and enable an effective diagnosis of an unsatisfactory training process. Two case studies that were conducted on the Otto Group Product Classification Challenge dataset demonstrate that BOOSTVis can provide informative feedback and guidance to improve understanding and diagnosis of tree boosting algorithms.

Although several effective learning-from-crowd methods have been developed to infer correct labels from noisy crowdsourced labels, a method for post-processed expert validation is still needed. This paper introduces a semi-supervised learning algorithm that is capable of selecting the most informative instances and maximizing the influence of expert labels. Specifically, we have developed a complete uncertainty assessment to facilitate the selection of the most informative instances. The expert labels are then propagated to similar instances via regularized Bayesian inference. Experiments on both real-world and simulated datasets indicate that given a specific accuracy goal (e.g., 95%) our method reduces expert effort from 39% to 60% compared with the state-of-the-art method.

Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and data mining problems. Dramatic advances in big data analytics have led to a wide variety of interactive model analysis tasks. In this paper, we present a comprehensive analysis and interpretation of this rapidly developing area. Specifically, we classify the relevant work into three categories: understanding, diagnosis, and refinement. Each category is exemplified by recent influential work. Possible future research opportunities are also explored and discussed.

In many applications, ideas that are described by a set of words often flow between different groups. To facilitate users in analyzing the flow, we present a method to model the flow behaviors that aims at identifying the lead-lag relationships between word clusters of different user groups. In particular, an improved Bayesian conditional cointegration based on dynamic time warping is employed to learn links between words in different groups. A tensor-based technique is developed to cluster these linked words into different clusters (ideas) and track the flow of ideas. The main feature of the tensor representation is that we introduce two additional dimensions to represent both time and lead-lag relationships. Experiments on both synthetic and real datasets show that our method is more effective than methods based on traditional clustering techniques and achieves better accuracy. A case study was conducted to demonstrate the usefulness of our method in helping users understand the flow of ideas between different user groups on social media.

We present an online visual analytics approach to helping users explore and understand hierarchical topic evolution in high-volume text streams. The key idea behind this approach is to identify representative topics in incoming documents and align them with the existing representative topics that they immediately follow (in time). To this end, we learn a set of streaming tree cuts from topic trees based on user-selected focus nodes. A dynamic Bayesian network model has been developed to derive the tree cuts in the incoming topic trees to balance the fitness of each tree cut and the smoothness between adjacent tree cuts. By connecting the corresponding topics at different times, we are able to provide an overview of the evolving hierarchical topics. A sedimentation-based visualization has been designed to enable the interactive analysis of streaming text data from global patterns to local details. We evaluated our method on real-world datasets and the results are generally favorable.

This paper presents a visual analytics approach to analyzing a full picture of relevant topics discussed in multiple sources, such as news, blogs, or micro-blogs. The full picture consists of a number of common topics covered by multiple sources, as well as distinctive topics from each source. Our approach models each textual corpus as a topic graph. These graphs are then matched using a consistent graph matching method. Next, we develop a level-of-detail (LOD) visualization that balances both readability and stability. Accordingly, the resulting visualization enhances the ability of users to understand and analyze the matched graph from multiple perspectives. By incorporating metric learning and feature selection into the graph matching algorithm, we allow users to interactively modify the graph matching result based on their information needs. We have applied our approach to various types of data, including news articles, tweets, and blog data. Quantitative evaluation and real-world case studies demonstrate the promise of our approach, especially in support of examining a topic-graph-based full picture at different levels of detail.

We present an evolutionary multi-branch tree clustering method to model hierarchical topics and their evolutionary patterns over time. The method builds evolutionary trees in a Bayesian online filtering framework. The tree construction is formulated as an online posterior estimation problem, which well balances both the fitness of the current tree and the smoothness between trees. The state-of-the-art multi-branch clustering method, Bayesian rose trees, is employed to generate a topic tree with a high fitness value. A constraint model is also introduced to preserve the smoothness between trees. A set of comprehensive experiments on real world news data demonstrates that the proposed method better incorporates historical tree information and is more efficient and effective than the traditional evolutionary hierarchical clustering algorithm. In contrast to our previous method[31], we implement two additional baseline algorithms to compare them with our algorithm. We also evaluate the performance of the clustering algorithm based on multiple constraint trees. Furthermore, two case studies are conducted to demonstrate the effectiveness and usefulness of our algorithm in helping users understand the major hierarchical topic evolutionary patterns in text data.

Research into social network analysis has shown that graph metrics, such as degree and closeness, are often used to summarize structural changes in a dynamic graph. However there have been few visual analytics approaches that have been proposed to help analysts study graph evolutions in the context of graph metrics. In this paper, we present a novel approach, called GraphFlow, to visualize dynamic graphs. In contrast to previous approaches that provide users with an animated visualization, GraphFlow offers a static flow visualization that summarizes the graph metrics of the entire graph and its evolution over time. Our solution supports the discovery of high-level patterns that are difficult to identify in an animation or in individual static representations. In addition, GraphFlow provides users with a set of interactions to create filtered views. These views allow users to investigate why a particular pattern has occurred. We showcase the versatility of GraphFlow using two different datasets and describe how it can help users gain insights into complex dynamic graphs.

Understanding topic hierarchies in text streams and their evolution patterns over time is very important in many applications. In this paper, we propose an evolutionary multi-branch tree clustering method for streaming text data. We build evolutionary trees in a Bayesian online filtering framework. The tree construction is formulated as an online posterior estimation problem, which considers both the likelihood of the current tree and conditional prior given the previous tree. We also introduce a constraint model to compute the conditional prior of a tree in the multi-branch setting. Experiments on real world news data demonstrate that our algorithm can better incorporate historical tree information and is more efficient and effective than the traditional evolutionary hierarchical clustering algorithm.