Arrow Research search

Author name cluster

Jundong Li

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.

54 papers
2 author rows

Possible papers

54

TMLR Journal 2026 Journal Article

Explainable Graph Learning for Particle Accelerator Operations

  • Song Wang
  • Chris Tennant
  • Jundong Li

Particle accelerators are vital tools in physics, medicine, and industry, requiring precise tuning to ensure optimal beam performance. However, real-world deviations from idealized simulations make beam tuning a time-consuming and error-prone process. In this work, we propose an explanation-driven framework for providing actionable insight into beamline operations, with a focus on the injector beamline at the Continuous Electron Beam Accelerator Facility (CEBAF). We represent beamline configurations as heterogeneous graphs, where setting nodes represent elements that human operators can actively adjust during beam tuning, and reading nodes passively provide diagnostic feedback. To identify the most influential setting nodes responsible for differences between any two beamline configurations, our approach first predicts the resulting changes in reading nodes caused by variations in settings, and then learns importance scores that capture the joint influence of multiple setting nodes. Experimental results on real-world CEBAF injector data demonstrate the framework’s ability to generate interpretable insights that can assist human operators in beamline tuning and reduce operational overhead.

PDF Details

ICML Conference 2025 Conference Paper

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

  • Binchi Zhang
  • Zaiyi Zheng
  • Zhengzhang Chen
  • Jundong Li

Symmetry in the parameter space of deep neural networks (DNNs) has proven beneficial for various deep learning applications. A well-known example is the permutation symmetry in Multi-Layer Perceptrons (MLPs), where permuting the rows of weight matrices in one layer and applying the inverse permutation to adjacent layers yields a functionally equivalent model. While permutation symmetry fully characterizes the equivalence set for MLPs, its discrete nature limits its utility for transformers. In this paper, we introduce rotation symmetry, a novel form of parameter space symmetry for transformers that generalizes permutation symmetry by rotating parameter matrices in self-attention layers. Unlike permutation symmetry, rotation symmetry operates in a continuous domain, thereby significantly expanding the equivalence set for transformers. Based on this property, we propose a theoretically optimal parameter matching algorithm as a plug-and-play module to enhance model fusion. We evaluate our approach using pre-trained transformers across diverse natural language and vision tasks. Experimental results demonstrate that our rotation symmetry-based matching algorithm substantially improves model fusion, highlighting the potential of parameter space symmetry to facilitate model fusion. Our code is available on https: //github. com/zhengzaiyi/RotationSymmetry

Details

AAAI Conference 2025 Conference Paper

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

  • Song Wang
  • Zhenyu Lei
  • Zhen Tan
  • Jiaqi Ding
  • Xinyu Zhao
  • Yushun Dong
  • Guorong Wu
  • Tianlong Chen

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn multiple pathways in brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Causal Effect Estimation with Mixed Latent Confounders and Post-treatment Variables

  • Yaochen Zhu
  • Jing Ma 0002
  • Liang Wu 0006
  • Qi Guo
  • Liangjie Hong
  • Jundong Li

Causal inference from observational data has attracted considerable attention among researchers. One main obstacle is the handling of confounders. As direct measurement of confounders may not be feasible, recent methods seek to address the confounding bias via proxy variables, i.e., covariates postulated to be conducive to the inference of latent confounders. However, the selected proxies may scramble both confounders and post-treatment variables in practice, which risks biasing the estimation by controlling for variables affected by the treatment. In this paper, we systematically investigate the bias due to latent post-treatment variables, i.e., latent post-treatment bias, in causal effect estimation. Specifically, we first derive the bias when selected proxies scramble both latent confounders and post-treatment variables, which we demonstrate can be arbitrarily bad. We then propose a Confounder-identifiable VAE (CiVAE) to address the bias. Based on a mild assumption that the prior of latent variables that generate the proxy belongs to a general exponential family with at least one invertible sufficient statistic in the factorized part, CiVAE individually identifies latent confounders and latent post-treatment variables up to bijective transformations. We then prove that with individual identification, the intractable disentanglement problem of latent confounders and post-treatment variables can be transformed into a tractable independence test problem despite arbitrary dependence may exist among them. Finally, we prove that the true causal effects can be unbiasedly estimated with transformed confounders inferred by CiVAE. Experiments on both simulated and real-world datasets demonstrate significantly improved robustness of CiVAE.

Details

ICLR Conference 2025 Conference Paper

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

  • Song Wang 0013
  • Peng Wang 0105
  • Tong Zhou
  • Yushun Dong
  • Zhen Tan 0001
  • Jundong Li

As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets. However, existing bias evaluation efforts often focus on only a particular type of bias and employ inconsistent evaluation metrics, leading to difficulties in comparison across different datasets and LLMs. To address these limitations, we collect a variety of datasets designed for the bias evaluation of LLMs, and further propose CEB, a Compositional Evaluation Bechmark that covers different types of bias across different social groups and tasks. The curation of CEB is based on our newly proposed compositional taxonomy, which characterizes each dataset from three dimensions: bias types, social groups, and tasks. By combining the three dimensions, we develop a comprehensive evaluation strategy for the bias in LLMs. Our experiments demonstrate that the levels of bias vary across these dimensions, thereby providing guidance for the development of specific bias mitigation methods.

Details

ICLR Conference 2025 Conference Paper

Edge Prompt Tuning for Graph Neural Networks

  • Xingbo Fu
  • Yinhan He
  • Jundong Li

Pre-training powerful Graph Neural Networks (GNNs) with unlabeled graph data in a self-supervised manner has emerged as a prominent technique in recent years. However, inevitable objective gaps often exist between pre-training and downstream tasks. To bridge this gap, graph prompt tuning techniques design and learn graph prompts by manipulating input graphs or reframing downstream tasks as pre-training tasks without fine-tuning the pre-trained GNN models. While recent graph prompt tuning methods have proven effective in adapting pre-trained GNN models for downstream tasks, they overlook the crucial role of edges in graph prompt design, which can significantly affect the quality of graph representations for downstream tasks. In this study, we propose EdgePrompt, a simple yet effective graph prompt tuning method from the perspective of edges. Unlike previous studies that design prompt vectors on node features, EdgePrompt manipulates input graphs by learning additional prompt vectors for edges and incorporates the edge prompts through message passing in the pre-trained GNN models to better embed graph structural information for downstream tasks. Our method is compatible with prevalent GNN architectures pre-trained under various pre-training strategies and is universal for different downstream tasks. We provide comprehensive theoretical analyses of our method regarding its capability of handling node classification and graph classification as downstream tasks. Extensive experiments on ten graph datasets under four pre-training strategies demonstrate the superiority of our proposed method against six baselines. Our code is available at https://github.com/xbfu/EdgePrompt.

