4 papers
CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation
Tong Qi, Jingyu Wu, Youbing Yin +3
Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectiv…
DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering
Guanqun Yang, Tong Qi, Xiaoxue Han
Real-world recommendation platforms routinely collect explicit negative feedback such as 1-star reviews, hate-button clicks, distrust between users, and very-low watch-ratio videos…
Asymptotically perfect seeded graph matching without edge correlation (and applications to inference)
Tong Qi, Vera Andersson, Peter Viechnicki +1
We present the OmniMatch algorithm for seeded multiple graph matching. In the setting of -dimensional Random Dot Product Graphs (RDPG), we prove that under mild assumptions, Omn…
Detection of Model-based Planted Pseudo-cliques in Random Dot Product Graphs by the Adjacency Spectral Embedding and the Graph Encoder Embedding
Tong Qi, Vince Lyzinski
In this paper, we explore the capability of both the Adjacency Spectral Embedding (ASE) and the Graph Encoder Embedding (GEE) for capturing an embedded pseudo-clique structure in t…