Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Graph representation learning
Graph learning studies neural networks on relational data: message-passing networks and graph transformers for node, edge and graph prediction, their expressivity and long-range behaviour, link prediction and knowledge-graph completion, and learned heuristics for combinatorial problems on graphs. Evaluation relies on shared benchmark suites with fixed splits (OGB, LRGB, TUDataset, heterophilous graphs); because differences between models are often smaller than tuning and seed effects, credible work reports many seeds and re-tunes classic GNN baselines.