Details

TMLR Journal 2025 Journal Article

FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs

  • Zihan Chen
  • Xingbo Fu
  • Yushun Dong
  • Jundong Li
  • Cong Shen

Graph neural networks (GNNs) have shown significant success in modeling graph data, and Federated Graph Learning (FGL) empowers clients to collaboratively train GNNs in a distributed manner while preserving data privacy. However, FGL faces unique challenges when the general neighbor distribution pattern of nodes varies significantly across clients. Specifically, FGL methods usually require that the graph data owned by all clients is homophilic to ensure similar neighbor distribution patterns of nodes. Such an assumption ensures that the learned knowledge is consistent across the local models from all clients. Therefore, these local models can be properly aggregated as a global model without undermining the overall performance. Nevertheless, when the neighbor distribution patterns of nodes vary across different clients (e.g., when clients hold graphs with different levels of heterophily), their local models may gain different and even conflict knowledge from their node-level predictive tasks. Consequently, aggregating these local models usually leads to catastrophic performance deterioration on the global model. To address this challenge, we propose FedHERO, an FGL framework designed to harness and share insights from heterophilic graphs effectively. At the heart of FedHERO is a dual-channel GNN equipped with a structure learner, engineered to discern the structural knowledge encoded in the local graphs. With this specialized component, FedHERO enables the local model for each client to identify and learn patterns that are universally applicable across graphs with different patterns of node neighbor distributions. FedHERO not only enhances the performance of individual client models by leveraging both local and shared structural insights but also sets a new precedent in this field to effectively handle graph data with various node neighbor distribution patterns. We conduct extensive experiments to validate the superior performance of FedHERO against existing alternatives.

PDF Details

TMLR Journal 2025 Journal Article

Generative Risk Minimization for Out-of-Distribution Generalization on Graphs

  • Song Wang
  • Zhen Tan
  • Yaochen Zhu
  • Chuxu Zhang
  • Jundong Li

Out-of-distribution (OOD) generalization on graphs aims at dealing with scenarios where the test graph distribution differs from the training graph distributions. Compared to i.i.d. data like images, the OOD generalization problem on graph-structured data remains challenging due to the non-i.i.d. property and complex structural information on graphs. Recently, several works on graph OOD generalization have explored extracting invariant subgraphs that share crucial classification information across different distributions. Nevertheless, such a strategy could be suboptimal for entirely capturing the invariant information, as the extraction of discrete structures could potentially lead to the loss of invariant information or the involvement of spurious information. In this paper, we propose an innovative framework, named Generative Risk Minimization (GRM), designed to generate an invariant subgraph for each input graph to be classified, instead of extraction. To address the challenge of optimization in the absence of optimal invariant subgraphs (i.e., ground truths), we derive a tractable form of the proposed GRM objective by introducing a latent causal variable, and its effectiveness is validated by our theoretical analysis. We further conduct extensive experiments across a variety of real-world graph datasets for both node-level and graph-level OOD generalization, and the results demonstrate the superiority of our framework GRM.

PDF Details

TMLR Journal 2025 Journal Article

Global Graph Counterfactual Explanation: A Subgraph Mapping Approach

  • Yinhan He
  • Wendy Zheng
  • Yaochen Zhu
  • Jing Ma
  • Saumitra Mishra
  • Natraj Raman
  • Ninghao Liu
  • Jundong Li

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-level perspective (i.e., generating counterfactuals for each individual graph), which suffers from information overload and lacks insights into the broader cross-graph relationships. To address such issues, we propose GlobalGCE, a novel global-level graph counterfactual explanation method. GlobalGCE aims to identify a collection of subgraph mapping rules as counterfactual explanations for the target GNN. According to these rules, substituting certain significant subgraphs with their counterfactual subgraphs will change the GNN prediction to the desired class for most graphs (i.e., maximum coverage). Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated. Extensive experiments demonstrate the superiority of our GlobalGCE compared to existing baselines. Our code can be found at \url{https://github.com/YinhanHe123/GlobalGCE}.

PDF Details

ICLR Conference 2025 Conference Paper

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

  • Yushun Dong
  • Patrick Soga
  • Yinhan He
  • Song Wang 0013
  • Jundong Li

Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based learning tasks. While their performance is often attributed to the powerful neighborhood aggregation mechanism, recent studies suggest that other components such as non-linear layers may also significantly affecting how GNNs process the input graph data in the spectral domain. Such evidence challenges the prevalent opinion that neighborhood aggregation mechanisms dominate the behavioral characteristics of GNNs in the spectral domain. To demystify such a conflict, this paper introduces a comprehensive benchmark to measure and evaluate GNNs' capability in capturing and leveraging the information encoded in different frequency components of the input graph data. Specifically, we first conduct an exploratory study demonstrating that GNNs can flexibly yield outputs with diverse frequency components even when certain frequencies are absent or filtered out from the input graph data. We then formulate a novel research problem of measuring and benchmarking the performance of GNNs from a spectral perspective. To take an initial step towards a comprehensive benchmark, we design an evaluation protocol supported by comprehensive theoretical analysis. Finally, we introduce a comprehensive benchmark on real-world datasets, revealing insights that challenge prevalent opinions from a spectral perspective. We believe that our findings will open new avenues for future advancements in this area. Our implementations can be found at: https://github.com/yushundong/Spectral-benchmark.

Details

NeurIPS Conference 2025 Conference Paper

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

  • Xingbo Fu
  • Zhenyu Lei
  • Zihan Chen
  • Binchi Zhang
  • Chuxu Zhang
  • Jundong Li

Graph Neural Networks (GNNs) have revolutionized the field of graph learning by learning expressive graph representations from massive graph data. As a common pattern to train powerful GNNs, the "pre-training, adaptation" scheme first pre-trains GNNs over unlabeled graph data and subsequently adapts them to specific downstream tasks. In the adaptation phase, graph prompting is an effective strategy that modifies input graph data with learnable prompts while keeping pre-trained GNN models frozen. Typically, existing graph prompting studies mainly focus on feature-oriented methods that apply graph prompts to node features or hidden representations. However, these studies often achieve suboptimal performance, as they consistently overlook the potential of topology-oriented prompting, which adapts pre-trained GNNs by modifying the graph topology. In this study, we conduct a pioneering investigation of graph prompting in terms of graph topology. We propose the first Graph T opology- O riented P rompting (GraphTOP) framework to effectively adapt pre-trained GNN models for downstream tasks. More specifically, we reformulate topology-oriented prompting as an edge rewiring problem within multi-hop local subgraphs and relax it into the continuous probability space through reparameterization while ensuring tight relaxation and preserving graph sparsity. Extensive experiments on five graph datasets under four pre-training strategies demonstrate that our proposed GraphTOP outshines six baselines on multiple node classification datasets. Our code is available at https: //github. com/xbfu/GraphTOP.

PDF Details

NeurIPS Conference 2025 Conference Paper

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

  • Yinhan He
  • Wendy Zheng
  • Song Wang
  • Zaiyi Zheng
  • Yushun Dong
  • Yaochen Zhu
  • Jundong Li

In-Context Learning (ICL) is a technique where large language models (LLMs) leverage multiple demonstrations (i. e. , examples) to perform tasks. With the recent expansion of LLM context windows, many-shot ICL (generally with more than 50 demonstrations) can lead to significant performance improvements on a variety of language tasks such as text classification and question answering. Nevertheless, ICL faces the issue of demonstration order instability (ICL-DOI), which means that performance varies significantly depending on the order of demonstrations. Moreover, ICL-DOI persists in many-shot ICL, validated by our thorough experimental investigation. Current strategies for handling ICL-DOI are not applicable to many-shot ICL due to two critical challenges: (1) Most existing methods assess demonstration order quality by first prompting the LLM, then using heuristic metrics based on the LLM's predictions. In the many-shot scenarios, these metrics without theoretical grounding become unreliable, where the LLMs struggle to effectively utilize information from long input contexts, making order distinctions less clear. The requirement to examine all orders for the large number of demonstrations is computationally infeasible due to the super-exponential complexity of the order space in many-shot ICL. To tackle the first challenge, we design a demonstration order evaluation metric based on information theory for measuring order quality, which effectively quantifies the usable information gain of a given demonstration order. To address the second challenge, we propose a hierarchical demonstration order optimization method named \texttt{HIDO} that enables a more refined exploration of the order space, achieving high ICL performance without the need to evaluate all possible orders. Extensive experiments on multiple LLMs and real-world datasets demonstrate that our \texttt{HIDO} method consistently and efficiently outperforms other baselines. Our code project can be found at https: //github. com/YinhanHe123/HIDO/.

