3 papers
cs.LG2026
Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
Ziwen Zhao, Menglin Yang
Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at…
cs.LG2025
A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
Ziwen Zhao, Yixin Su, Yuhua Li +3
Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data…
cs.LG2024
Masked Graph Autoencoder with Non-discrete Bandwidths
Ziwen Zhao, Yuhua Li, Yixiong Zou +2
Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete ed…