Arrow Research search

Author name cluster

Daniel Zeng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

37 papers
1 author row

Possible papers

37

IS Journal 2026 Journal Article

A Dynamic Framework to Integrate Deep Reinforcement Learning with Hierarchical Symbolic Plans

  • Xuelong Liu
  • Nuo Chen
  • Wenji Mao
  • Daniel Zeng

Neuro-symbolic framework has become one of the mainstream paradigms in intelligent system design. For intelligent decision-making, Reinforcement Learning (RL) and automated planning are the representative neural and symbolic techniques, respectively, which can facilitate each other. Despite the rapid development and wide applications of deep RL, its drawbacks on sample efficiency and convergence in sparse-reward environments have become the major obstacles to hinder its advancement. To address these issues, in this paper, we propose a neuro-symbolic framework to integrate deep RL with hierarchical plans. Specifically, we develop a selective Monte-Carlo Tree Search algorithm, in which hierarchical plans are dynamically constructed during the learning process. The constructed plans, in turn, provide the high-level guidance for RL to constrain the subtasks leading to goal attainment, thus reducing useless/redundant exploration in RL. Experiments on five challenging scenarios show that our framework achieves better sample efficiency and faster convergence compared to the state-of-the-art approaches.

Details DOI

AAMAS Conference 2025 Conference Paper

Offline Meta Reinforcement Learning with Weighted Policy Constraints and Proximal Context Collection

  • Haorui Li
  • Jiaqi Liang
  • Linjing Li
  • Daniel Zeng

Offline meta-reinforcement learning (OMRL) encounters two key challenges: effectively learning the meta-policy from offline datasets and correctly inferring unseen tasks. Existing methods often address the first challenge by imposing policy constraints, but are limited by the suboptimal actions in offline datasets. For the second challenge, most focus on meta-training without enhancing task inference during meta-testing. To address these issues, we propose a novel method called weighted policy conStraints and proximal contExt coLlECtion sTrategy for OMRL (SELECT). During metatraining, we integrate policy constraints with weighted behavior cloning, allowing for more flexible policy learning while maintaining desirable behaviors. In the meta-testing phase, SELECT introduces a proximal context collection strategy that balances exploration and exploitation. This strategy gathers high-quality context, improving task inference and adaptation to unseen tasks. Experimental results show that SELECT significantly reduces the distributional shift, enhances the meta-policy’s generalization, and outperforms state-of-the-art methods across various domains.

PDF

IS Journal 2024 Journal Article

Mining the User’s Personality With an Attention-Based Label Prompt Method

  • Liping Chen
  • Yilin Wu
  • Qiudan Li
  • Yuxuan Song
  • Chenyu Yuan
  • Daniel Zeng

Identifying personality traits from online posts is becoming a hot research topic and often plays an essential role in behavior analysis and recommender systems. Previous studies have adopted deep neural networks or pretrained language models to mine semantic information without considering the prompting role of personality labels and the connection between writing style and personality traits. This paper proposes an attention-based label-prompt method (ABLPM) to address the aforementioned challenges. The ABLPM utilizes label-prompt semantic learning to generate personality representations while integrating writing style into text semantics. Then, the style-enhanced attention mechanism further constructs the deep dynamic interaction among the personality label, text semantics, and writing style. Finally, multiple loss functions optimize the distribution of the generated personality representations. The experimental results with the MyPersonality and topic-oriented social media comment datasets demonstrate the efficacy of the proposed method.

Details DOI

IS Journal 2024 Journal Article

SHAPAttack: Shapley-Guided Multigranularity Adversarial Attack Against Text Transformers

  • Jiahui Shi
  • Linjing Li
  • Daniel Zeng

Despite the great success of text transformers, recent studies have revealed their vulnerability to textual adversarial attacks. Existing attack methods are limited to a single granularity and often suffer from a low attack success rate and a high query cost. To mitigate these issues, we propose a Shapley-guided multigranularity adversarial attack (SHAPAttack) that generates adversarial examples (AEs). SHAPAttack expands the perturbation space by combining granularities at both the word and phrase levels, which enhances the diversity of the generated AEs. To improve attack efficiency and reduce the query cost, SHAPAttack adopts a query-free constituent importance ranking method guided by the Shapley value to measure the importance of each constituent. We conduct extensive experiments on three benchmark datasets across three text transformers. The experimental results demonstrate that SHAPAttack outperforms strong baselines in terms of both attack success rate and model queries, indicating the effectiveness and efficiency of the proposed method.

