Research map / Graph learning / Knowledge and temporal graphs
Session-Based Recommendation with Graph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| model session sequences as graphs with gated graph neural networks | SR-GNN · Yoochoose 1/64, Yoochoose 1/4, and Diginetica | P@20 and MRR@20 | Helped |
| replace session-specific connections with normalized global connections (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Hurt |
| add explicit direct connections for all higher-order item relationships (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Hurt |
| use local embedding only instead of the hybrid local-global session embedding (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Hurt |
| use average pooling for the global embedding instead of attention (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Hurt |
| use attention-based global embedding only instead of the hybrid embedding (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Hurt |
| combine current local interest with global session preference (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Helped |
| use attention to weight items in the global session embedding rather than average pooling (ablation) | SR-GNN · Yoochoose and Diginetica | recommendation performance | Helped |
Closest papers by meaning
- LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.91)
- Dynamic Multi-Interest Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.89)
- Mind Individual Information! Principal Graph Learning for Multimedia Recommendation (AAAI 2025 · similarity 0.88)
- Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation (AAAI 2025 · similarity 0.86)
- ContextGNN: Beyond Two-Tower Recommendation Systems (ICLR 2025 · similarity 0.86)
- Ready for You When You Are Back: Content-Driven Session-Based Recommendation for Continuity of Experience (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.