Research map / Graph learning / Knowledge and temporal graphs
Learning to Match on Graph for Fashion Compatibility Modeling
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 |
|---|---|---|---|
| add attentive relational propagation (replace constant-weight RGCN-ML propagation) (ablation) | RGCN-ML · Amazon-Men (V+T) | NDCG@5: 0.646 -> 0.668 | Helped |
| add attentive relational propagation (ablation) | RGCN-ML · Amazon-Women (V only) | NDCG@5: 0.502 -> 0.538 | Helped |
| add compatibility metric learning (diagonal PSD metric) to RGCN (ablation) | RGCN · Amazon-Men (V+T) | NDCG@5: 0.518 -> 0.646 | Helped |
| add compatibility metric learning to RGCN (ablation) | RGCN · Amazon-Women (V only) | NDCG@5: 0.428 -> 0.502 | Helped |
| use graph with extra-connectivities (user-item, substitute) instead of pairwise-only SiaNet (ablation) | SiaNet · Amazon-Men (V only) | NDCG@5: 0.378 -> 0.498 | Helped |
| add textual modality to visual features (ablation) | DREP · Amazon-Men | NDCG@5: 0.498 -> 0.668 | Helped |
| query items with no graph connectivity (ablation) | DREP and RGCN-ML · Amazon-Men subgroup 0 connections | NDCG@5 | Hurt |
| query items with at least some extra connectivity (ablation) | DREP and RGCN-ML · Amazon-Men subgroups | NDCG@5 | Helped |
Closest papers by meaning
- TransNFCM: Translation-Based Neural Fashion Compatibility Modeling (AAAI 2019 · similarity 0.90)
- Context-Aware Visual Compatibility Prediction (CVPR 2019 · similarity 0.89)
- Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation (AAAI 2024 · similarity 0.89)
- Compatibility Family Learning for Item Recommendation and Generation (AAAI 2018 · similarity 0.88)
- ICAR: Image-Based Complementary Auto Reasoning (AAAI 2024 · similarity 0.83)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.82)
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.