Details DOI

IS Journal 2023 Journal Article

CRule: Category-Aware Symbolic Multihop Reasoning on Knowledge Graphs

  • Zikang Wang
  • Linjing Li
  • Jinlin Li
  • Pengfei Zhao
  • Daniel Zeng

Multihop reasoning is essential in knowledge graph (KG) research and applications. Current methods rely on specific KG entities, while human cognition operates at a more abstract level. This article proposes a category-aware rule-based (CRule) approach for symbolic multihop reasoning. Specifically, given a KG, CRule first categorizes entities and constructs a category-aware KG; it then uses rules retrieved from the categorized KG to perform multihop reasoning on the original KG. Experiments on five datasets show that CRule is simple, is effective, and combines the advantages of symbolic and neural network methods. It overcomes symbolic reasoning’s complexity limitations, can perform reasoning on KGs of more than 300, 000 edges, and can be three times more efficient than neural network models.

Details DOI

NeurIPS Conference 2023 Conference Paper

PRODIGY: Enabling In-context Learning Over Graphs

  • Qian Huang
  • Hongyu Ren
  • Peng Chen
  • Gregor Kržmanc
  • Daniel Zeng
  • Percy S. Liang
  • Jure Leskovec

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how in-context learning could be performed over graphs is unexplored. In this paper, we develop \textbf{Pr}etraining \textbf{O}ver \textbf{D}iverse \textbf{I}n-Context \textbf{G}raph S\textbf{y}stems (PRODIGY), the first pretraining framework that enables in-context learning over graphs. The key idea of our framework is to formulate in-context learning over graphs with a novel \emph{prompt graph} representation, which connects prompt examples and queries. We then propose a graph neural network architecture over the prompt graph and a corresponding family of in-context pretraining objectives. With PRODIGY, the pretrained model can directly perform novel downstream classification tasks on unseen graphs via in-context learning. We provide empirical evidence of the effectiveness of our framework by showcasing its strong in-context learning performance on tasks involving citation networks and knowledge graphs. Our approach outperforms the in-context learning accuracy of contrastive pretraining baselines with hard-coded adaptation by 18\% on average across all setups. Moreover, it also outperforms standard finetuning with limited data by 33\% on average with in-context learning.

PDF Details

IS Journal 2022 Journal Article

An Orthogonal Subspace Decomposition Method for Cross-Modal Retrieval

  • Zhixiong Zeng
  • Nan Xu
  • Wenji Mao
  • Daniel Zeng

As a general characteristic observed in the real-world datasets, multimodal data are usually partially associated, which comprise the commonly shared information across modalities (i. e. , modality-shared information) and the specific information only exists in a single modality (i. e. , modality-specific information). Cross-modal retrieval methods typically use these information in multimodal data as a whole and project them into a common representation space to calculate the similarity measure. In fact, only modality-shared information can be well aligned in the learning of common representations, whereas modality-specific information usually brings about interference term and decreases the performance of cross-modal retrieval. The explicit distinction and utilization of these two kinds of multimodal information are important to cross-modal retrieval, but rarely studied in previous research. In this article, we explicitly distinguish and utilize modality-shared and modality-specific features for learning better common representations, and propose an orthogonal subspace decomposition method for cross-modal retrieval, named orthogonal subspace decomposition method. Specifically, we introduce a structure preservation loss to ensure modality-shared information to be well preserved, and optimize the intramodal discrimination loss and intermodal invariance loss to learn the semantic discriminative features for cross-modal retrieval. We conduct comprehensive experiments on four widely used benchmark datasets, and the experimental results demonstrate the effectiveness of our proposed method.

Details DOI

IJCAI Conference 2022 Conference Paper

Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

  • Jiazhi Xu
  • Sheng Huang
  • Fengtao Zhou
  • Luwen Huangfu
  • Daniel Zeng
  • Bo Liu

Multi-Label Image Classification (MLIC) appro-aches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features and lead to model overfitting. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The source code is released at https: //github. com/Robbie-Xu/CPSD.