PDF Details

TMLR Journal 2025 Journal Article

Instance-Aware Graph Prompt Learning

  • Jiazheng Li
  • Jundong Li
  • Chuxu Zhang

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus the pretraining and fine-tuning paradigm has been proposed to mitigate the label cost issue. Subsequently, the gap between the pretext tasks and downstream tasks has spurred the development of graph prompt learning which inserts a set of graph prompts into the original graph data with minimal parameters while preserving competitive performance. However, the current exploratory works are still limited since they all concentrate on learning fixed task-specific prompts which may not generalize well across the diverse instances that the task comprises. To tackle this challenge, we introduce Instance-Aware Graph Prompt Learning (IA-GPL) in this paper, aiming to generate distinct prompts tailored to different input instances. The process involves generating intermediate prompts for each instance using a lightweight architecture, quantizing these prompts through trainable codebook vectors, and employing the exponential moving average technique to ensure stable training. Extensive experiments conducted on multiple datasets and settings showcase the superior performance of IA-GPL compared to state-of-the-art baselines.

PDF Details

IJCAI Conference 2025 Conference Paper

Interpreting Pretrained Language Models via Concept Bottlenecks (Extended Abstract)

  • Zhen Tan
  • Lu Cheng
  • Song Wang
  • Yuan Bo
  • Jundong Li
  • Huan Liu

Pretrained language models (PLMs) achieve state-of-the-art results but often function as ``black boxes'', hindering interpretability and responsible deployment. While methods like attention analysis exist, they often lack clarity and intuitiveness. We propose interpreting PLMs through high-level, human-understandable concepts using Concept Bottleneck Models (CBMs). This extended abstract introduces C3M (ChatGPT-guided Concept augmentation with Concept-level Mixup), a novel framework for training Concept-Bottleneck-Enabled PLMs (CBE-PLMs). C3M leverages Large Language Models (LLMs) like ChatGPT to augment concept sets and generate noisy concept labels, combined with a concept-level MixUp mechanism to enhance robustness and effectively learn from both human-annotated and machine-generated concepts. Empirical results show our approach provides intuitive explanations, aids model diagnosis via test-time intervention, and improves the interpretability-utility trade-off, even with limited or noisy concept annotations. This is an concise version of [Tan et al. , 2024b], recipient of the Best Paper Award at PAKDD 2024. Code and data are released at https: //github. com/Zhen-Tan-dmml/CBM_NLP. git.

PDF Details DOI

ICML Conference 2025 Conference Paper

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

  • Zihan Chen 0002
  • Song Wang 0013
  • Zhen Tan 0001
  • Jundong Li
  • Cong Shen 0001

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the expanded context windows of LLMs have led to many-shot ICL, which uses hundreds of demonstrations and outperforms few-shot ICL, which relies on fewer examples. However, this approach is often hindered by the high cost of obtaining large amounts of labeled data. To address this challenge, we propose M any-Shot A daptive P seudo- L ab E ling, namely MAPLE, a novel influence-based many-shot ICL framework that utilizes pseudo-labeled samples to compensate for the lack of label information. We first identify a subset of impactful unlabeled samples and perform pseudo-labeling on them by querying LLMs. These pseudo-labeled samples are then adaptively selected and tailored to each test query as input to improve the performance of many-shot ICL, without significant labeling costs. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework, showcasing its ability to enhance LLM adaptability and performance with limited labeled data. Our code is provided at https: //github. com/Chen-1031/MAPLE_ICL.

Details

ICLR Conference 2025 Conference Paper

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

  • Song Wang 0013
  • Junhong Lin
  • Xiaojie Guo 0002
  • Julian Shun
  • Jundong Li
  • Yada Zhu

While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate. This limitation reduces the accuracy of answering questions based on these graphs. Our analysis reveals that the combination of greedy search and forward reasoning is a major contributor to this issue. To overcome these challenges, we introduce the concept of super-relations, which enables both forward and backward reasoning by summarizing and connecting various relational paths within the graph. This holistic approach not only expands the search space, but also significantly improves retrieval efficiency. In this paper, we propose the ReKnoS framework, which aims to Reason over Knowledge Graphs with Super-Relations. Our framework’s key advantages include the inclusion of multiple relation paths through super-relations, enhanced forward and backward reasoning capabilities, and increased efficiency in querying LLMs. These enhancements collectively lead to a substantial improvement in the successful retrieval rate and overall reasoning performance. We conduct extensive experiments on a variety of datasets to evaluate ReKnoS, and the results demonstrate the superior performance of ReKnoS over existing state-of-the-art baselines, with an average accuracy gain of 2.92% across nine real-world datasets.

Details

NeurIPS Conference 2025 Conference Paper

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

  • Yinhan He
  • Wendy Zheng
  • Yaochen Zhu
  • Zaiyi Zheng
  • Lin Su
  • Sriram Vasudevan
  • Qi Guo
  • Liangjie Hong

Chain-of-Thought (CoT) enhances the performance of Large Language Models (LLMs) on reasoning tasks by encouraging step-by-step solutions. However, the verbosity of CoT reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which encode reasoning steps within LLM's hidden embeddings (termed ``implicit reasoning'') rather than explicit tokens. This approach accelerates CoT reasoning by reducing the reasoning length and bypassing some LLM components. However, existing implicit CoT methods face two significant challenges: (1) they fail to preserve the semantic alignment between the implicit reasoning (when transformed to natural language) and the ground-truth reasoning, resulting in a significant CoT performance degradation, and (2) they focus on reducing the length of the implicit reasoning; however, they neglect the considerable time cost for an LLM to generate one individual implicit reasoning token. To tackle these challenges, we propose a novel semantically-aligned implicit CoT framework termed SemCoT. In particular, for the first challenge, we design a contrastively trained sentence transformer that evaluates semantic alignment between implicit and explicit reasoning, which is used to enforce semantic preservation during implicit reasoning optimization. To address the second challenge, we introduce an efficient implicit reasoning generator by finetuning a lightweight language model using knowledge distillation. This generator is guided by our sentence transformer to distill ground-truth reasoning into semantically aligned implicit reasoning, while also optimizing for accuracy. SemCoT is the first approach that enhances CoT efficiency by jointly optimizing token-level generation speed and preserving semantic alignment with ground-truth reasoning. Extensive experiments demonstrate the superior performance of SemCoT compared to state-of-the-art methods in both efficiency and effectiveness. Our code can be found at https: //github. com/YinhanHe123/SemCoT/.

PDF Details

AAAI Conference 2025 Conference Paper

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data

  • Zhenyu Lei
  • Yushun Dong
  • Jundong Li
  • Chen Chen

Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.

