Suhang Wang

TMLR Journal 2026 Journal Article

DiffKGW: Stealthy and Robust Diffusion Model Watermarking

• Tianxin Wei
• Ruizhong Qiu
• Yifan Chen
• Yunzhe Qi
• Jiacheng Lin
• Wenxuan Bao
• Wenju Xu
• Sreyashi Nag

Diffusion models are known for their supreme capability to generate realistic images. However, ethical concerns, such as copyright protection and the generation of inappropriate content, pose significant challenges for the practical deployment of diffusion models. Recent work has proposed a flurry of watermarking techniques that inject artificial patterns into initial latent representations of diffusion models, offering a promising solution to these issues. However, enforcing a specific pattern on selected elements can disrupt the Gaussian distribution of the initial latent representation. Inspired by watermarks for large language models (LLMs), we generalize the LLM KGW watermark to image diffusion models and propose a stealthy probability adjustment approach DiffKGW that preserves the Gaussian distribution of initial latent representation. In addition, we dissect the design principles of state-of-the-art watermarking techniques and introduce a unified framework. We identify a set of dimensions that explain the manipulation enforced by watermarking methods, including the distribution of individual elements, the specification of watermark shapes within each channel, and the choice of channels for watermark embedding. Through the empirical studies on regular text-to-image applications and the first systematic attempt at watermarking image-to-image diffusion models, we thoroughly verify the effectiveness of our proposed framework through comprehensive evaluations. On all the diffusion models, including Stable Diffusion, our approach induced from the proposed framework not only preserves image quality but also outperforms existing methods in robustness against a wide range of attacks.

AAAI Conference 2026 Conference Paper

SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis

• Haitong Luo
• Weiyao Zhang
• Suhang Wang
• Wenji Zou
• Chungang Lin
• Xuying Meng
• Yujun Zhang

The proliferation of high-quality text from Large Language Models (LLMs) demands reliable and efficient detection methods. While existing training-free approaches show promise, they often rely on surface-level statistics and overlook fundamental signal properties of the text generation process. In this work, we reframe detection as a signal processing problem, introducing a novel paradigm that analyzes the sequence of token log-probabilities in the frequency domain. By systematically analyzing the signal's spectral properties using the global Discrete Fourier Transform (DFT) and the local Short-Time Fourier Transform (STFT), we find that human-written text consistently exhibits significantly higher spectral energy. This higher energy reflects the larger-amplitude fluctuations inherent in human writing compared to the suppressed dynamics of LLM-generated text. Based on this key insight, we construct SpecDetect, a detector built on a single, robust feature from the global DFT: DFT total energy. We also propose an enhanced version, SpecDetect++, which incorporates a sampling discrepancy mechanism to further boost robustness. Extensive experiments show that our approach outperforms the state-of-the-art model while running in nearly half the time. Our work introduces a new, efficient, and interpretable pathway for LLM-generated text detection, showing that classical signal processing techniques offer a surprisingly powerful solution to this modern challenge.

TIST Journal 2025 Journal Article

A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

• Fali Wang
• Zhiwei Zhang
• Xianren Zhang
• Zongyu Wu
• TzuHao Mo
• Qiuhao Lu
• Wanjing Wang
• Rui Li

Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use, which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessitating specialized models. Therefore, Small Language Models (SLMs) are increasingly favored for their low inference latency, cost-effectiveness, efficient development, and easy customization and adaptability. These models are particularly well-suited for resource-limited environments and domain knowledge acquisition, addressing LLMs’ challenges and proving ideal for applications that require localized data handling for privacy, minimal inference latency for efficiency, and domain knowledge acquisition through lightweight fine-tuning. The rising demand for SLMs has spurred extensive research and development. However, a comprehensive survey investigating issues related to the definition, acquisition, application, enhancement, and reliability of SLM remains lacking, prompting us to conduct a detailed survey on these topics. The definition of SLMs varies widely; thus, to standardize, we propose defining SLMs by their capability to perform specialized tasks and suitability for resource-constrained settings, setting boundaries based on the minimal size for emergent abilities and the maximum size sustainable under resource constraints. For other aspects, we provide a taxonomy of relevant models/methods and develop general frameworks for each category to enhance and utilize SLMs effectively. We have compiled the collected SLM models and related methods on GitHub: https://github.com/FairyFali/SLMs-Survey.

