papers

Publications (95)

cs.CL2026

Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight

Haolin Yang, Hakaze Cho, Kaize Ding +1

Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations a…

cs.IR2024

Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models

Kexin Zhang, Fuyuan Lyu, Xing Tang +5

The evolution of previous Click-Through Rate (CTR) models has mainly been driven by proposing complex components, whether shallow or deep, that are adept at modeling feature intera…

cs.LG2022

GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Yixin Liu, Kaize Ding, Huan Liu +1

Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training da…

cs.CL2026

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Ziqing Wang, Weihao Li, Shijie Chen +2

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language mo…

cs.CL2025

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering

Ziqing Wang, Chengsheng Mao, Xiaole Wen +2

Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA). However, when deployed in low-resource settings where…

cs.LG2026

Revisiting Multivariate Time Series Forecasting with Missing Values

Jie Yang, Yifan Hu, Kexin Zhang +3

Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliab…

cs.CL2020

Fact-Enhanced Synthetic News Generation

Kai Shu, Yichuan Li, Kaize Ding +1

The advanced text generation methods have witnessed great success in text summarization, language translation, and synthetic news generation. However, these techniques can be abuse…

cs.AI2026

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

Tianyu Liu, Allen Xin Wang, Antonia Panescu +30

AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchma…

cs.LG2024

MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detection

Xiongxiao Xu, Kaize Ding, Canyu Chen +1

Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The maj…

cs.LG2022

Supervised Graph Contrastive Learning for Few-shot Node Classification

Zhen Tan, Kaize Ding, Ruocheng Guo +1

Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph anno…

cs.LG2026

Tackling Fake Forgetting through Uncertainty Quantification

Yingdan Shi, Sijia Liu, Kaize Ding +1

Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric for assessing unlearning perfor…

cs.LG2022

Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity

Kaize Ding, Elnaz Nouri, Guoqing Zheng +2

The success of graph neural networks on graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice. When only few labeled nodes…

cs.LG2023

Towards Self-Interpretable Graph-Level Anomaly Detection

Yixin Liu, Kaize Ding, Qinghua Lu +3

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable dissimilarity compared to the majority in a collection. However, current works primarily focus on…

cs.IR2021

Sequential Recommendation for Cold-start Users with Meta Transitional Learning

Jianling Wang, Kaize Ding, James Caverlee

A fundamental challenge for sequential recommenders is to capture the sequential patterns of users toward modeling how users transit among items. In many practical scenarios, howev…

cs.LG2025

On Large Language Model Continual Unlearning

Chongyang Gao, Lixu Wang, Kaize Ding +3

While large language models have demonstrated impressive performance across various domains and tasks, their security issues have become increasingly severe. Machine unlearning has…

cs.LG2023

Federated Few-shot Learning

Song Wang, Xingbo Fu, Kaize Ding +3

Federated Learning (FL) enables multiple clients to collaboratively learn a machine learning model without exchanging their own local data. In this way, the server can exploit the…

cs.CL2026

HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification

Ziqing Wang, Kaize Ding

Node classification on text-attributed graphs (TAGs) is a fundamental task with broad applications in citation analysis, social networks, and recommendation systems. Current GNN-ba…

cs.LG2026

RAPTOR: Ridge-Adaptive Logistic Probes

Ziqi Gao, Yaotian Zhu, Qingcheng Zeng +4

Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used opera…

cs.CL2021

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

Kaize Ding, Dingcheng Li, Alexander Hanbo Li +4

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on larg…

cs.CR2025

A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments

Kaixiang Zhao, Lincan Li, Kaize Ding +3

Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increas…

cs.CR2025

Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection

Junjun Pan, Yixin Liu, Rui Miao +5

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical…

cs.LG2023

Virtual Node Tuning for Few-shot Node Classification

Zhen Tan, Ruocheng Guo, Kaize Ding +1

Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-…

cs.CL2024

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

Qingcheng Zeng, Mingyu Jin, Qinkai Yu +12

Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. One commonly used method to assess the reliability…

cs.LG2024

Multitask Active Learning for Graph Anomaly Detection

Wenjing Chang, Kay Liu, Kaize Ding +2

In the web era, graph machine learning has been widely used on ubiquitous graph-structured data. As a pivotal component for bolstering web security and enhancing the robustness of…

cs.IR2024

FBAdtTracker: An Interactive Data Collection and Analysis Tool for Facebook Advertisements

