17 papers
MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
Junlin Chen, Wenhao Wang, Junchao Xu +5
Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental graph learning, predictions ar…
MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning
Junlin Chen, Yuhan Wang, Xuefei Wang +3
Graph few-shot class-incremental learning (GFSCIL) requires a model to continually recognize emerging classes from only a few labeled nodes while preserving previously acquired kno…
LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
Di Zhang, Jingyang Zhang, Ziqian Wang +4
Large language models (LLMs) have shown promise for spatio-temporal forecasting, but existing approaches often rely on regularly sampled token sequences and struggle with irregular…
Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does
Junlin Chen, Ruijie Wang, Jianxin Li
Reinforcement-learning models commonly predict complete future states, observations, or feature occupancies, even though action selection depends only on differences between the co…
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
Xuefei Wang, Jun Han, Zixuan Wang +4
Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-domain interactions. Existin…
AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration
Bing Hao, Ruijie Wang, Haodong Qian +5
Large Language Models (LLMs) demonstrate remarkable potential in dynamic graph reasoning, but suffer from a scaling bottleneck: current models can only handle graphs with tens of n…
G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
Yuhan Wang, Yibo Ding, Yutong Ye +4
LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style co…
S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs
Yuhan Wang, Haopeng Zhang, Yibo Ding +6
Pre-training on text-attributed graphs (TAGs) is central to building transferable graph foundation models, where LLM-as-Aligner methods align graph and text representations through…
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
Xuefei Wang, Jialu Wang, Fengbo Zhang +6
Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the under…
LIVE: Learnable Monotonic Vertex Embedding for Efficient Exact Subgraph Matching (Technical Report)
Yutong Ye, Weilong Ren, Yang Liu +5
Exact subgraph matching is a fundamental graph operator that supports many graph analytics tasks, yet it remains computationally challenging due to its NP-completeness. Recent lear…
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
Yunlong Chu, Minglai Shao, Yuhang Liu +4
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approache…
RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
Yuhang Liu, Ruijie Wang, Yunlong Chu +4
Large Language Models (LLMs) excel at multi-step reasoning, yet increasing the structural complexity of inference does not consistently improve system-level returns. Methods such a…
AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
Jiaqi Yuan, Jialu Wang, Zihan Wang +3
Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from rankin…
SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
Chenzhi Hu, Qinzhe Hu, Yuhang Xu +6
Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. However, the inherent v…
LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs
Bing Hao, Minglai Shao, Zengyi Wo +3
The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs. Temporal motifs, as an elementary unit…
Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization
Yunlong Chu, Minglai Shao, Zengyi Wo +4
Graph Neural Networks (GNNs) face a fundamental adaptability challenge: their fixed message-passing architectures struggle with the immense diversity of real-world graphs, where op…
Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment
Yuhang Liu, Minglai Shao, Zengyi Wo +5
Pre-training Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) is central to web-scale applications such as search, recommendation, and knowledge discovery. However,…