PDF Details DOI

ICML Conference 2025 Conference Paper

Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models

  • Yinhan He
  • Wendy Zheng
  • Yushun Dong
  • Yaochen Zhu
  • Chen Chen 0022
  • Jundong Li

Mechanistic interpretability (MI) research aims to understand large language models (LLMs) by identifying computational circuits, subgraphs of model components with associated functional interpretations, that explain specific behaviors. Current MI approaches focus on discovering task-specific circuits, which has two key limitations: (1) poor generalizability across different language tasks, and (2) high costs associated with requiring human or advanced LLM interpretation of each computational node. To address these challenges, we propose developing a “modular circuit (MC) vocabulary” consisting of task-agnostic functional units. Each unit consists of a small computational subgraph with its interpretation. This approach enables global interpretability by allowing different language tasks to share common MCs, while reducing costs by reusing established interpretations for new tasks. We establish five criteria for characterizing the MC vocabulary and present ModCirc, a novel global-level mechanistic interpretability framework for discovering MC vocabularies in LLMs. We demonstrate ModCirc’s effectiveness by showing that it can identify modular circuits that perform well on various metrics.

Details

AAAI Conference 2025 Conference Paper

Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning

  • Xingbo Fu
  • Zihan Chen
  • Yinhan He
  • Song Wang
  • Binchi Zhang
  • Chen Chen
  • Jundong Li

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such as graph property prediction. In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes. In particular, graph properties are usually associated with invariant label-relevant substructures (i.e., subgraphs) across clients, while label-irrelevant substructures can appear in a client-specific manner. The issue of distribution shifts of graph data hinders the efficiency of GNN training and leads to serious performance degradation in FGL. To tackle the aforementioned issue, we propose a novel FGL framework entitled FedVN that eliminates distribution shifts through client-specific graph augmentation strategies with multiple learnable Virtual Nodes (VNs). Specifically, FedVN lets the clients jointly learn a set of shared VNs while training a global GNN model. To eliminate distribution shifts, each client trains a personalized edge generator that determines how the VNs connect local graphs in a client-specific manner. Furthermore, we provide theoretical analyses indicating that FedVN can eliminate distribution shifts of graph data across clients. Comprehensive experiments on four datasets under five settings demonstrate the superiority of our proposed FedVN over nine baselines.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Adversarial Attacks on Fairness of Graph Neural Networks

  • Binchi Zhang
  • Yushun Dong
  • Chen Chen 0022
  • Yada Zhu
  • Minnan Luo
  • Jundong Li

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly improve the algorithmic fairness of GNNs, the fairness can be easily corrupted by carefully designed adversarial attacks. In this paper, we investigate the problem of adversarial attacks on fairness of GNNs and propose G-FairAttack, a general framework for attacking various types of fairness-aware GNNs in terms of fairness with an unnoticeable effect on prediction utility. In addition, we propose a fast computation technique to reduce the time complexity of G-FairAttack. The experimental study demonstrates that G-FairAttack successfully corrupts the fairness of different types of GNNs while keeping the attack unnoticeable. Our study on fairness attacks sheds light on potential vulnerabilities in fairness-aware GNNs and guides further research on the robustness of GNNs in terms of fairness.

Details

NeurIPS Conference 2024 Conference Paper

Efficient Prompt Optimization Through the Lens of Best Arm Identification

  • Chengshuai Shi
  • Kun Yang
  • Zihan Chen
  • Jundong Li
  • Jing Yang
  • Cong Shen

The remarkable instruction-following capability of large language models (LLMs) has sparked a growing interest in automatically finding good prompts, i. e. , prompt optimization. Most existing works follow the scheme of selecting from a pre-generated pool of candidate prompts. However, these designs mainly focus on the generation strategy, while limited attention has been paid to the selection method. Especially, the cost incurred during the selection (e. g. , accessing LLM and evaluating the responses) is rarely explicitly considered. To overcome this limitation, this work provides a principled framework, TRIPLE, to efficiently perform prompt selection under an explicit budget constraint. TRIPLE is built on a novel connection established between prompt optimization and fixed-budget best arm identification (BAI-FB) in multi-armed bandits (MAB); thus, it is capable of leveraging the rich toolbox from BAI-FB systematically and also incorporating unique characteristics of prompt optimization. Extensive experiments on multiple well-adopted tasks using various LLMs demonstrate the remarkable performance improvement of TRIPLE over baselines while satisfying the limited budget constraints. As an extension, variants of TRIPLE are proposed to efficiently select examples for few-shot prompts, also achieving superior empirical performance.

PDF Details DOI

TMLR Journal 2024 Journal Article

Federated Graph Learning with Graphless Clients

  • Xingbo Fu
  • Song Wang
  • Yushun Dong
  • Binchi Zhang
  • Chen Chen
  • Jundong Li

Federated graph learning is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated learning systems where only a part of the clients have such data while other clients graphless clients may only have features. This naturally leads to a novel problem in federated graph learning: how to jointly train a model over distributed graph data with graphless clients? To tackle this problem, we propose a novel Federated Graph Structure Learning (FedGSL) framework in this paper. In FedGSL, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments on five real-world graph datasets demonstrate the superiority of FedGSL over other five federated learning approaches.

PDF Details

NeurIPS Conference 2024 Conference Paper

Mixture of Demonstrations for In-Context Learning

  • Song Wang
  • Zihan Chen
  • Chengshuai Shi
  • Cong Shen
  • Jundong Li

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle various tasks by providing input-output examples as additional inputs, referred to as demonstrations. Nevertheless, the performance of ICL could be easily impacted by the quality of selected demonstrations. Existing efforts generally learn a retriever model to score each demonstration for selecting suitable demonstrations, however, the effect is suboptimal due to the large search space and the noise from unhelpful demonstrations. In this study, we introduce MoD, which partitions the demonstration pool into groups, each governed by an expert to reduce search space. We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model. During inference, experts collaboratively retrieve demonstrations for the input query to enhance the ICL performance. We validate MoD via experiments across a range of NLP datasets and tasks, demonstrating its state-of-the-art performance and shedding new light on the future design of retrieval methods for ICL.

PDF Details DOI

ICML Conference 2024 Conference Paper

Towards Certified Unlearning for Deep Neural Networks

  • Binchi Zhang
  • Yushun Dong
  • Tianhao Wang
  • Jundong Li

In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees. However, its application to deep neural networks (DNNs), known for their highly nonconvex nature, still poses challenges. To bridge the gap between certified unlearning and DNNs, we propose several simple techniques to extend certified unlearning methods to nonconvex objectives. To reduce the time complexity, we develop an efficient computation method by inverse Hessian approximation without compromising certification guarantees. In addition, we extend our discussion of certification to nonconvergence training and sequential unlearning, considering that real-world users can send unlearning requests at different time points. Extensive experiments on three real-world datasets demonstrate the efficacy of our method and the advantages of certified unlearning in DNNs.

Details

ICML Conference 2024 Conference Paper

Verification of Machine Unlearning is Fragile

  • Binchi Zhang
  • Zihan Chen 0002
  • Cong Shen 0001
  • Jundong Li

As privacy concerns escalate in the realm of machine learning, data owners now have the option to utilize machine unlearning to remove their data from machine learning models, following recent legislation. To enhance transparency in machine unlearning and avoid potential dishonesty by model providers, various verification strategies have been proposed. These strategies enable data owners to ascertain whether their target data has been effectively unlearned from the model. However, our understanding of the safety issues of machine unlearning verification remains nascent. In this paper, we explore the novel research question of whether model providers can circumvent verification strategies while retaining the information of data supposedly unlearned. Our investigation leads to a pessimistic answer: the verification of machine unlearning is fragile. Specifically, we categorize the current verification strategies regarding potential dishonesty among model providers into two types. Subsequently, we introduce two novel adversarial unlearning processes capable of circumventing both types. We validate the efficacy of our methods through theoretical analysis and empirical experiments using real-world datasets. This study highlights the vulnerabilities and limitations in machine unlearning verification, paving the way for further research into the safety of machine unlearning.