NeurIPS Conference 2025 Conference Paper

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

• Fali Wang
• Hui Liu
• Zhenwei Dai
• Jingying Zeng
• Zhiwei Zhang
• Zongyu Wu
• Chen Luo
• Zhen Li

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world problems are multi-stage complex tasks, composed of a sequence of heterogeneous subtasks with each subtask requires LLM of specific capability. Therefore, we study a novel problem: the test-time compute-optimal scaling in multi-stage complex tasks, aiming to select suitable models and allocate budgets per subtask to maximize overall performance. TTS in multi-stage tasks introduces two fundamental challenges: (i) The combinatorial search space of model and budget allocations, combined with the high cost of inference, makes brute-force search impractical. (ii) The optimal model and budget allocations across subtasks are interdependent, increasing the complexity of the compute-optimal search. To address this gap, we conduct extensive pilot experiments on four tasks across six datasets, deriving three empirical insights characterizing the behavior of LLMs in multi-stage complex tasks. Informed by these insights, we propose AgentTTS, an LLM-agent-based framework that autonomously searches for compute-optimal allocations through iterative feedback-driven interactions with the execution environment. Experimental results demonstrate that AgentTTS significantly outperforms traditional and other LLM-based baselines in search efficiency, and shows improved robustness to varying training set sizes and enhanced interpretability.

ICLR Conference 2025 Conference Paper

Catastrophic Failure of LLM Unlearning via Quantization

• Zhiwei Zhang 0028
• Fali Wang
• Xiaomin Li
• Zongyu Wu 0001
• Xianfeng Tang
• Hui Liu 0031
• Qi He 0002
• Wenpeng Yin 0001

Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their training data, which can include copyrighted and private content. Machine unlearning has been introduced as a viable solution to remove the influence of such problematic content without the need for costly and time-consuming retraining. This process aims to erase specific knowledge from LLMs while preserving as much model utility as possible. Despite the effectiveness of current unlearning methods, little attention has been given to whether existing unlearning methods for LLMs truly achieve forgetting or merely hide the knowledge, which current unlearning benchmarks fail to detect. This paper reveals that applying quantization to models that have undergone unlearning can restore the "forgotten" information. We conduct comprehensive experiments using various quantization techniques across multiple precision levels to thoroughly evaluate this phenomenon. We find that for unlearning methods with utility constraints, the unlearned model retains an average of 21\% of the intended forgotten knowledge in full precision, which significantly increases to 83\% after 4-bit quantization. Based on our empirical findings, we provide a theoretical explanation for the observed phenomenon and propose a quantization-robust unlearning strategy aimed at mitigating this intricate issue. Our results highlight a fundamental tension between preserving the utility of the unlearned model and preventing knowledge recovery through quantization, emphasizing the challenge of balancing these two objectives. Altogether, our study underscores a major failure in existing unlearning methods for LLMs, strongly advocating for more comprehensive and robust strategies to ensure authentic unlearning without compromising model utility. Our code is available at: https://github.com/zzwjames/FailureLLMUnlearning.

NeurIPS Conference 2025 Conference Paper

Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking

• Liangliang Zhang
• Zhuorui Jiang
• Hongliang Chi
• Haoyang Chen
• Mohammed ElKoumy
• Fali Wang
• Qiong Wu
• Zhengyi Zhou

Knowledge Graph Question Answering (KGQA) systems rely on high-quality benchmarks to evaluate complex multi-hop reasoning. However, despite their widespread use, popular datasets such as WebQSP and CWQ suffer from critical quality issues, including inaccurate or incomplete ground-truth annotations, poorly constructed questions that are ambiguous, trivial, or unanswerable, and outdated or inconsistent knowledge. Through a manual audit of 16 popular KGQA datasets—including WebQSP and CWQ—we find that the average factual correctness rate is only 57%. To address these issues, we introduce KGQAGen, an LLM-in-the-loop framework that systematically resolves these pitfalls. KGQAGen combines structured knowledge grounding, LLM-guided generation, and symbolic verification to produce challenging and verifiable QA instances. Using KGQAGen, we construct KGQAGen-10k, a 10K-scale benchmark grounded in Wikidata, and evaluate a diverse set of KG-RAG models. Experimental results demonstrate that even state-of-the-art systems struggle on this benchmark, highlighting its ability to expose limitations of existing models. Our findings advocate for more rigorous benchmark construction and position KGQAGen as a scalable framework for advancing KGQA evaluation.

NeurIPS Conference 2025 Conference Paper

DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

• Junjie Xu
• Jiahao Zhang
• Mangal Prakash
• Xiang Zhang
• Suhang Wang

Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and proteins. These systems require models that can simultaneously capture fine-grained atomic interactions, long-range dependencies across spatially distant components, and biologically relevant hierarchical structure—such as atoms forming residues, which in turn form higher-order domains. Existing geometric GNNs, which typically operate exclusively in either Euclidean or Spherical Harmonics space, are limited in their ability to capture both the fine-scale atomic details and the long-range, symmetry-aware dependencies required for modeling the multi-scale structure of large biomolecules. We introduce DualEquiNet, a Dual-Space Hierarchical Equivariant Network that constructs complementary representations in both Euclidean and Spherical Harmonics spaces to capture local geometry and global symmetry-aware features. DualEquiNet employs bidirectional cross-space message passing and a novel Cross-Space Interaction Pooling mechanism to hierarchically aggregate atomic features into biologically meaningful units, such as residues, enabling efficient and expressive multi-scale modeling for large biomolecular systems. DualEquiNet achieves state-of-the-art performance on multiple existing benchmarks for RNA property prediction and protein modeling, and outperforms prior methods on two newly introduced 3D structural benchmarks demonstrating its broad effectiveness across a range of large biomolecule modeling tasks.

