5 papers
Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells
Mattie Ji, Indradyumna Roy, Vikas Garg
Persistent homology (PH) encodes global information, such as cycles, and is thus increasingly integrated into graph neural networks (GNNs). PH methods in GNNs typically traverse an…
Contextual Tokenization for Graph Inverted Indices
Pritish Chakraborty, Indradyumna Roy, Soumen Chakrabarti +1
Retrieving graphs from a large corpus, that contain a subgraph isomorphic to a given query graph, is a core operation in many real-world applications. While recent multi-vector gra…
Charting the Design Space of Neural Graph Representations for Subgraph Matching
Vaibhav Raj, Indradyumna Roy, Ashwin Ramachandran +2
Subgraph matching is vital in knowledge graph (KG) question answering, molecule design, scene graph, code and circuit search, etc. Neural methods have shown promising results for s…
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
Ashwin Ramachandran, Vaibhav Raj, Indrayumna Roy +2
Graph retrieval based on subgraph isomorphism has several real-world applications such as scene graph retrieval, molecular fingerprint detection and circuit design. Roy et al. [35]…
Graph Edit Distance with General Costs Using Neural Set Divergence
Eeshaan Jain, Indradyumna Roy, Saswat Meher +2
Graph Edit Distance (GED) measures the (dis-)similarity between two given graphs, in terms of the minimum-cost edit sequence that transforms one graph to the other. However, the ex…