22 papers
OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains
Xunkai Li, Miao Zhang, Zekai Chen +6
Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms of agent organization. Exis…
MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
Kairui Yang, Ziheng Yi, Xunkai Li +4
Collaboration topology shapes both the performance and execution cost of LLM-based multi-agent systems. Because tasks differ in complexity and required capabilities, recent approac…
MACE: Memory-Agent Co-Evolution with Adaptive Memory Graphs for Multi-Agent Systems
Kairui Yang, Minghao An, Xunkai Li +4
LLM-based multi-agent systems generate collaboration traces that record how agents plan tasks, verify intermediate results, and repair failures. Reusing these procedures requires p…
OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems
Kairui Yang, Xunkai Li, Kaixiang Zhang +4
Graph-enhanced multi-agent systems (G-MAS) coordinate large language model agents through communication graphs and role assignments, which determine how agents exchange information…
Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach
Sirui Zhang, Yubing Zhou, Xunkai Li +6
Multimodal graphs couple node attributes in different modalities, such as text and images, with relational structure, enabling topological structure and cross-modality attributes t…
LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
Xunkai Li, Zekai Chen, Zhengyu Wu +6
Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This…
MMFGU: Multimodal Federated Graph Unlearning
Haodong Lu, Zekai Chen, Weiwei Ji +5
Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However,…
FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
Zekai Chen, Haodong Lu, Shihao Li +5
Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information. As such risks evolve, clients must learn emerging class…
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
Yuze Dai, Zhihan Zhang, Yan Zhao +6
Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality iss…
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
Zekai Chen, Kairui Yang, Xuaner Chen +4
Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-cen…
Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach
Zhengyu Wu, Hongchao Qin, Xunkai Li +3
MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance…
PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Zekai Chen, Miao Zhang, Jiayang Xing +4
Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images. However, real-world clients may not share a common modali…
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
Sirui Zhang, Haonan Wang, Xunkai Li +5
Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applicat…
STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
Zekai Chen, Xun Wu, Xunkai Li +3
Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and…
OpenDDI: A Comprehensive Benchmark for DDI Prediction
Xinmo Jin, Bowen Fan, Xunkai Li +9
Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computa…
The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR
Irsyad Adam, Zekai Chen, David Laprade +5
Large language models (LLMs) trained with next-word-prediction have achieved success as clinical foundation models. Representations from these language backbones yield strong linea…
LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
Xunkai Li, Zhengyu Wu, Zekai Chen +6
Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This…
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
Zekai Chen, Haodong Lu, Xunkai Li +5
Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. With the rise of large language models (LLMs), textual attributes in FGL graphs…
BoostFGL: Boosting Fairness in Federated Graph Learning
Zekai Chen, Kairui Yang, Xunkai Li +6
Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods o…
MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
Zekai Chen, Xunkai Li, Sirui Zhang +6
De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affini…
A Comprehensive Data-centric Overview of Federated Graph Learning
Zhengyu Wu, Xunkai Li, Yinlin Zhu +8
In the era of big data applications, Federated Graph Learning (FGL) has emerged as a prominent solution that reconcile the tradeoff between optimizing the collective intelligence b…
Rethinking Client-oriented Federated Graph Learning
Zekai Chen, Xunkai Li, Yinlin Zhu +2
As a new distributed graph learning paradigm, Federated Graph Learning (FGL) facilitates collaborative model training across local systems while preserving data privacy. We review…