NeurIPS Conference 2025 Conference Paper

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

• Jie Ren
• Zhenwei Dai
• Xianfeng Tang
• Yue Xing
• Shenglai Zeng
• Jingying Zeng
• Qiankun Peng
• Samarth Varshney

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these concerns, unlearning techniques have been developed to remove the influence of specific data without retraining from scratch. However, this paper reveals a critical vulnerability in fine-tuning-based unlearning: a malicious user can craft a manipulated forgetting request that stealthily degrades the model’s utility for benign users. We demonstrate this risk through a red-teaming Stealthy Attack (SA), which is inspired by two key limitations of existing unlearning—the inability to constrain the scope of unlearning effect and the failure to distinguish benign tokens from unlearning signals. Prior work has shown that unlearned models tend to memorize forgetting data as unlearning signals, and respond with hallucinations or feigned ignorance when unlearning signals appear in the input. By subtly increasing the presence of common benign tokens in the forgetting data, SA enhances the connection between benign tokens and unlearning signals. As a result, when normal users include such tokens in their prompts, the model exhibits unlearning behaviors, leading to unintended utility degradation. To address this vulnerability, we propose Scope-aware Unlearning (SU), a lightweight enhancement that introduces a scope term into the unlearning objective, encouraging the model to localize the forgetting effect. Our method requires no additional data processing, integrates seamlessly with existing fine-tuning frameworks, and significantly improves robustness against SA. Extensive experiments validate the effectiveness of both SA and SU.

ICLR Conference 2025 Conference Paper

Robustness Inspired Graph Backdoor Defense

• Zhiwei Zhang 0028
• Minhua Lin
• Junjie Xu
• Zongyu Wu 0001
• Enyan Dai
• Suhang Wang

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their real-world adoption. Despite initial efforts to defend against specific graph backdoor attacks, there is no work on defending against various types of backdoor attacks where generated triggers have different properties. Hence, we first empirically verify that prediction variance under edge dropping is a crucial indicator for identifying poisoned nodes. With this observation, we propose using random edge dropping to detect backdoors and theoretically show that it can efficiently distinguish poisoned nodes from clean ones. Furthermore, we introduce a novel robust training strategy to efficiently counteract the impact of the triggers. Extensive experiments on real-world datasets show that our framework can effectively identify poisoned nodes, significantly degrade the attack success rate, and maintain clean accuracy when defending against various types of graph backdoor attacks with different properties. Our code is available at: https://github.com/zzwjames/RIGBD.

ICML Conference 2024 Conference Paper

Efficient Contrastive Learning for Fast and Accurate Inference on Graphs

• Teng Xiao
• Huaisheng Zhu
• Zhiwei Zhang 0028
• Zhimeng Guo
• Charu C. Aggarwal
• Suhang Wang
• Vasant G. Honavar

Graph contrastive learning has made remarkable advances in settings where there is a scarcity of task-specific labels. Despite these advances, the significant computational overhead for representation inference incurred by existing methods that rely on intensive message passing makes them unsuitable for latency-constrained applications. In this paper, we present GraphECL, a simple and efficient contrastive learning method for fast inference on graphs. GraphECL does away with the need for expensive message passing during inference. Specifically, it introduces a novel coupling of the MLP and GNN models, where the former learns to computationally efficiently mimic the computations performed by the latter. We provide a theoretical analysis showing why MLP can capture essential structural information in neighbors well enough to match the performance of GNN in downstream tasks. The extensive experiments on widely used real-world benchmarks that show that GraphECL achieves superior performance and inference efficiency compared to state-of-the-art graph constrastive learning (GCL) methods on homophilous and heterophilous graphs.

ICML Conference 2024 Conference Paper

Language Models as Semantic Indexers

• Bowen Jin
• Hansi Zeng
• Guoyin Wang 0001
• Xiusi Chen
• Tianxin Wei
• Ruirui Li 0002
• Zhengyang Wang
• Zheng Li 0018

Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic indexing. It is non-trivial to design a method that can learn the document’s semantic representations and its hierarchical structure simultaneously, given that semantic IDs are discrete and sequentially structured, and the semantic supervision is deficient. In this paper, we introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We tackle the challenge of sequential discrete ID by introducing a semantic indexer capable of generating neural sequential discrete representations with progressive training and contrastive learning. In response to the semantic supervision deficiency, we propose to train the model with a self-supervised document reconstruction objective. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval on five datasets from various domains. Code is available at https: //github. com/PeterGriffinJin/LMIndexer.