PDF Details DOI

IS Journal 2021 Journal Article

Learning Parameters for a Generalized Vidale-Wolfe Response Model With Flexible Ad Elasticity and Word-of-Mouth

  • Yanwu Yang
  • Baozhu Feng
  • Daniel Zeng

In this research, we investigate a generalized form of Vidale-Wolfe (GVW) model. One key element of our modeling work is that the GVW model contains two useful indexes representing advertiser's elasticity and the word-of-mouth (WoM) effect, respectively. Moreover, we discuss some desirable properties of the GVW model, and present a deep neural network-based estimation method to learn its parameters. Furthermore, based on three realworld datasets, we conduct computational experiments to validate the GVW model and identified properties. In addition, we also discuss potential advantages of the GVW model over econometric models. The research outcome shows that both the ad elasticity index and the WoM index have significant influences on advertising responses, and the GVW model has potential advantages over econometric models of advertising, in terms of several interesting phenomena drawn from practical advertising situations. The GVW model and its deep learning-based estimation method provide a basis to support big data-driven advertising analytics and decision makings; in the meanwhile, identified properties and experimental findings of this research illuminate critical managerial insights for advertisers in various advertising forms.

Details DOI

IS Journal 2021 Journal Article

MDA: Multimodal Data Augmentation Framework for Boosting Performance on Sentiment/Emotion Classification Tasks

  • Nan Xu
  • Wenji Mao
  • Penghui Wei
  • Daniel Zeng

Multimodal data analysis has drawn increasing attention with the explosive growth of multimedia data. Although traditional unimodal data analysis tasks have accumulated abundant labeled datasets, there are few labeled multimodal datasets due to the difficulty and complexity of multimodal data annotation, nor is it easy to directly transfer unimodal knowledge to multimodal data. Unfortunately, there is little related data augmentation work in multimodal domain, especially for image–text data. In this article, to address the scarcity problem of labeled multimodal data, we propose a Multimodal Data Augmentation framework for boosting the performance on multimodal image–text classification task. Our framework learns a cross-modality matching network to select image–text pairs from existing unimodal datasets as the multimodal synthetic dataset, and uses this dataset to enhance the performance of classifiers. We take the multimodal sentiment analysis and multimodal emotion analysis as the experimental tasks and the experimental results show the effectiveness of our framework for boosting the performance on multimodal classification task.

Details DOI

IS Journal 2019 Journal Article

Keyword Generation for Sponsored Search Advertising: Balancing Coverage and Relevance

  • Han Nie
  • Yanwu Yang
  • Daniel Zeng

How to automatically generate a pool of keywords used by potential consumers is a challenging issue for advertisers in sponsored search advertising (SSA). Such a keyword pool serves as the base for market research and determines the feasible space of consequent keyword related decisions. This article presents a novel method for keyword generation with Wikipedia as a corpus of the source text (WIKG). Starting with a few seed keywords, the WIKG supports flexible keywords generation by taking advantage of Wikipedia's rich link structure to construct a graph of entry articles in an iterative way. The termination condition is determined by a threshold reflecting the tradeoff between coverage of the generated keyword set and its relevance to seed keywords. Experimental results show that the WIKG outperforms three baselines derived from the extant literature, in terms of both coverage and relevance.

Details DOI

IS Journal 2019 Journal Article

Keyword Optimization in Sponsored Search Advertising: A Multilevel Computational Framework

  • Yanwu Yang
  • Bernard J. Jansen
  • Yinghui Yang
  • Xunhua Guo
  • Daniel Zeng

In sponsored search advertising, keywords serve as an essential bridge linking advertisers, search users, and search engines. Advertisers have to deal with a series of keyword decisions throughout the entire lifecycle of search advertising campaigns. This paper proposes a multilevel and closed-form computational framework for keyword optimization (MKOF) to support various keyword decisions. Based on this framework, we develop corresponding optimization strategies for keyword targeting, keyword assignment, and keyword grouping at different levels (e. g. , market, campaign, and adgroup). With two real-world datasets obtained from past search advertising campaigns, we conduct computational experiments to evaluate our keyword optimization framework and instantiated strategies. Experimental results show that our method can approach the optimal solution in a steady way, and it outperforms two baseline keyword strategies commonly used in practice. The proposed MKOF framework also provides a valid experimental environment to implement and assess various keyword strategies in sponsored search advertising.

Details DOI

AAAI Conference 2018 Short Paper

A Novel Embedding Method for News Diffusion Prediction

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

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

PDF Details

IS Journal 2013 Journal Article

AI's 10 to Watch

  • Daniel Zeng

Every two years, IEEE Intelligent Systems acknowledges and celebrates 10 young stars in the field of AI as "AI's 10 to Watch. " These accomplished researchers--Nora Ayanian, Finale Doshi-Velez, Heng Ji, Brad Knox, Honglak Lee, Nina Narodytska, Ariel Procaccia, Stefanie Tellex, Jun Zhu, and Aviv Zohar--have all completed their doctoral work in the past five years. Despite being relatively junior in their career, each one has made impressive research contributions. Their successes, goals, and ongoing efforts are discussed here.