Details

ECAI Conference 2023 Conference Paper

Fair Few-Shot Learning with Auxiliary Sets

  • Song Wang 0013
  • Jing Ma 0002
  • Lu Cheng 0001
  • Jundong Li

Recently, there has been a growing interest in developing machine learning (ML) models that can promote fairness, i. e. , eliminating biased predictions towards certain populations (e. g. , individuals from a specific demographic group). Most existing works learn such models based on well-designed fairness constraints in optimization. Nevertheless, in many practical ML tasks, only very few labeled data samples can be collected, which can lead to inferior fairness performance. This is because existing fairness constraints are designed to restrict the prediction disparity among different sensitive groups, but with few samples, it becomes difficult to accurately measure the disparity, thus rendering ineffective fairness optimization. In this paper, we define the fairness-aware learning task with limited training samples as the fair few-shot learning problem. To deal with this problem, we devise a novel framework that accumulates fairness-aware knowledge across different meta-training tasks and then generalizes the learned knowledge to meta-test tasks. To compensate for insufficient training samples, we propose an essential strategy to select and leverage an auxiliary set for each meta-test task. These auxiliary sets contain several labeled training samples that can enhance the model performance regarding fairness in meta-test tasks, thereby allowing for the transfer of learned useful fairness-oriented knowledge to meta-test tasks. Furthermore, we conduct extensive experiments on three real-world datasets to validate the superiority of our framework against the state-of-the-art baselines.

Details

AAAI Conference 2023 Conference Paper

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

  • Yushun Dong
  • Song Wang
  • Jing Ma
  • Ninghao Liu
  • Jundong Li

Graph Neural Networks (GNNs) have emerged as the leading paradigm for solving graph analytical problems in various real-world applications. Nevertheless, GNNs could potentially render biased predictions towards certain demographic subgroups. Understanding how the bias in predictions arises is critical, as it guides the design of GNN debiasing mechanisms. However, most existing works overwhelmingly focus on GNN debiasing, but fall short on explaining how such bias is induced. In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes. Specifically, we propose a novel strategy named Probabilistic Distribution Disparity (PDD) to measure the bias exhibited in GNNs, and develop an algorithm to efficiently estimate the influence of each training node on such bias. We verify the validity of PDD and the effectiveness of influence estimation through experiments on real-world datasets. Finally, we also demonstrate how the proposed framework could be used for debiasing GNNs. Open-source code can be found at https://github.com/yushundong/BIND.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Learning Causal Effects on Hypergraphs (Extended Abstract)

  • Jing Ma
  • Mengting Wan
  • Longqi Yang
  • Jundong Li
  • Brent Hecht
  • Jaime Teevan

Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we study hypergraphs from the perspective of causality. Specifically, we focus on the problem of individual treatment effect (ITE) estimation on hypergraphs, aiming to estimate how much an intervention (e. g. , wearing face covering) would causally affect an outcome (e. g. , COVID-19 infection) of each individual node. Existing works on ITE estimation either assume that the outcome of one individual should not be influenced by the treatment of other individuals (i. e. , no interference), or assume the interference only exists between connected individuals in an ordinary graph. We argue that these assumptions can be unrealistic on real-world hypergraphs, where higher-order interference can affect the ITE estimations due to group interactions. We investigate high-order interference modeling, and propose a new causality learning framework powered by hypergraph neural networks. Extensive experiments on real-world hypergraphs verify the superiority of our framework over existing baselines.

PDF Details DOI

TMLR Journal 2023 Journal Article

Mind the Gap: Mitigating the Distribution Gap in Graph Few-shot Learning

  • Chunhui Zhang
  • Hongfu Liu
  • Jundong Li
  • Yanfang Ye
  • Chuxu Zhang

Prevailing supervised deep graph learning models often suffer from the issue of label scarcity, leading to performance degradation in the face of limited annotated data. Although numerous graph few-shot learning (GFL) methods have been developed to mitigate this problem, they tend to rely excessively on labeled data. This over-reliance on labeled data can result in impaired generalization ability in the test phase due to the existence of a distribution gap. Moreover, existing GFL methods lack a general purpose as their designs are coupled with task or data-specific characteristics. To address these shortcomings, we propose a novel Self-Distilled Graph Few-shot Learning framework (SDGFL) that is both general and effective. SDGFL leverages a self-distilled contrastive learning procedure to boost GFL. Specifically, our model first pre-trains a graph encoder with contrastive learning using unlabeled data. Later, the trained encoder is frozen as a teacher model to distill a student model with a contrastive loss. The distilled model is then fed to GFL. By learning data representation in a self-supervised manner, SDGFL effectively mitigates the distribution gap and enhances generalization ability. Furthermore, our proposed framework is task and data-independent, making it a versatile tool for general graph mining purposes. To evaluate the effectiveness of our proposed framework, we introduce an information-based measurement that quantifies its capability. Through comprehensive experiments, we demonstrate that SDGFL outperforms state-of-the-art baselines on various graph mining tasks across multiple datasets in the few-shot scenario. We also provide a quantitative measurement of SDGFL’s superior performance in comparison to existing methods.

PDF Details

NeurIPS Conference 2022 Conference Paper

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

  • Kay Liu
  • Yingtong Dou
  • Yue Zhao
  • Xueying Ding
  • Xiyang Hu
  • Ruitong Zhang
  • Kaize Ding
  • Canyu Chen

Detecting which nodes in graphs are outliers is a relatively new machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years for this task, there has been no standard comprehensive setting for performance evaluation. Consequently, it has been difficult to understand which methods work well and when under a broad range of settings. To bridge this gap, we present—to the best of our knowledge—the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights. (1) We benchmark the outlier detection performance of 14 methods ranging from classical matrix factorization to the latest graph neural networks. (2) Using nine real datasets, our benchmark assesses how the different detection methods respond to two major types of synthetic outliers and separately to “organic” (real non-synthetic) outliers. (3) Using an existing random graph generation technique, we produce a family of synthetically generated datasets of different graph sizes that enable us to compare the running time and memory usage of the different outlier detection algorithms. Based on our experimental results, we discuss the pros and cons of existing graph outlier detection algorithms, and we highlight opportunities for future research. Importantly, our code is freely available and meant to be easily extendable: https: //github. com/pygod-team/pygod/tree/main/benchmark

PDF Details

NeurIPS Conference 2022 Conference Paper

CLEAR: Generative Counterfactual Explanations on Graphs

  • Jing Ma
  • Ruocheng Guo
  • Saumitra Mishra
  • Aidong Zhang
  • Jundong Li

Counterfactual explanations promote explainability in machine learning models by answering the question “how should the input instance be altered to obtain a desired predicted label? ". The comparison of this instance before and after perturbation can enhance human interpretation. Most existing studies on counterfactual explanations are limited in tabular data or image data. In this paper, we study the problem of counterfactual explanation generation on graphs. A few studies have explored to generate counterfactual explanations on graphs, but many challenges of this problem are still not well-addressed: 1) optimizing in the discrete and disorganized space of graphs; 2) generalizing on unseen graphs; 3) maintaining the causality in the generated counterfactuals without prior knowledge of the causal model. To tackle these challenges, we propose a novel framework CLEAR which aims to generate counterfactual explanations on graphs for graph-level prediction models. Specifically, CLEAR leverages a graph variational autoencoder based mechanism to facilitate its optimization and generalization, and promotes causality by leveraging an auxiliary variable to better identify the causal model. Extensive experiments on both synthetic and real-world graphs validate the superiority of CLEAR over state-of-the-art counterfactual explanation methods on graphs in different aspects.