AAAI Conference 2024 Conference Paper

Spectral-Based Graph Neural Networks for Complementary Item Recommendation

• Haitong Luo
• Xuying Meng
• Suhang Wang
• Hanyun Cao
• Weiyao Zhang
• Yequan Wang
• Yujun Zhang

Modeling complementary relationships greatly helps recommender systems to accurately and promptly recommend the subsequent items when one item is purchased. Unlike traditional similar relationships, items with complementary relationships may be purchased successively (such as iPhone and Airpods Pro), and they not only share relevance but also exhibit dissimilarity. Since the two attributes are opposites, modeling complementary relationships is challenging. Previous attempts to exploit these relationships have either ignored or oversimplified the dissimilarity attribute, resulting in ineffective modeling and an inability to balance the two attributes. Since Graph Neural Networks (GNNs) can capture the relevance and dissimilarity between nodes in the spectral domain, we can leverage spectral-based GNNs to effectively understand and model complementary relationships. In this study, we present a novel approach called Spectral-based Complementary Graph Neural Networks (SComGNN) that utilizes the spectral properties of complementary item graphs. We make the first observation that complementary relationships consist of low-frequency and mid-frequency components, corresponding to the relevance and dissimilarity attributes, respectively. Based on this spectral observation, we design spectral graph convolutional networks with low-pass and mid-pass filters to capture the low-frequency and mid-frequency components. Additionally, we propose a two-stage attention mechanism to adaptively integrate and balance the two attributes. Experimental results on four e-commerce datasets demonstrate the effectiveness of our model, with SComGNN significantly outperforming existing baseline models.

ICLR Conference 2024 Conference Paper

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

• Tianxin Wei
• Bowen Jin
• Ruirui Li 0002
• Hansi Zeng
• Zhengyang Wang
• Jianhui Sun
• Qingyu Yin
• Hanqing Lu

Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Our daily choices, especially in domains like fashion and retail, are substantially shaped by multi-modal data, such as pictures and textual descriptions. These modalities not only offer intuitive guidance but also cater to personalized user preferences. However, the predominant personalization approaches mainly focus on ID or text-based recommendation problems, failing to comprehend the information spanning various tasks or modalities. In this paper, our goal is to establish a Unified paradigm for Multi-modal Personalization systems (UniMP), which effectively leverages multi-modal data while eliminating the complexities associated with task- and modality-specific customization. We argue that the advancements in foundational generative modeling have provided the flexibility and effectiveness necessary to achieve the objective. In light of this, we develop a generic and extensible personalization generative framework, that can handle a wide range of personalized needs including item recommendation, product search, preference prediction, explanation generation, and further user-guided image generation. Our methodology enhances the capabilities of foundational language models for personalized tasks by seamlessly ingesting interleaved cross-modal user history information, ensuring a more precise and customized experience for users. To train and evaluate the proposed multi-modal personalized tasks, we also introduce a novel and comprehensive benchmark covering a variety of user requirements. Our experiments on the real-world benchmark showcase the model's potential, outperforming competitive methods specialized for each task.

NeurIPS Conference 2023 Conference Paper

Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation

• Wei Jin
• Haitao Mao
• Zheng Li
• Haoming Jiang
• Chen Luo
• Hongzhi Wen
• Haoyu Han
• Hanqing Lu

Modeling customer shopping intentions is a crucial task for e-commerce, as it directly impacts user experience and engagement. Thus, accurately understanding customer preferences is essential for providing personalized recommendations. Session-based recommendation, which utilizes customer session data to predict their next interaction, has become increasingly popular. However, existing session datasets have limitations in terms of item attributes, user diversity, and dataset scale. As a result, they cannot comprehensively capture the spectrum of user behaviors and preferences. To bridge this gap, we present the Amazon Multilingual Multi-locale Shopping Session Dataset, namely Amazon-M2. It is the first multilingual dataset consisting of millions of user sessions from six different locales, where the major languages of products are English, German, Japanese, French, Italian, and Spanish. Remarkably, the dataset can help us enhance personalization and understanding of user preferences, which can benefit various existing tasks as well as enable new tasks. To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation. With the above tasks, we benchmark a range of algorithms on our proposed dataset, drawing new insights for further research and practice. In addition, based on the proposed dataset and tasks, we hosted a competition in the KDD CUP 2023 https: //www. aicrowd. com/challenges/amazon-kdd-cup-23-multilingual-recommendation-challenge and have attracted thousands of users and submissions. The winning solutions and the associated workshop can be accessed at our website~https: //kddcup23. github. io/.