Details DOI

IS Journal 2013 Journal Article

Big Data Analytics: Perspective Shifting from Transactions to Ecosystems

  • Daniel Zeng
  • Robert Lusch

Understanding the flow and interrelated nature of institutions and business entities' processes and exchanges helps researchers develop and apply big data analytics techniques more effectively from an ecosystem-based perspective (rather than individual transactions and components).

Details DOI

IS Journal 2013 Journal Article

Contributing to IEEE Intelligent Systems

  • Daniel Zeng

What is it, exactly, that technical magazines want? Here, IEEE Intelligent Systems' Editor in Chief discusses common misconceptions and tips for potential contributing authors, to help them publish their work.

Details DOI

IS Journal 2013 Journal Article

Editorial Reflections and Planning for the Future

  • Daniel Zeng

The newest editor in chief begins his tenure with IEEE Intelligent Systems by laying out a roadmap for the magazine going forward. Plans for IS's future include connecting with mainstream artificial intelligence communities, incorporating more from AI industry professionals, and increasing the magazine's presence on social media. The Web extra thanks IS's many reviewers for all their hard work in 2012.

Details DOI

IS Journal 2013 Journal Article

Social Computing: An AI Perspective

  • Daniel Zeng

How has social computing diversified the AI community? What influence will AI have over social computing's development? And how will social intelligence emerge?

Details DOI

IS Journal 2012 Journal Article

Opening Doors to Sharing Social Media Data

  • Fred Morstatter
  • Huan Liu
  • Daniel Zeng

Research data sharing becomes increasingly difficult in the context of social media. Increasing restrictions from social media sites are creating an environment where data cannot be freely shared and as a result scientific claims cannot be verified. In this work, we present a novel approach to data sharing that does not require explicitly publishing a dataset. We create a framework where researchers systematically share the parameters they used to crawl the dataset along with the code used to collect the data, allowing the reader to re-assemble the dataset at a later time. While this approach is by no means a silver bullet, we seek to start a conversation for researchers to implement approaches to data sharing that can be embraced by the research community.

Details DOI

IS Journal 2010 Journal Article

Social Media Analytics and Intelligence

  • Daniel Zeng
  • Hsinchun Chen
  • Robert Lusch
  • Shu-Hsing Li

In a broad sense, social media refers to a conversational, distributed mode of content generation, dissemination, and communication among communities. Different from broadcast-based traditional and industrial media, social media has torn down the boundaries between authorship and readership, while the information consumption and dissemination process is becoming intrinsically intertwined with the process of generating and sharing information. This special issue samples the state of the art in social media analytics and intelligence research that has direct relevance to the AI subfield from either an methodological or domain perspective.

Details DOI

IS Journal 2009 Journal Article

AI for Global Disease Surveillance

  • Hsinchun Chen
  • Daniel Zeng
  • David L. Buckeridge
  • Masoumeh Izadi Izadi
  • Aman Verma
  • Anya Okhmatovskaia
  • Xiaohua Hu
  • Xiajiong Shen

In this time of increasing concern over the deadly and costly threats of infectious diseases, preparation for, early detection of, and timely response to emerging infectious diseases and epidemic outbreaks are key public-health priorities and are driving an emerging field of multidisciplinary research. The four essays in this installment of Trends & Controversies discuss uses of AI in global disease surveillance.

Details DOI

IS Journal 2008 Journal Article

Intelligent-Commerce Research in China

  • Daniel Zeng
  • Fei-Yue Wang
  • Xiaolong Zheng
  • Yong Yuan
  • Guoqing Chen
  • Jian Chen

Recent years have witnessed the increased application of AI technologies to real-world e-commerce challenges. This article presents a brief overview of representative work by Chinese researchers, covering topics such as multiagent decision making, keyword advertising, social networks, recommender systems, information retrieval and the semantic Web, and computational experiments. This article is part of a special issue on AI in China.

