16 papers
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…
CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
Daohan Su, Hao Liu, Xunkai Li +6
Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectu…
Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
Sicheng Liu, Xunkai Li, Daohan Su +4
Graph Foundation Models (GFMs) have achieved remarkable success in generalizing across diverse domains. However, they mainly focus on Text-Attributed Graphs (TAGs), leaving Multimo…
SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation
Chao Chen, Longfei Xu, Daohan Su +5
Route recommendation systems commonly adopt a multi-stage pipeline involving fine-ranking and re-ranking to produce high-quality ordered recommendations. However, this paradigm fac…
DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
Ru Zhang, Xunkai Li, Yaxin Deng +7
Recently, data-centric AI methodology has been a dominant paradigm in single-cell transcriptomics analysis, which treats data representation rather than model complexity as the fun…
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…
Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
Zhengyu Wu, Daohan Su, Yang Zhang +3
Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information. However, existing methods…
Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Xunkai Li, Daohan Su, Sicheng Liu +5
Inspired by the success of LLMs, GFMs are designed to learn the optimal embedding functions from multi-domain text-attributed graphs for the downstream cross-task generalization ca…
Towards Unbiased Federated Graph Learning: Label and Topology Perspectives
Zhengyu Wu, Boyang Pang, Xunkai Li +6
Federated Graph Learning (FGL) enables privacy-preserving, distributed training of graph neural networks without sharing raw data. Among its approaches, subgraph-FL has become the…
Toward Effective Digraph Representation Learning: A Magnetic Adaptive Propagation based Approach
Xunkai Li, Daohan Su, Zhengyu Wu +4
The -parameterized magnetic Laplacian serves as the foundation of directed graph (digraph) convolution, enabling this kind of digraph neural network (MagDG) to encode node featu…
Knowledge-Driven Federated Graph Learning on Model Heterogeneity
Zhengyu Wu, Guang Zeng, Huilin Lai +7
Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preservi…
Towards Data-centric Machine Learning on Directed Graphs: a Survey
Henan Sun, Xunkai Li, Daohan Su +3
In recent years, Graph Neural Networks (GNNs) have made significant advances in processing structured data. However, most of them primarily adopted a model-centric approach, which…
DiRW: Path-Aware Digraph Learning for Heterophily
Daohan Su, Xunkai Li, Zhenjun Li +3
Recently, graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data. However, most approaches are tailored for undirected graphs,…
LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
Xunkai Li, Meihao Liao, Zhengyu Wu +4
Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and…
Rethinking Node-wise Propagation for Large-scale Graph Learning
Xunkai Li, Jingyuan Ma, Zhengyu Wu +4
Scalable graph neural networks (GNNs) have emerged as a promising technique, which exhibits superior predictive performance and high running efficiency across numerous large-scale…
Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification
Henan Sun, Xunkai Li, Zhengyu Wu +3
Recently, graph neural networks (GNNs) have shown prominent performance in semi-supervised node classification by leveraging knowledge from the graph database. However, most existi…