NeurIPS Conference 2023 Conference Paper

Certifiably Robust Graph Contrastive Learning

• Minhua Lin
• Teng Xiao
• Enyan Dai
• Xiang Zhang
• Suhang Wang

Graph Contrastive Learning (GCL) has emerged as a popular unsupervised graph representation learning method. However, it has been shown that GCL is vulnerable to adversarial attacks on both the graph structure and node attributes. Although empirical approaches have been proposed to enhance the robustness of GCL, the certifiable robustness of GCL is still remain unexplored. In this paper, we develop the first certifiably robust framework in GCL. Specifically, we first propose a unified criteria to evaluate and certify the robustness of GCL. We then introduce a novel technique, RES (Randomized Edgedrop Smoothing), to ensure certifiable robustness for any GCL model, and this certified robustness can be provably preserved in downstream tasks. Furthermore, an effective training method is proposed for robust GCL. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model. The source code of RES is available at https: //github. com/ventr1c/RES-GCL.

TIST Journal 2023 Journal Article

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

• Tianxiang Zhao
• Dongsheng Luo
• Xiang Zhang
• Suhang Wang

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, such as nodes or edges, that the target GNN relies upon for making predictions. Though various algorithms are proposed, most of them formalize this task by searching the minimal subgraph, which can preserve original predictions. However, an inductive bias is deep-rooted in this framework: Several subgraphs can result in the same or similar outputs as the original graphs. Consequently, they have the danger of providing spurious explanations and failing to provide consistent explanations. Applying them to explain weakly performed GNNs would further amplify these issues. To address this problem, we theoretically examine the predictions of GNNs from the causality perspective. Two typical reasons for spurious explanations are identified: confounding effect of latent variables like distribution shift and causal factors distinct from the original input. Observing that both confounding effects and diverse causal rationales are encoded in internal representations, we propose a new explanation framework with an auxiliary alignment loss, which is theoretically proven to be optimizing a more faithful explanation objective intrinsically. Concretely for this alignment loss, a set of different perspectives are explored: anchor-based alignment, distributional alignment based on Gaussian mixture models, mutual-information-based alignment, and so on. A comprehensive study is conducted both on the effectiveness of this new framework in terms of explanation faithfulness/consistency and on the advantages of these variants. For our codes, please refer to the following URL link: https://github.com/TianxiangZhao/GraphNNExplanation

NeurIPS Conference 2023 Conference Paper

Simple and Asymmetric Graph Contrastive Learning without Augmentations

• Teng Xiao
• Huaisheng Zhu
• Zhengyu Chen
• Suhang Wang

Graph Contrastive Learning (GCL) has shown superior performance in representation learning in graph-structured data. Despite their success, most existing GCL methods rely on prefabricated graph augmentation and homophily assumptions. Thus, they fail to generalize well to heterophilic graphs where connected nodes may have different class labels and dissimilar features. In this paper, we study the problem of conducting contrastive learning on homophilic and heterophilic graphs. We find that we can achieve promising performance simply by considering an asymmetric view of the neighboring nodes. The resulting simple algorithm, Asymmetric Contrastive Learning for Graphs (GraphACL), is easy to implement and does not rely on graph augmentations and homophily assumptions. We provide theoretical and empirical evidence that GraphACL can capture one-hop local neighborhood information and two-hop monophily similarity, which are both important for modeling heterophilic graphs. Experimental results show that the simple GraphACL significantly outperforms state-of-the-art graph contrastive learning and self-supervised learning methods on homophilic and heterophilic graphs. The code of GraphACL is available at https: //github. com/tengxiao1/GraphACL.

NeurIPS Conference 2022 Conference Paper

Decoupled Self-supervised Learning for Graphs

• Teng Xiao
• Zhengyu Chen
• Zhimeng Guo
• Zeyang Zhuang
• Suhang Wang

This paper studies the problem of conducting self-supervised learning for node representation learning on graphs. Most existing self-supervised learning methods assume the graph is homophilous, where linked nodes often belong to the same class or have similar features. However, such assumptions of homophily do not always hold in real-world graphs. We address this problem by developing a decoupled self-supervised learning (DSSL) framework for graph neural networks. DSSL imitates a generative process of nodes and links from latent variable modeling of the semantic structure, which decouples different underlying semantics between different neighborhoods into the self-supervised learning process. Our DSSL framework is agnostic to the encoders and does not need prefabricated augmentations, thus is flexible to different graphs. To effectively optimize the framework, we derive the evidence lower bound of the self-supervised objective and develop a scalable training algorithm with variational inference. We provide a theoretical analysis to justify that DSSL enjoys the better downstream performance. Extensive experiments on various types of graph benchmarks demonstrate that our proposed framework can achieve better performance compared with competitive baselines.