Ujun Jeong, Kaize Ding, Huan Liu

The growing use of social media has led to drastic changes in our decision-making. Especially, Facebook offers marketing API which promotes business to target potential groups who…

cs.LG2026

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection

Zhengyu Hu, Zheyuan Xiao, Linxin Song +10

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the high…

cs.LG2025

A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization

Ziqing Wang, Kexin Zhang, Zihan Zhao +4

Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic not…

cs.CL2026

Cat-DPO: Category-Adaptive Safety Alignment

Tiankai Yang, Yi Nian, Xinyuan Li +3

Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most prefere…

cs.LG2022

Few-Shot Learning on Graphs

Chuxu Zhang, Kaize Ding, Jundong Li +4

Graph representation learning has attracted tremendous attention due to its remarkable performance in many real-world applications. However, prevailing supervised graph representat…

cs.LG2021

Few-shot Network Anomaly Detection via Cross-network Meta-learning

Kaize Ding, Qinghai Zhou, Hanghang Tong +1

Network anomaly detection aims to find network elements (e.g., nodes, edges, subgraphs) with significantly different behaviors from the vast majority. It has a profound impact in a…

cs.CV2026

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thin…

cs.CL2026

No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents

Tiankai Yang, Jiate Li, Yi Nian +5

LLM-based agents increasingly operate across repeated sessions, maintaining task states to ensure continuity. In many deployments, a single agent serves multiple users within a tea…

cs.LG2025

Cross-Domain Conditional Diffusion Models for Time Series Imputation

Kexin Zhang, Baoyu Jing, K. Selçuk Candan +4

Cross-domain time series imputation is an underexplored data-centric research task that presents significant challenges, particularly when the target domain suffers from high missi…

cs.CL2026

CoAct: Co-Active LLM Preference Learning with Human-AI Synergy

Ruiyao Xu, Mihir Parmar, Tiankai Yang +3

Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated preference data remains expen…

cs.LG2025

Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey

Ruiyao Xu, Kaize Ding

Detecting anomalies or out-of-distribution (OOD) samples is critical for maintaining the reliability and trustworthiness of machine learning systems. Recently, Large Language Model…

cs.CL2024

RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response

Junyu Luo, Xiao Luo, Kaize Ding +3

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the coll…

cs.LG2024

Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs

Shuhan Liu, Kaize Ding

Distribution shifts on graphs -- the data distribution discrepancies between training and testing a graph machine learning model, are often ubiquitous and unavoidable in real-world…

cs.CV2026

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning

Jiazheng Li, Chi-Hao Wu, Yunze Liu +3

Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even…

cs.LG2022

Data Augmentation for Deep Graph Learning: A Survey

Kaize Ding, Zhe Xu, Hanghang Tong +1

Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To address the data…

cs.SI2022

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Ujun Jeong, Kaize Ding, Lu Cheng +3

Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to…

cs.SI2020

Combating Disinformation in a Social Media Age

Kai Shu, Amrita Bhattacharjee, Faisal Alatawi +4

The creation, dissemination, and consumption of disinformation and fabricated content on social media is a growing concern, especially with the ease of access to such sources, and…

cs.IR2021

GLOW : Global Weighted Self-Attention Network for Web Search

Xuan Shan, Chuanjie Liu, Yiqian Xia +6

Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval. When l…

cs.CL2023

GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs

Yichuan Li, Kaize Ding, Kyumin Lee

Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received incr…

cs.AI2026

LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning

Xudong Chen, Yixin Liu, Hua Wei +1

Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. Across different tasks, role…

cs.LG2024

TSI-Bench: Benchmarking Time Series Imputation

Wenjie Du, Jun Wang, Linglong Qian +12

Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the communit…

cs.LG2022

Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning

Kaize Ding, Yancheng Wang, Yingzhen Yang +1

Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive…

cs.LG2020

Feature Interaction-aware Graph Neural Networks

Kaize Ding, Yichuan Li, Jundong Li +2

Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on…

cs.LG2025

LEGO-Learn: Label-Efficient Graph Open-Set Learning

Haoyan Xu, Kay Liu, Zhengtao Yao +4

How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to addre…

cs.LG2022

Meta Propagation Networks for Graph Few-shot Semi-supervised Learning

Kaize Ding, Jianling Wang, James Caverlee +1

Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance…

cs.LG2025

Glocal Information Bottleneck for Time Series Imputation

Jie Yang, Kexin Zhang, Guibin Zhang +2

Time Series Imputation (TSI), which aims to recover missing values in temporal data, remains a fundamental challenge due to the complex and often high-rate missingness in real-worl…

