Link Prediction with Persistent Homology: An Interactive View
Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.
Code (1)
Tasks
Graph LearningGraph Neural NetworkLink PredictionPredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Weighted persistent homology for osmolyte molecular aggregation and hydrogen-bonding network analysis
It has long been observed that trimethylamin N-oxide (TMAO) and urea demonstrate dramatically different properties in a protein folding process. Even with the enormous theoretical and experimental research work of the tw…
Protein FoldingPHLP: Sole Persistent Homology for Link Prediction - Interpretable Feature Extraction
Link prediction (LP), inferring the connectivity between nodes, is a significant research area in graph data, where a link represents essential information on relationships between nodes. Although graph neural network (G…
Graph Neural NetworkLink PredictionTopological Data AnalysisHomology-constrained vector quantization entropy regularizer
This paper describes an entropy regularization term for vector quantization (VQ) based on the analysis of persistent homology of the VQ embeddings. Higher embedding entropy positively correlates with higher codebook util…
QuantizationA higher homotopic extension of persistent (co)homology
Our objective in this article is to show a possibly interesting structure of homotopic nature appearing in persistent (co)homology. Assuming that the filtration of the (say) simplicial set embedded in a finite dimensiona…
Topological Data AnalysisAdversary Detection in Neural Networks via Persistent Homology
We outline a detection method for adversarial inputs to deep neural networks. By viewing neural network computations as graphs upon which information flows from input space to out- put distribution, we compare the differ…