AAAI Conference 2022 Conference Paper

Towards Off-Policy Learning for Ranking Policies with Logged Feedback

• Teng Xiao
• Suhang Wang

Probabilistic learning to rank (LTR) has been the dominating approach for optimizing the ranking metric, but cannot maximize long-term rewards. Reinforcement learning models have been proposed to maximize user long-term rewards by formulating the recommendation as a sequential decision-making problem, but could only achieve inferior accuracy compared to LTR counterparts, primarily due to the lack of online interactions and the characteristics of ranking. In this paper, we propose a new off-policy value ranking (VR) algorithm that can simultaneously maximize user long-term rewards and optimize the ranking metric offline for improved sample efficiency in a unified Expectation-Maximization (EM) framework. We theoretically and empirically show that the EM process guides the leaned policy to enjoy the benefit of integration of the future reward and ranking metric, and learn without any online interactions. Extensive offline and online experiments demonstrate the effectiveness of our methods.

AAAI Conference 2021 Conference Paper

Neural Utility Functions

• Porter Jenkins
• Ahmad Farag
• J. Stockton Jenkins
• Huaxiu Yao
• Suhang Wang
• Zhenhui Li

Current neural network architectures have no mechanism for explicitly reasoning about item trade-offs. Such trade-offs are important for popular tasks such as recommendation. The main idea of this work is to give neural networks inductive biases that are inspired by economic theories. To this end, we propose Neural Utility Functions, which directly optimize the gradients of a neural network so that they are more consistent with utility theory, a mathematical framework for modeling choice among items. We demonstrate that Neural Utility Functions can recover theoretical item relationships better than vanilla neural networks, analytically show existing neural networks are not quasi-concave and do not inherently reason about trade-offs, and that augmenting existing models with a utility loss function improves recommendation results. The Neural Utility Functions we propose are theoretically motivated, and yield strong empirical results.

AAAI Conference 2020 Conference Paper

Graph Few-Shot Learning via Knowledge Transfer

• Huaxiu Yao
• Chuxu Zhang
• Ying Wei
• Meng Jiang
• Suhang Wang
• Junzhou Huang
• Nitesh Chawla
• Zhenhui Li

Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model and the contribution of each component.

AAAI Conference 2020 Conference Paper

Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

• Xianfeng Tang
• Huaxiu Yao
• Yiwei Sun
• Charu Aggarwal
• Prasenjit Mitra
• Suhang Wang

Multivariate time series (MTS) forecasting is widely used in various domains, such as meteorology and traffic. Due to limitations on data collection, transmission, and storage, realworld MTS data usually contains missing values, making it infeasible to apply existing MTS forecasting models such as linear regression and recurrent neural networks. Though many efforts have been devoted to this problem, most of them solely rely on local dependencies for imputing missing values, which ignores global temporal dynamics. Local dependencies/patterns would become less useful when the missing ratio is high, or the data have consecutive missing values; while exploring global patterns can alleviate such problem. Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values. However, work in this direction is rather limited. Therefore, we study a novel problem of MTS forecasting with missing values by jointly exploring local and global temporal dynamics. We propose a new framework LGnet, which leverages memory network to explore global patterns given estimations from local perspectives. We further introduce adversarial training to enhance the modeling of global temporal distribution. Experimental results on real-world datasets show the effectiveness of LGnet for MTS forecasting with missing values and its robustness under various missing ratios.

IJCAI Conference 2019 Conference Paper

MEGAN: A Generative Adversarial Network for Multi-View Network Embedding

• Yiwei Sun
• Suhang Wang
• Tsung-Yu Hsieh
• Xianfeng Tang
• Vasant Honavar

Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e. g. , friendship, shared interests in music, etc. ) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i. e. , the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.

AAAI Conference 2019 Conference Paper

Unsupervised Fake News Detection on Social Media: A Generative Approach

• Shuo Yang
• Kai Shu
• Suhang Wang
• Renjie Gu
• Fan Wu
• Huan Liu

Social media has become one of the main channels for people to access and consume news, due to the rapidness and low cost of news dissemination on it. However, such properties of social media also make it a hotbed of fake news dissemination, bringing negative impacts on both individuals and society. Therefore, detecting fake news has become a crucial problem attracting tremendous research effort. Most existing methods of fake news detection are supervised, which require an extensive amount of time and labor to build a reliably annotated dataset. In search of an alternative, in this paper, we investigate if we could detect fake news in an unsupervised manner. We treat truths of news and users’ credibility as latent random variables, and exploit users’ engagements on social media to identify their opinions towards the authenticity of news. We leverage a Bayesian network model to capture the conditional dependencies among the truths of news, the users’ opinions, and the users’ credibility. To solve the inference problem, we propose an efficient collapsed Gibbs sampling approach to infer the truths of news and the users’ credibility without any labelled data. Experiment results on two datasets show that the proposed method significantly outperforms the compared unsupervised methods.