Details DOI

IS Journal 2007 Journal Article

A Comparison of Collaborative-Filtering Recommendation Algorithms for E-commerce

  • Zan Huang
  • Daniel Zeng
  • Hsinchun Chen

Collaborative filtering is one of the most widely adopted and successful recommendation approaches. Unlike approaches based on intrinsic consumer and product characteristics, CF characterizes consumers and products implicitly by their previous interactions. The simplest example is to recommend the most popular products to all consumers. Researchers are advancing CF technologies in such areas as algorithm design, human- computer interaction design, consumer incentive analysis, and privacy protection.

Details DOI

IS Journal 2007 Journal Article

Guest Editors' Introduction: Social Computing

  • Daniel Zeng
  • Fei-Yue Wang
  • Kathleen M. Carley

Broadly stated, social computing takes a computational approach to the study and modeling of social interactions and communications. It also encompasses the development of technologies supporting these interactions. In recent years, we've seen social computing impact numerous information and communications technology (ICT) fields. It's attracted significant interest from not only researchers in the computing and social sciences but also software and online game vendors, Web entrepreneurs, political analysts, and digital-government practitioners, among others. This special issue samples the state of the art social-computing research from several perspectives: the overall paradigm of social-computing research; technological support for social-computing applications; cognitive modeling and architecture of agents and agent societies; and social-computing applications in areas such as terrorist network analysis, competitive business strategies, and agent behavior in financial markets. This article is part of a special issue on social computing.

Details DOI

IS Journal 2007 Journal Article

Protecting Transportation Infrastructure

  • Daniel Zeng
  • Sudarshan S. Chawathe
  • Hua Huang
  • Fei-Yue Wang

Transportation infrastructures are a key component of a nation's critical infrastructures, covering physical assets such as airports, ports, and railway and mass transit networks as well as software systems such as traffic control systems. Because physical transportation networks attract large numbers of people, they're also high-value targets for terrorists intending to inflict heavy casualties. Protecting transportation infrastructure provides a potentially fruitful application domain for many subdisciplines of AI and closely related fields. The authors review research challenges in this domain.

Details DOI

IS Journal 2007 Journal Article

Social Computing: From Social Informatics to Social Intelligence

  • Fei-Yue Wang
  • Kathleen M. Carley
  • Daniel Zeng
  • Wenji Mao

Social computing represents a new computing paradigm and an interdisciplinary research and application field. Undoubtedly, it strongly influences system and software developments in the years to come. We expect that social computing's scope continues to expand and its applications multiply. From both theoretical and technological perspectives, social computing technologies moves beyond social information processing towards emphasizing social intelligence. As we've discussed, the move from social informatics to social intelligence is achieved by modeling and analyzing social behavior, by capturing human social dynamics, and by creating artificial social agents and generating and managing actionable social knowledge

Details DOI

IS Journal 2006 Journal Article

AI Research in China: 50 Years down the Road

  • Ruqian Lu
  • Daniel Zeng
  • Fei-Yue Wang

Year 2006 marks the 50th anniversary of the birth of modern artificial intelligence research. Chinese researchers have been conducting AI research for decades. Here, the authors sample some of the most promising areas Chinese AI researchers are studying and discuss related future activities. This article is part of a special issue on the Future of AI.

Details DOI

IS Journal 2005 Journal Article

Rule + Exception Strategies for Security Information Analysis

  • Yiyu Yao
  • Fei-Yue Wang
  • Jue Wang
  • Daniel Zeng

Broadly defined, intelligence and security informatics is "the study of the use and development of advanced information technologies, systems, algorithms, and databases for national- and homeland-security-related applications". Processing security-related information is a critical component of ISI research, which involves studying a wide range of technical and systems challenges related to the acquisition, collection, storage, retrieval, synthesis, analysis, visualization, presentation, and understanding of security-related information. Our research aims to develop a unified data description and understanding framework to enable discovery of useful knowledge and events from data sets related to international, homeland, or other types of security. In particular, this article focuses on a common security information analysis task: how to develop an efficient knowledge representation framework and related automated learning and mining mechanisms to describe and identify abnormal situations or behavior. We advocate the use of a specific knowledge representation and data mining framework based on rules and exceptions for analysis of security-related information. In this rule+exception framework, normal and abnormal situations or behaviors occur as pairs of dual entities: rules succinctly summarize normal situations, and exceptions characterize abnormal situations. The rule+exception approach -which closely resembles how humans understand, organize, and use knowledge -has the potential to evolve into a unified, multilevel data description and understanding framework applicable across many security informatics applications.

Details DOI