PDF Details

IJCAI Conference 2022 Conference Paper

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs

  • Song Wang
  • Yushun Dong
  • Xiao Huang
  • Chen Chen
  • Jundong Li

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to graph classes with limited labeled graphs. Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set. However, existing methods generally ignore task correlations among meta-training tasks while treating them independently. Nevertheless, such task correlations can advance the model generalization to the target task for better classification performance. On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. Then we further design a loss-based sampling strategy to select tasks with more correlated classes. Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification. Extensive experiments on four prevalent few-shot graph classification datasets demonstrate the superiority of FAITH over other state-of-the-art baselines.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Few-Shot Learning on Graphs

  • Chuxu Zhang
  • Kaize Ding
  • Jundong Li
  • Xiangliang Zhang
  • Yanfang Ye
  • Nitesh V. Chawla
  • Huan Liu

Graph representation learning has attracted tremendous attention due to its remarkable performance in many real-world applications. However, prevailing supervised graph representation learning models for specific tasks often suffer from label sparsity issue as data labeling is always time and resource consuming. In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge. There have been many studies working on FSLG recently. In this paper, we comprehensively survey these work in the form of a series of methods and applications. Specifically, we first introduce FSLG challenges and bases, then categorize and summarize existing work of FSLG in terms of three major graph mining tasks at different granularity levels, i. e. , node, edge, and graph. Finally, we share our thoughts on some future research directions of FSLG. The authors of this survey have contributed significantly to the AI literature on FSLG over the last few years.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Graph Few-shot Learning with Task-specific Structures

  • Song Wang
  • Chen Chen
  • Jundong Li

Graph few-shot learning is of great importance among various graph learning tasks. Under the few-shot scenario, models are often required to conduct classification given limited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i. e. , the graph that the meta-task is sampled from) to learn node representations. Consequently, the learned representations for the same nodes are identical in all meta-tasks. Since the class sets are different across meta-tasks, node representations should be task-specific to promote classification performance. Therefore, to adaptively learn node representations across meta-tasks, we propose a novel framework that learns a task-specific structure for each meta-task. To handle the variety of nodes across meta-tasks, we extract relevant nodes and learn task-specific structures based on node influence and mutual information. In this way, we can learn node representations with the task-specific structure tailored for each meta-task. We further conduct extensive experiments on five node classification datasets under both single- and multiple-graph settings to validate the superiority of our framework over the state-of-the-art baselines.

PDF Details

TIST Journal 2022 Journal Article

Gray-Box Shilling Attack: An Adversarial Learning Approach

  • Zongwei Wang
  • Min Gao
  • Jundong Li
  • Junwei Zhang
  • Jiang Zhong

Recommender systems are essential components of many information services, which aim to find relevant items that match user preferences. Several studies have shown that shilling attacks can significantly weaken the robustness of recommender systems by injecting fake user profiles. Traditional shilling attacks focus on creating hand-engineered fake user profiles, but these profiles can be detected effortlessly by advanced detection methods. Adversarial learning, which has emerged in recent years, can be leveraged to generate powerful and intelligent attack models. To this end, in this article we explore potential risks of recommender systems and shed light on a gray-box shilling attack model based on generative adversarial networks, named GSA-GANs. Specifically, we aim to generate fake user profiles that can achieve two goals: unnoticeable and offensive. Toward these goals, there are several challenges that we need to address: (1) learning complex user behaviors from user-item rating data, and (2) adversely influencing the recommendation results without knowing the underlying recommendation algorithms. To tackle these challenges, two essential GAN modules are respectively designed to make generated fake profiles more similar to real ones and harmful to recommendation results. Experimental results on three public datasets demonstrate that the proposed GSA-GANs framework outperforms baseline models in attack effectiveness, transferability, and camouflage. In the end, we also provide several possible defensive strategies against GSA-GANs. The exploration and analysis in our work will contribute to the defense research of recommender systems.

Details DOI

NeurIPS Conference 2022 Conference Paper

TwiBot-22: Towards Graph-Based Twitter Bot Detection

  • Shangbin Feng
  • Zhaoxuan Tan
  • Herun Wan
  • Ningnan Wang
  • Zilong Chen
  • Binchi Zhang
  • Qinghua Zheng
  • Wenqian Zhang

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at \url{https: //twibot22. github. io/}.

PDF Details

IS Journal 2021 Journal Article

Anomaly Detection Aided Budget Online Classification for Imbalanced Data Streams

  • Xijun Liang
  • Xiaoxin Song
  • KAI QI
  • Jundong Li
  • Jinyu Liu
  • Ling Jian

Learning from imbalanced data streams differs from the traditional learning paradigm due to the issues of imbalanced classes. It has significant implications in a myriad of real-world applications, ranging from financial risk, network security, to medical diagnosis. Moreover, outliers usually appear in data streams. The issue of class imbalance or anomaly itself could negatively affect the performance of the underlying learning algorithms, and their combination makes the learning problem harder. In this work, we propose an anomaly detection aided budget online weighted learning method (BOW-LM) to identify positive and negative instances from imbalanced data streams. BOW-LM is based on the widely used Feedforward Networks with Random Weights. An agile lightweight anomaly detector is designed based on the nonlinear mapping of the network. To reduce computational complexity and to response promptly, BOW-LM employs a matrix correction technique to update the learning model by only $\mathcal {O}(L^2)$O(L2) operations for each data chunk with $L$L hidden layer nodes. Empirical studies on both synthetic and real-world datasets demonstrate the effectiveness of BOW-LM.

Details DOI

IJCAI Conference 2021 Conference Paper

Multi-Cause Effect Estimation with Disentangled Confounder Representation

  • Jing Ma
  • Ruocheng Guo
  • Aidong Zhang
  • Jundong Li

One fundamental problem in causality learning is to estimate the causal effects of one or multiple treatments (e. g. , medicines in the prescription) on an important outcome (e. g. , cure of a disease). One major challenge of causal effect estimation is the existence of unobserved confounders -- the unobserved variables that affect both the treatments and the outcome. Recent studies have shown that by modeling how instances are assigned with different treatments together, the patterns of unobserved confounders can be captured through their learned latent representations. However, the interpretability of the representations in these works is limited. In this paper, we focus on the multi-cause effect estimation problem from a new perspective by learning disentangled representations of confounders. The disentangled representations not only facilitate the treatment effect estimation but also strengthen the understanding of causality learning process. Experimental results on both synthetic and real-world datasets show the superiority of our proposed framework from different aspects.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

IGNITE: A Minimax Game Toward Learning Individual Treatment Effects from Networked Observational Data

  • Ruocheng Guo
  • Jundong Li
  • Yichuan Li
  • K. Selçuk Candan
  • Adrienne Raglin
  • Huan Liu

Networked observational data presents new opportunities for learning individual causal effects, which plays an indispensable role in decision making. Such data poses the challenge of confounding bias. Previous work presents two desiderata to handle confounding bias. On the treatment group level, we aim to balance the distributions of confounder representations. On the individual level, it is desirable to capture patterns of hidden confounders that predict treatment assignments. Existing methods show the potential of utilizing network information to handle confounding bias, but they only try to satisfy one of the two desiderata. This is because the two desiderata seem to contradict each other. When the two distributions of confounder representations are highly overlapped, then we confront the undiscriminating problem between the treated and the controlled. In this work, we formulate the two desiderata as a minimax game. We propose IGNITE that learns representations of confounders from networked observational data, which is trained by a minimax game to achieve the two desiderata. Experiments verify the efficacy of IGNITE on two datasets under various settings.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Inductive Anomaly Detection on Attributed Networks