AAAI Conference 2018 Conference Paper

Exploiting Emotion on Reviews for Recommender Systems

• Xuying Meng
• Suhang Wang
• Huan Liu
• Yujun Zhang

Review history is widely used by recommender systems to infer users’ preferences and help find the potential interests from the huge volumes of data, whereas it also brings in great concerns on the sparsity and cold-start problems due to its inadequacy. Psychology and sociology research has shown that emotion information is a strong indicator for users’ preferences. Meanwhile, with the fast development of online services, users are willing to express their emotion on others’ reviews, which makes the emotion information pervasively available. Besides, recent research shows that the number of emotion on reviews is always much larger than the number of reviews. Therefore incorporating emotion on reviews may help to alleviate the data sparsity and cold-start problems for recommender systems. In this paper, we provide a principled and mathematical way to exploit both positive and negative emotion on reviews, and propose a novel framework MIR- ROR, exploiting eMotIon on Reviews for RecOmmendeR systems from both global and local perspectives. Empirical results on real-world datasets demonstrate the effectiveness of our proposed framework and further experiments are conducted to understand how emotion on reviews works for the proposed framework.

AAAI Conference 2018 Conference Paper

Personalized Privacy-Preserving Social Recommendation

• Xuying Meng
• Suhang Wang
• Kai Shu
• Jundong Li
• Bo Chen
• Huan Liu
• Yujun Zhang

Privacy leakage is an important issue for social recommendation. Existing privacy preserving social recommendation approaches usually allow the recommender to fully control users’ information. This may be problematic since the recommender itself may be untrusted, leading to serious privacy leakage. Besides, building social relationships requires sharing interests as well as other private information, which may lead to more privacy leakage. Although sometimes users are allowed to hide their sensitive private data using privacy settings, the data being shared can still be abused by the adversaries to infer sensitive private information. Supporting social recommendation with least privacy leakage to untrusted recommender and other users (i. e. , friends) is an important yet challenging problem. In this paper, we aim to address the problem of achieving privacy-preserving social recommendation under personalized privacy settings. We propose PrivSR, a novel framework for privacy-preserving social recommendation, in which users can model ratings and social relationships privately. Meanwhile, by allocating different noise magnitudes to personalized sensitive and non-sensitive ratings, we can protect users’ privacy against the untrusted recommender and friends. Theoretical analysis and experimental evaluation on real-world datasets demonstrate that our framework can protect users’ privacy while being able to retain effectiveness of the underlying recommender system.

TIST Journal 2018 Journal Article

Random-Forest-Inspired Neural Networks

• Suhang Wang
• Charu Aggarwal
• Huan Liu

Neural networks have become very popular in recent years, because of the astonishing success of deep learning in various domains such as image and speech recognition. In many of these domains, specific architectures of neural networks, such as convolutional networks, seem to fit the particular structure of the problem domain very well and can therefore perform in an astonishingly effective way. However, the success of neural networks is not universal across all domains. Indeed, for learning problems without any special structure, or in cases where the data are somewhat limited, neural networks are known not to perform well with respect to traditional machine-learning methods such as random forests. In this article, we show that a carefully designed neural network with random forest structure can have better generalization ability. In fact, this architecture is more powerful than random forests, because the back-propagation algorithm reduces to a more powerful and generalized way of constructing a decision tree. Furthermore, the approach is efficient to train and requires a small constant factor of the number of training examples. This efficiency allows the training of multiple neural networks to improve the generalization accuracy. Experimental results on real-world benchmark datasets demonstrate the effectiveness of the proposed enhancements for classification and regression.

TIST Journal 2018 Journal Article

Understanding and Identifying Rhetorical Questions in Social Media

• Suhas Ranganath
• Xia Hu
• Jiliang Tang
• Suhang Wang
• Huan Liu

Social media provides a platform for seeking information from a large user base. Information seeking in social media, however, occurs simultaneously with users expressing their viewpoints by making statements. Rhetorical questions have the form of a question but serve the function of a statement and are an important tool employed by users to express their viewpoints. Therefore, rhetorical questions might mislead platforms assisting information seeking in social media. It becomes difficult to identify rhetorical questions as they are not syntactically different from other questions. In this article, we develop a framework to identify rhetorical questions by modeling some motivations of the users to post them. We focus on two motivations of the users drawing from linguistic theories to implicitly convey a message and to modify the strength of a statement previously made. We develop a quantitative framework from these motivations to identify rhetorical questions in social media. We evaluate the framework using two datasets of questions posted on a social media platform Twitter and demonstrate its effectiveness in identifying rhetorical questions. This is the first framework, to the best of our knowledge, to model the possible motivations for posting rhetorical questions to identify them on social media platforms.