cs.LG2023

Few-shot Node Classification with Extremely Weak Supervision

Song Wang, Yushun Dong, Kaize Ding +2

Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abund…

cs.LG2024

STERLING: Synergistic Representation Learning on Bipartite Graphs

Baoyu Jing, Yuchen Yan, Kaize Ding +4

A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address…

cs.CV2023

Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation

Zhangsihao Yang, Mengwei Ren, Kaize Ding +2

Pretraining CNN models (i.e., UNet) through self-supervision has become a powerful approach to facilitate medical image segmentation under low annotation regimes. Recent contrastiv…

cs.CL2024

Empowering Large Language Models for Textual Data Augmentation

Yichuan Li, Kaize Ding, Jianling Wang +1

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentatio…

cs.LG2026

Generalizing GNNs with Tokenized Mixture of Experts

Xiaoguang Guo, Zehong Wang, Jiazheng Li +5

Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that stati…

cs.LG2021

Graph Few-shot Class-incremental Learning

Zhen Tan, Kaize Ding, Ruocheng Guo +1

The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommenda…

cs.LG2022

Task-Adaptive Few-shot Node Classification

Song Wang, Kaize Ding, Chuxu Zhang +2

Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of cla…

cs.LG2020

Graph Prototypical Networks for Few-shot Learning on Attributed Networks

Kaize Ding, Jianling Wang, Jundong Li +3

Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central an…

cs.LG2026

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

Ziqing Wang, Yibo Wen, Abhishek Pandy +2

In drug discovery, molecular optimization aims to iteratively refine a lead compound to improve molecular properties while preserving structural similarity to the original molecule…

stat.ML2025

Topology-Aware Conformal Prediction for Stream Networks

Jifan Zhang, Fangxin Wang, Zihe Song +3

Stream networks, a unique class of spatiotemporal graphs, exhibit complex directional flow constraints and evolving dependencies, making uncertainty quantification a critical yet c…

cs.LG2025

Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies

Yibo Wen, Chenwei Xu, Jerry Yao-Chieh Hu +2

We present a three-stage framework for training deep learning models specializing in antibody sequence-structure co-design. We first pre-train a language model using millions of an…

cs.CL2025

Population-Aligned Persona Generation for LLM-based Social Simulation

Zhengyu Hu, Jianxun Lian, Zheyuan Xiao +7

Recent advances in large language models (LLMs) have enabled human-like social simulations at unprecedented scale and fidelity, offering new opportunities for computational social…

cs.IR2025

Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers

Haoyu Wu, Qingcheng Zeng, Kaize Ding

Dense retrievers and rerankers are central to retrieval-augmented generation (RAG) pipelines, where accurately retrieving factual information is crucial for maintaining system trus…

cs.CL2025

Synthetic Clinical Notes for Rare ICD Codes: A Data-Centric Framework for Long-Tail Medical Coding

Truong Vo, Weiyi Wu, Kaize Ding

Automatic ICD coding from clinical text is a critical task in medical NLP but remains hindered by the extreme long-tail distribution of diagnostic codes. Thousands of rare and zero…

cs.LG2025

POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization

Ziqing Wang, Yibo Wen, William Pattie +6

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similar…

cs.LG2025

Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

Zhengyu Hu, Yichuan Li, Zhengyu Chen +4

Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap…

cs.LG2025

Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization

Wenhan Wu, Zheyuan Liu, Chongyang Gao +2

Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowl…

cs.LG2022

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

Kay Liu, Yingtong Dou, Yue Zhao +12

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…

cs.LG2022

AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter

Yushun Dong, Kaize Ding, Brian Jalaian +2

Graph Neural Networks have recently become a prevailing paradigm for various high-impact graph analytical problems. Existing efforts can be mainly categorized as spectral-based and…

cs.CV2026

Predicting Immune Biomarkers with MultiModal Mixture-of-Expert Pathology Foundation Models Empowers Precision Oncology

