Xunkai Li
PulseAugur coverage of Xunkai Li — every cluster mentioning Xunkai Li across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New S2-DiGCL framework advances directed graph contrastive learning
Researchers have introduced S2-DiGCL, a new framework designed to enhance contrastive learning for directed graphs. Unlike previous methods that primarily focused on undirected graphs, S2-DiGCL incorporates directional …
-
New GraphMNL Framework Tackles Multimodal Graph Learning Imbalance
Researchers have introduced GraphMNL, a novel framework for multimodal graph negative learning designed to address semantic imbalance in attributed graphs. This approach uses negative learning to guide learning across d…
-
New graph condensation methods boost GNN efficiency and scalability
Two new research papers propose novel methods for graph condensation and coarsening, aiming to make Graph Neural Networks (GNNs) more efficient and scalable. The first paper, SP-ESGC, introduces a decoupled approach tha…
-
DOGMA framework weaves biological structure into single-cell transcriptomics AI
Researchers have introduced DOGMA, a novel data-centric AI framework for single-cell transcriptomics analysis. This framework integrates multi-level biological prior knowledge, moving beyond purely data-driven heuristic…