mlsanityData to 7 Oct 2026

SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Network

arXiv 2405.01927 ↗First posted 3 May 2024cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graphs are ubiquitous to model complex data. There are urgent needs on powerful heterogeneous graph neural networks to effectively support important applications. We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neighbors of a node v are forced to be transformed to the feature space of v for aggregation, though the neighbors are in different types. That is, the semantics in different node types are entangled together into node v's representation. To address the issue, we propose SlotGAT with separate message passing processes in slots, one for each node type, to maintain the representations in their own node-type feature spaces. Moreover, in a slot-based message passing layer, we design an attention mechanism for effective slot-wise message aggregation. Further, we develop a slot attention technique after the last layer of SlotGAT, to learn the importance of different slots in downstream tasks. Our analysis indicates that the slots in SlotGAT can preserve different semantics in various feature spaces. The superiority of SlotGAT is evaluated against 13 baselines on 6 datasets for node classification and link prediction. Our code is at https://github.com/scottjiao/SlotGATICML23/.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

29 of 44 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  10. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  11. 2020Simple and Deep Graph Convolutional Networkscited by 857
  12. 2019Heterogeneous Graph Attention Networkcited by 732
17 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 711
  2. 2020Heterogeneous Graph Transformercited by 581
  3. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  4. 2019Graph Transformer Networkscited by 520
  5. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  6. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 342
  7. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  8. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  9. 2020Towards Deeper Graph Neural Networkscited by 296
  10. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  11. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  12. 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
  13. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  14. 2019Representation Learning for Attributed Multiplex Heterogeneous Networkcited by 91
  15. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  16. 2021DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendationcited by 28
  17. 2022Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Networkcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 1.

11 papers.

  1. 2024Road Network Representation Learning with the Third Law of Geographycited by 10
  2. 2024Heterogeneous Sheaf Neural Networkscited by 10
  3. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  4. 2025GLProtein: Global-and-Local Structure Aware Protein Representation Learningcited by 5
  5. 2024TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillationcited by 4
  6. 2025Simple yet Effective Graph Distillation via Clusteringcited by 4
  7. 2025GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphscited by 3
  8. 2024Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approachcited by 2
  9. 2025Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspectivecited by 0
  10. 2025Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorizationcited by 0
  11. 2026BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materialscited by 0