Tianyu Liu, Ziqing Wang, Zhaokang Liang +12

Predicting immune biomarkers associated with the tumor immune microenvironment (TIME) is critical for advancing precision oncology, yet existing approaches are largely limited to s…

cs.CR2025

A Survey on Model Extraction Attacks and Defenses for Large Language Models

Kaixiang Zhao, Lincan Li, Kaize Ding +3

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comp…

cs.CR2025

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives

Kaixiang Zhao, Lincan Li, Kaize Ding +3

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and speciali…

cs.LG2023

UPREVE: An End-to-End Causal Discovery Benchmarking System

Suraj Jyothi Unni, Paras Sheth, Kaize Ding +2

Discovering causal relationships in complex socio-behavioral systems is challenging but essential for informed decision-making. We present Upload, PREprocess, Visualize, and Evalua…

cs.CL2026

Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators

Zhengyu Hu, Jieyu Zhang, Zhihan Xiong +3

Despite the remarkable success of Large Language Models (LLMs), evaluating their outputs' quality regarding preference remains a critical challenge. While existing works usually le…

cs.CL2025

AD-LLM: Benchmarking Large Language Models for Anomaly Detection

Tiankai Yang, Yi Nian, Shawn Li +9

Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. Within natural lang…

cs.CL2024

Political-LLM: Large Language Models in Political Science

Lincan Li, Jiaqi Li, Catherine Chen +44

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and mis…

cs.LG2026

From Observations to States: Latent Time Series Forecasting

Jie Yang, Yifan Hu, Yuante Li +3

Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate pr…

cs.LG2023

Learning Strong Graph Neural Networks with Weak Information

Yixin Liu, Kaize Ding, Jianling Wang +3

Graph Neural Networks (GNNs) have exhibited impressive performance in many graph learning tasks. Nevertheless, the performance of GNNs can deteriorate when the input graph data suf…

cs.LG2026

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models

Oscar Rivera, Ziqing Wang, Matthieu Dagommer +2

Machine learning accelerates molecular property prediction, yet state-of-the-art Large Language Models and Graph Neural Networks operate as black boxes. In drug discovery, where sa…

cs.LG2025

Explaining Length Bias in LLM-Based Preference Evaluations

Zhengyu Hu, Linxin Song, Jieyu Zhang +7

The use of large language models (LLMs) as judges, particularly in preference comparisons, has become widespread, but this reveals a notable bias towards longer responses, undermin…

cs.LG2025

Uncertainty-Aware Robust Learning on Noisy Graphs

Shuyi Chen, Kaize Ding, Shixiang Zhu

Graph neural networks (GNNs) have excelled in various graph learning tasks, particularly node classification. However, their performance is often hampered by noisy measurements in…

cs.CL2020

Be More with Less: Hypergraph Attention Networks for Inductive Text Classification

Kaize Ding, Jianling Wang, Jundong Li +2

Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention i…

cs.LG2024

Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization

Haohui Wang, Baoyu Jing, Kaize Ding +6

In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitig…

cs.CL2026

MedLatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis

Ziqing Wang, Lili Zhao, Kaize Ding

Rare diseases affect over million patients across more than conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis.…

cs.LG2022

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Zhen Tan, Song Wang, Kaize Ding +2

Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous at…

cs.LG2026

GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback

Ruiyao Xu, Kaize Ding

Large Language Models (LLMs) have shown strong performance on text-attributed graphs (TAGs) due to their superior semantic understanding ability on textual node features. However,…

cs.CL2025

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Mingyu Jin, Qinkai Yu, Jingyuan Huang +10

Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities rem…

cs.LG2025

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

Yili Wang, Yixin Liu, Xu Shen +6

To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD)…

cs.IR2023

HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer

Kaize Ding, Albert Jiongqian Liang, Bryan Perrozi +6

Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval. Though recent deep learning methods can parti…

cs.AI2026

MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models

Zeyu Zhang, Ziqing Wang, Kaize Ding

MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue. Existing medical QA benchmarks largely test shor…

cs.LG2025

A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation

Kexin Zhang, Shuhan Liu, Song Wang +6

Distribution shifts on graphs -- the discrepancies in data distribution between training and employing a graph machine learning model -- are ubiquitous and often unavoidable in rea…

cs.IR2021

Session-based Recommendation with Hypergraph Attention Networks

Jianling Wang, Kaize Ding, Ziwei Zhu +1

Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms. A critical challenge is to accurately model user in…

cs.CL2025

Avoiding Copyright Infringement via Large Language Model Unlearning

Guangyao Dou, Zheyuan Liu, Qing Lyu +2

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal…

cs.LG2022

Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification

Kaize Ding, Jianling Wang, Jundong Li +2

Graphs are widely used to model the relational structure of data, and the research of graph machine learning (ML) has a wide spectrum of applications ranging from drug design in mo…

cs.SI2020

Challenges in Combating COVID-19 Infodemic -- Data, Tools, and Ethics

Kaize Ding, Kai Shu, Yichuan Li +2

While the COVID-19 pandemic continues its global devastation, numerous accompanying challenges emerge. One important challenge we face is to efficiently and effectively use recentl…