  • Kaize Ding
  • Jundong Li
  • Nitin Agarwal
  • Huan Liu

Anomaly detection on attributed networks has attracted a surge of research attention due to its broad applications in various high-impact domains, such as security, finance, and healthcare. Nonetheless, most of the existing efforts do not naturally generalize to unseen nodes, leading to the fact that people have to retrain the detection model from scratch when dealing with newly observed data. In this study, we propose to tackle the problem of inductive anomaly detection on attributed networks with a novel unsupervised framework: Aegis (adversarial graph differentiation networks). Specifically, we design a new graph neural layer to learn anomaly-aware node representations and further employ generative adversarial learning to detect anomalies among new data. Extensive experiments on various attributed networks demonstrate the efficacy of the proposed approach.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Tracking Disaster Footprints with Social Streaming Data

  • Lu Cheng
  • Jundong Li
  • K. Selcuk Candan
  • Huan Liu

Social media has become an indispensable tool in the face of natural disasters due to its broad appeal and ability to quickly disseminate information. For instance, Twitter is an important source for disaster responders to search for (1) topics that have been identified as being of particular interest over time, i. e. , common topics such as “disaster rescue”; (2) new emerging themes of disaster-related discussions that are fast gathering in social media streams (Saha and Sindhwani 2012), i. e. , distinct topics such as “the latest tsunami destruction”. To understand the status quo and allocate limited resources to most urgent areas, emergency managers need to quickly sift through relevant topics generated over time and investigate their commonness and distinctiveness. A major obstacle to the effective usage of social media, however, is its massive amount of noisy and undesired data. Hence, a naive method, such as set intersection/difference to find common/distinct topics, is often not practical. To address this challenge, this paper studies a new topic tracking problem that seeks to effectively identify the common and distinct topics with social streaming data. The problem is important as it presents a promising new way to efficiently search for accurate information during emergency response. This is achieved by an online Nonnegative Matrix Factorization (NMF) scheme that conducts a faster update of latent factors, and a joint NMF technique that seeks the balance between the reconstruction error of topic identification and the losses induced by discovering common and distinct topics. Extensive experimental results on real-world datasets collected during Hurricane Harvey and Florence reveal the effectiveness of our framework.

PDF Details

IJCAI Conference 2019 Conference Paper

InterSpot: Interactive Spammer Detection in Social Media

  • Kaize Ding
  • Jundong Li
  • Shivam Dhar
  • Shreyash Devan
  • Huan Liu

Spammer detection in social media has recently received increasing attention due to the rocketing growth of user-generated data. Despite the empirical success of existing systems, spammers may continuously evolve over time to impersonate normal users while new types of spammers may also emerge to combat with the current detection system, leading to the fact that a built system will gradually lose its efficacy in spotting spammers. To address this issue, grounded on the contextual bandit model, we present a novel system for conducting interactive spammer detection. We demonstrate our system by showcasing the interactive learning process, which allows the detection model to keep optimizing its detection strategy through incorporating the feedback information from human experts.

PDF Details

IJCAI Conference 2019 Conference Paper

PI-Bully: Personalized Cyberbullying Detection with Peer Influence

  • Lu Cheng
  • Jundong Li
  • Yasin Silva
  • Deborah Hall
  • Huan Liu

Cyberbullying has become one of the most pressing online risks for adolescents and has raised serious concerns in society. Recent years have witnessed a surge in research aimed at developing principled learning models to detect cyberbullying behaviors. These efforts have primarily focused on building a single generic classification model to differentiate bullying content from normal (non-bullying) content among all users. These models treat users equally and overlook idiosyncratic information about users that might facilitate the accurate detection of cyberbullying. In this paper, we propose a personalized cyberbullying detection framework, PI-Bully, that draws on empirical findings from psychology highlighting unique characteristics of victims and bullies and peer influence from like-minded users as predictors of cyberbullying behaviors. Our framework is novel in its ability to model peer influence in a collaborative environment and tailor cyberbullying prediction for each individual user. Extensive experimental evaluations on real-world datasets corroborate the effectiveness of the proposed framework.

PDF Details

IJCAI Conference 2018 Conference Paper

ANOMALOUS: A Joint Modeling Approach for Anomaly Detection on Attributed Networks

  • Zhen Peng
  • Minnan Luo
  • Jundong Li
  • Huan Liu
  • Qinghua Zheng

The key point of anomaly detection on attributed networks lies in the seamless integration of network structure information and attribute information. A vast majority of existing works are mainly based on the Homophily assumption that implies the nodal attribute similarity of connected nodes. Nonetheless, this assumption is untenable in practice as the existence of noisy and structurally irrelevant attributes may adversely affect the anomaly detection performance. Despite the fact that recent attempts perform subspace selection to address this issue, these algorithms treat subspace selection and anomaly detection as two separate steps which often leads to suboptimal solutions. In this paper, we investigate how to fuse attribute and network structure information more synergistically to avoid the adverse effects brought by noisy and structurally irrelevant attributes. Methodologically, we propose a novel joint framework to conduct attribute selection and anomaly detection as a whole based on CUR decomposition and residual analysis. By filtering out noisy and irrelevant node attributes, we perform anomaly detection with the remaining representative attributes. Experimental results on both synthetic and real-world datasets corroborate the effectiveness of the proposed framework.

PDF Details

TIST Journal 2018 Journal Article

Exploiting Multilabel Information for Noise-Resilient Feature Selection

  • Ling Jian
  • Jundong Li
  • Huan Liu

In a conventional supervised learning paradigm, each data instance is associated with one single class label. Multilabel learning differs in the way that data instances may belong to multiple concepts simultaneously, which naturally appear in a variety of high impact domains, ranging from bioinformatics and information retrieval to multimedia analysis. It targets leveraging the multiple label information of data instances to build a predictive learning model that can classify unlabeled instances into one or multiple predefined target classes. In multilabel learning, even though each instance is associated with a rich set of class labels, the label information could be noisy and incomplete as the labeling process is both time consuming and labor expensive, leading to potential missing annotations or even erroneous annotations. The existence of noisy and missing labels could negatively affect the performance of underlying learning algorithms. More often than not, multilabeled data often has noisy, irrelevant, and redundant features of high dimensionality. The existence of these uninformative features may also deteriorate the predictive power of the learning model due to the curse of dimensionality. Feature selection, as an effective dimensionality reduction technique, has shown to be powerful in preparing high-dimensional data for numerous data mining and machine-learning tasks. However, a vast majority of existing multilabel feature selection algorithms either boil down to solving multiple single-labeled feature selection problems or directly make use of the imperfect labels to guide the selection of representative features. As a result, they may not be able to obtain discriminative features shared across multiple labels. In this article, to bridge the gap between a rich source of multilabel information and its blemish in practical usage, we propose a novel noise-resilient multilabel informed feature selection framework (MIFS) by exploiting the correlations among different labels. In particular, to reduce the negative effects of imperfect label information in obtaining label correlations, we decompose the multilabel information of data instances into a low-dimensional space and then employ the reduced label representation to guide the feature selection phase via a joint sparse regression framework. Empirical studies on both synthetic and real-world datasets demonstrate the effectiveness and efficiency of the proposed MIFS framework.

