14 papers
ARM: Attention with Routed-Memory for Learnable Sparse Control
Qiuhao Zeng, Jerry Huang, Peng Lu +7
Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computa…
Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transport
Xiangyu Wang, Shuo Wang, Ruiyi Fang +1
Graph prompt learning enables parameter-efficient adaptation of frozen Graph Neural Networks to downstream tasks through lightweight prompt parameters. As routing becomes increasin…
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
Quanxin Wang, Xuanting Xie, Bingheng Li +4
Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, existing methods operate within a…
Full spectrum Unlearnable Examples via Spectral Equalization
Jiale Cai, Gezheng Xu, Zhihao Li +6
Unlearnable examples (UEs) protect training data by injecting imperceptible perturbations so that models fail to extract exploitable representations. In this paper, we reveal that…
The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning
Shuo Wang, Xiangyu Wang, Quanxin Wang +9
Current evaluation practices in relational learning rely heavily on flat leaderboards that average performance across heterogeneous datasets, implicitly assuming a uniform underlyi…
Structure-Centric Graph Foundation Model via Geometric Bases
Xiaodong He, Haolan He, Ruiyi Fang +2
Graph foundation models (GFMs) seek transferable representations across graph domains but are limited by structural heterogeneity and incompatible node feature spaces. We propose S…
When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining
Zhihao Li, Gezheng Xu, Jiale Cai +5
Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlyin…
Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
Zihao Jing, Qiuhao Zeng, Ruiyi Fang +3
Molecular understanding is central to advancing areas such as scientific discovery, yet Large Language Models (LLMs) struggle to understand molecular graphs effectively. Existing g…
Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structure
Ruiyi Fang, Shuo Wang, Ruizhi Pu +8
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. However, existing GDA methods t…
Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
Zihao Jing, Qiuhao Zeng, Ruiyi Fang +4
Large language models (LLMs) are enabling reasoning over 2D and 3D structures, yet existing methods remain modality-specific and typically compress structural inputs through sequen…
Homophily Enhanced Graph Domain Adaptation
Ruiyi Fang, Bingheng Li, Jingyu Zhao +5
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the…
On the Benefits of Attribute-Driven Graph Domain Adaptation
Ruiyi Fang, Bingheng Li, Zhao Kang +5
Graph Domain Adaptation (GDA) addresses a pressing challenge in cross-network learning, particularly pertinent due to the absence of labeled data in real-world graph datasets. Rece…
Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression
Ruizhi Pu, Gezheng Xu, Ruiyi Fang +3
Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning…
Simplified PCNet with Robustness
Bingheng Li, Xuanting Xie, Haoxiang Lei +2
Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs. However, they cannot general…