REVIEW 3 cited by
Graph Soft-Contrastive Learning via Neighborhood Ranking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Graph Contrastive Learning (GCL) has emerged as a promising approach in the realm of graph self-supervised learning. Prevailing GCL methods mainly derive from the principles of contrastive learning in the field of computer vision: modeling invariance by specifying absolutely similar pairs. However, when applied to graph data, this paradigm encounters two significant limitations: (1) the validity of the generated views cannot be guaranteed: graph perturbation may produce invalid views against semantics and intrinsic topology of graph data; (2) specifying absolutely similar pairs in the graph views is unreliable: for abstract and non-Euclidean graph data, it is difficult for humans to decide the absolute similarity and dissimilarity intuitively. Despite the notable performance of current GCL methods, these challenges necessitate a reevaluation: Could GCL be more effectively tailored to the intrinsic properties of graphs, rather than merely adopting principles from computer vision? In response to this query, we propose a novel paradigm, Graph Soft-Contrastive Learning (GSCL). This approach facilitates GCL via neighborhood ranking, avoiding the need to specify absolutely similar pairs. GSCL leverages the underlying graph characteristic of diminishing label consistency, asserting that nodes that are closer in the graph are overall more similar than far-distant nodes. Within the GSCL framework, we introduce pairwise and listwise gated ranking InfoNCE loss functions to effectively preserve the relative similarity ranking within neighborhoods. Moreover, as the neighborhood size exponentially expands with more hops considered, we propose neighborhood sampling strategies to improve learning efficiency. Our extensive empirical results across 11 commonly used graph datasets-including 8 homophily graphs and 3 heterophily graphs-demonstrate GSCL's superior performance compared to 20 SOTA GCL methods.
Forward citations
Cited by 3 Pith papers
-
Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning
DiMNet combines multi-span cross-time message passing with disentangled active/stable node factors to set new state-of-the-art MRR on four TKG extrapolation benchmarks.
-
Soft Graph Clustering for single-cell RNA Sequencing Data
A soft graph clustering framework combining ZINB autoencoding, joint normalized-cut embeddings, and optimal transport outperforms prior methods on ten scRNA-seq benchmarks.
-
Distilling Closed-Source LLM's Knowledge for Locally Stable and Economic Biomedical Entity Linking
A closed-source LLM's re-ranking labels are distilled into a locally deployable open-source LLM, producing small but consistent Acc@1 gains in low-resource biomedical entity linking on two datasets.
Discussion (0). Continue with ORCID to comment.