Details DOI

IJCAI Conference 2018 Conference Paper

INITIATOR: Noise-contrastive Estimation for Marked Temporal Point Process

  • Ruocheng Guo
  • Jundong Li
  • Huan Liu

Copious sequential event data has consistently increased in various high-impact domains such as social media and sharing economy. When events start to take place in a sequential fashion, an important question arises: "what type of event will happen at what time in the near future? " To answer the question, a class of mathematical models called the marked temporal point process is often exploited as it can model the timing and properties of events seamlessly in a joint framework. Recently, various recurrent neural network (RNN) models are proposed to enhance the predictive power of mark temporal point process. However, existing marked temporal point models are fundamentally based on the Maximum Likelihood Estimation (MLE) framework for the training, and inevitably suffer from the problem resulted from the intractable likelihood function. Surprisingly, little attention has been paid to address this issue. In this work, we propose INITIATOR - a novel training framework based on noise-contrastive estimation to resolve this problem. Theoretically, we show the exists a strong connection between the proposed INITIATOR and the exact MLE. Experimentally, the efficacy of INITIATOR is demonstrated over the state-of-the-art approaches on several real-world datasets from various areas.

PDF Details

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.

PDF Details

AAAI Conference 2018 Conference Paper

Unsupervised Personalized Feature Selection

  • Jundong Li
  • Liang Wu
  • Harsh Dani
  • Huan Liu

Feature selection is effective in preparing high-dimensional data for a variety of learning tasks such as classification, clustering and anomaly detection. A vast majority of existing feature selection methods assume that all instances share some common patterns manifested in a subset of shared features. However, this assumption is not necessarily true in many domains where data instances could show high individuality. For example, in the medical domain, we need to capture the heterogeneous nature of patients for personalized predictive modeling, which could be characterized by a subset of instance-specific features. Motivated by this, we propose to study a novel problem of personalized feature selection. In particular, we investigate the problem in an unsupervised scenario as label information is usually hard to obtain in practice. To be specific, we present a novel unsupervised personalized feature selection framework UPFS to find some shared features by all instances and instance-specific features tailored to each instance. We formulate the problem into a principled optimization framework and provide an effective algorithm to solve it. Experimental results on real-world datasets verify the effectiveness of the proposed UPFS framework.

PDF Details

IS Journal 2017 Journal Article

Challenges of Feature Selection for Big Data Analytics

  • Jundong Li
  • Huan Liu

We're surrounded by huge amounts of large-scale high-dimensional data, but learning tasks require reduced data dimensionality. Feature selection has shown its effectiveness in many applications by building simpler and more comprehensive models, improving learning performance, and preparing clean, understandable data. Some unique characteristics of big data such as data velocity and data variety have presented challenges to the feature selection problem. In this article, the authors envision these challenges for big data analytics. To facilitate and promote feature selection research, they present an open source feature selection repository (scikit-feature) of popular algorithms.

Details DOI

IJCAI Conference 2017 Conference Paper

Radar: Residual Analysis for Anomaly Detection in Attributed Networks

  • Jundong Li
  • Harsh Dani
  • Xia Hu
  • Huan Liu

Attributed networks are pervasive in different domains, ranging from social networks, gene regulatory networks to financial transaction networks. This kind of rich network representation presents challenges for anomaly detection due to the heterogeneity of two data representations. A vast majority of existing algorithms assume certain properties of anomalies are given a prior. Since various types of anomalies in real-world attributed networks co-exist, the assumption that priori knowledge regarding anomalies is available does not hold. In this paper, we investigate the problem of anomaly detection in attributed networks generally from a residual analysis perspective, which has been shown to be effective in traditional anomaly detection problems. However, it is a non-trivial task in attributed networks as interactions among instances complicate the residual modeling process. Methodologically, we propose a learning framework to characterize the residuals of attribute information and its coherence with network information for anomaly detection. By learning and analyzing the residuals, we detect anomalies whose behaviors are singularly different from the majority. Experiments on real datasets show the effectiveness and generality of the proposed framework.

PDF Details

IJCAI Conference 2017 Conference Paper

Reconstruction-based Unsupervised Feature Selection: An Embedded Approach

  • Jundong Li
  • Jiliang Tang
  • Huan Liu

Feature selection has been proven to be effective and efficient in preparing high-dimensional data for data mining and machine learning problems. Since real-world data is usually unlabeled, unsupervised feature selection has received increasing attention in recent years. Without label information, unsupervised feature selection needs alternative criteria to define feature relevance. Recently, data reconstruction error emerged as a new criterion for unsupervised feature selection, which defines feature relevance as the capability of features to approximate original data via a reconstruction function. Most existing algorithms in this family assume predefined, linear reconstruction functions. However, the reconstruction function should be data dependent and may not always be linear especially when the original data is high-dimensional. In this paper, we investigate how to learn the reconstruction function from the data automatically for unsupervised feature selection, and propose a novel reconstruction-based unsupervised feature selection framework REFS, which embeds the reconstruction function learning process into feature selection. Experiments on various types of real-world datasets demonstrate the effectiveness of the proposed framework REFS.

PDF Details

AAAI Conference 2017 Conference Paper

Unsupervised Sentiment Analysis with Signed Social Networks

  • Kewei Cheng
  • Jundong Li
  • Jiliang Tang
  • Huan Liu

Huge volumes of opinion-rich data is user-generated in social media at an unprecedented rate, easing the analysis of individual and public sentiments. Sentiment analysis has shown to be useful in probing and understanding emotions, expressions and attitudes in the text. However, the distinct characteristics of social media data present challenges to traditional sentiment analysis. First, social media data is often noisy, incomplete and fast-evolved which necessitates the design of a sophisticated learning model. Second, sentiment labels are hard to collect which further exacerbates the problem by not being able to discriminate sentiment polarities. Meanwhile, opportunities are also unequivocally presented. Social media contains rich sources of sentiment signals in textual terms and user interactions, which could be helpful in sentiment analysis. While there are some attempts to leverage implicit sentiment signals in positive user interactions, little attention is paid on signed social networks with both positive and negative links. The availability of signed social networks motivates us to investigate if negative links also contain useful sentiment signals. In this paper, we study a novel problem of unsupervised sentiment analysis with signed social networks. In particular, we incorporate explicit sentiment signals in textual terms and implicit sentiment signals from signed social networks into a coherent model SignedSenti for unsupervised sentiment analysis. Empirical experiments on two real-world datasets corroborate its effectiveness.

PDF Details

IJCAI Conference 2016 Conference Paper

Multi-Label Informed Feature Selection

  • Ling Jian
  • Jundong Li
  • Kai Shu
  • Huan Liu

Multi-label learning has been extensively studied in the area of bioinformatics, information retrieval, multimedia annotation, etc. In multi-label learning, each instance is associated with multiple interdependent class labels, the label information can be noisy and incomplete. In addition, multi-labeled data often has noisy, irrelevant and redundant features of high dimensionality. As an effective data preprocessing step, feature selection has shown its effectiveness to prepare high-dimensional data for numerous data mining and machine learning tasks. Most of existing multi-label feature selection algorithms either boil down to solving multiple single-labeled feature selection problems or directly make use of imperfect labels. Therefore, they may not be able to find discriminative features that are shared by multiple labels. In this paper, we propose a novel multi-label informed feature selection framework MIFS, which exploits label correlations to select discriminative features across multiple labels. Specifically, to reduce the negative effects of imperfect label information in finding label correlations, we decompose the multi-label information into a low-dimensional space and then employ the reduced space to steer the feature selection process. Empirical studies on real-world datasets demonstrate the effectiveness and efficiency of the proposed framework.

PDF Details
v2026.09.13