AI Paper Atlas

Research map / Graph learning / GNN architectures

SlotGAT: Slot-based Message Passing for Heterogeneous Graphs

Ziang Zhou, Jieming Shi, Renchi Yang, Yuanhang Zou, Qing Li

ICML 2023 · Graph learning › GNN architectures · approach: Expressive equivariant message passing

Read the paper

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 changedWhereMeasuredEffect
slot-based message passing with slot attention (SlotGAT) vs. baselinesheterogeneous GNN node classification and link prediction · DBLP, IMDB, ACM, PubMed NC, Freebase, LastFM, PubMed LPMicro-F1 / Macro-F1 / ROC-AUC / MRRImproved
replace slot attention with simple averaging of slot representations (ablation)SlotGAT · DBLP, IMDB, ACM, PubMed NCMicro-F1: e.g., DBLP 95.31 to 94.93; IMDB 68.54 to 67.56Hurt
use only the target-type slot instead of slot attention (ablation)SlotGAT · DBLP, IMDBMicro-F1: DBLP 95.31 to 87.73; IMDB 68.54 to 48.91Hurt
replace slot attention with non-biased fully connected layer (ablation)SlotGAT · DBLP, IMDB, ACM, PubMed NC, FreebaseMicro-F1: comparable; e.g., DBLP 95.31 vs 95.11, IMDB 68.54 vs 68.16No clear effect
slot-based message passing (separate slots per node type) vs. single-representation message passing with type transformationSlotGAT · node classification and link predictiontraining time per epoch / memory: e.g., DBLP training 76.21 ms (simpleHGN) vs 230.61 ms; peak memory 13.37 GB on PubMed NCHurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy