Research map / Graph learning / GNN architectures
SlotGAT: Slot-based Message Passing for Heterogeneous Graphs
Ziang Zhou, Jieming Shi, Renchi Yang, Yuanhang Zou, Qing Li
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| slot-based message passing with slot attention (SlotGAT) vs. baselines | heterogeneous GNN node classification and link prediction · DBLP, IMDB, ACM, PubMed NC, Freebase, LastFM, PubMed LP | Micro-F1 / Macro-F1 / ROC-AUC / MRR | Improved |
| replace slot attention with simple averaging of slot representations (ablation) | SlotGAT · DBLP, IMDB, ACM, PubMed NC | Micro-F1: e.g., DBLP 95.31 to 94.93; IMDB 68.54 to 67.56 | Hurt |
| use only the target-type slot instead of slot attention (ablation) | SlotGAT · DBLP, IMDB | Micro-F1: DBLP 95.31 to 87.73; IMDB 68.54 to 48.91 | Hurt |
| replace slot attention with non-biased fully connected layer (ablation) | SlotGAT · DBLP, IMDB, ACM, PubMed NC, Freebase | Micro-F1: comparable; e.g., DBLP 95.31 vs 95.11, IMDB 68.54 vs 68.16 | No clear effect |
| slot-based message passing (separate slots per node type) vs. single-representation message passing with type transformation | SlotGAT · node classification and link prediction | training time per epoch / memory: e.g., DBLP training 76.21 ms (simpleHGN) vs 230.61 ms; peak memory 13.37 GB on PubMed NC | Hurt |
Later papers that compared with this method
3 later accepted papers report SlotGAT as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Atomic HINs: Entity-Attribute Duality for Heterogeneous Graph Modeling (ICLR 2026 · better on 3 of 3 shared results)
- NoiseHGNN: Synthesized Similarity Graph-Based Neural Network for Noised Heterogeneous Graph Representation Learning (AAAI 2025 · better on 5 of 7 shared results)
- Long-range Meta-path Search on Large-scale Heterogeneous Graphs (NeurIPS 2024 · better on 4 of 5 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks (NeurIPS 2024 · similarity 0.85)
- On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks (NeurIPS 2024 · similarity 0.85)
- Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs (ICML 2024 · similarity 0.85)
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.85)
- Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing (ICML 2024 · similarity 0.85)
- Towards Dynamic Message Passing on Graphs (NeurIPS 2024 · similarity 0.84)
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.