AAAI Conference 2017 Conference Paper

CLARE: A Joint Approach to Label Classification and Tag Recommendation

• Yilin Wang
• Suhang Wang
• Jiliang Tang
• Guojun Qi
• Huan Liu
• Baoxin Li

Data classification and tag recommendation are both important and challenging tasks in social media. These two tasks are often considered independently and most efforts have been made to tackle them separately. However, labels in data classification and tags in tag recommendation are inherently related. For example, a Youtube video annotated with NCAA, stadium, pac12 is likely to be labeled as football, while a video/image with the class label of coast is likely to be tagged with beach, sea, water and sand. The existence of relations between labels and tags motivates us to jointly perform classification and tag recommendation for social media data in this paper. In particular, we provide a principled way to capture the relations between labels and tags, and propose a novel framework CLARE, which fuses data CLAssification and tag REcommendation into a coherent model. With experiments on three social media datasets, we demonstrate that the proposed framework CLARE achieves superior performance on both tasks compared to the state-of-the-art methods.

AAAI Conference 2016 Conference Paper

Predicting Online Protest Participation of Social Media Users

• Suhas Ranganath
• Fred Morstatter
• Xia Hu
• Jiliang Tang
• Suhang Wang
• Huan Liu

AAAI Conference 2016 Conference Paper

Recommendation with Social Dimensions

• Jiliang Tang
• Suhang Wang
• Xia Hu
• Dawei Yin
• Yingzhou Bi
• Yi Chang
• Huan Liu

The pervasive presence of social media greatly enriches online users’ social activities, resulting in abundant social relations. Social relations provide an independent source for recommendation, bringing about new opportunities for recommender systems. Exploiting social relations to improve recommendation performance attracts a great amount of attention in recent years. Most existing social recommender systems treat social relations homogeneously and make use of direct connections (or strong dependency connections). However, connections in online social networks are intrinsically heterogeneous and are a composite of various relations. While connected users in online social networks form groups, and users in a group share similar interests, weak dependency connections are established among these users when they are not directly connected. In this paper, we investigate how to exploit the heterogeneity of social relations and weak dependency connections for recommendation. In particular, we employ social dimensions to simultaneously capture heterogeneity of social relations and weak dependency connections, and provide principled ways to model social dimensions, and propose a recommendation framework SoDimRec which incorporates heterogeneity of social relations and weak dependency connections based on social dimensions. Experimental results on real-world data sets demonstrate the effectiveness of the proposed framework. We conduct further experiments to understand the important role of social dimensions in the proposed framework.

AAAI Conference 2015 Conference Paper

Embedded Unsupervised Feature Selection

• Suhang Wang
• Jiliang Tang
• Huan Liu

Sparse learning has been proven to be a powerful technique in supervised feature selection, which allows to embed feature selection into the classification (or regression) problem. In recent years, increasing attention has been on applying spare learning in unsupervised feature selection. Due to the lack of label information, the vast majority of these algorithms usually generate cluster labels via clustering algorithms and then formulate unsupervised feature selection as sparse learning based supervised feature selection with these generated cluster labels. In this paper, we propose a novel unsupervised feature selection algorithm EUFS, which directly embeds feature selection into a clustering algorithm via sparse learning without the transformation. The Alternating Direction Method of Multipliers is used to address the optimization problem of EUFS. Experimental results on various benchmark datasets demonstrate the effectiveness of the proposed framework EUFS.

IJCAI Conference 2015 Conference Paper

Exploring Implicit Hierarchical Structures for Recommender Systems

• Suhang Wang
• Jiliang Tang
• Yilin Wang
• Huan Liu

Items in real-world recommender systems exhibit certain hierarchical structures. Similarly, user preferences also present hierarchical structures. Recent studies show that incorporating the explicit hierarchical structures of items or user preferences can improve the performance of recommender systems. However, explicit hierarchical structures are usually unavailable, especially those of user preferences. Thus, there’s a gap between the importance of hierarchical structures and their availability. In this paper, we investigate the problem of exploring the implicit hierarchical structures for recommender systems when they are not explicitly available. We propose a novel recommendation framework HSR to bridge the gap, which enables us to capture the implicit hierarchical structures of users and items simultaneously. Experimental results on two real world datasets demonstrate the effectiveness of the proposed framework.

IJCAI Conference 2015 Conference Paper

Unsupervised Sentiment Analysis for Social Media Images

• Yilin Wang
• Suhang Wang
• Jiliang Tang
• Huan Liu
• Baoxin Li

Recently text-based sentiment prediction has been extensively studied, while image-centric sentiment analysis receives much less attention. In this paper, we study the problem of understanding human sentiments from large-scale social media images, considering both visual content and contextual information, such as comments on the images, captions, etc. The challenge of this problem lies in the “semantic gap” between low-level visual features and higher-level image sentiments. Moreover, the lack of proper annotations/labels in the majority of social media images presents another challenge. To address these two challenges, we propose a novel Unsupervised SEntiment Analysis (USEA) framework for social media images. Our approach exploits relations among visual content and relevant contextual information to bridge the “semantic gap” in prediction of image sentiments. With experiments on two large-scale datasets, we show that the proposed method is effective in addressing the two challenges.