mlsanityData to 7 Oct 2026

Learning Conjoint Attentions for Graph Neural Nets

arXiv 2102.03147 ↗First posted 5 Feb 2021cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). Besides considering the layer-wise node features propagated within the GNN, CAs can additionally incorporate various structural interventions, such as node cluster embedding, and higher-order structural correlations that can be learned outside of GNN, when computing attention scores. The node features that are regarded as significant by the conjoint criteria are therefore more likely to be propagated in the GNN. Given the novel Conjoint Attention strategies, we then propose Graph conjoint attention networks (CATs) that can learn representations embedded with significant latent features deemed by the Conjoint Attentions. Besides, we theoretically validate the discriminative capacity of CATs. CATs utilizing the proposed Conjoint Attention strategies have been extensively tested in well-established benchmarking datasets and comprehensively compared with state-of-the-art baselines. The obtained notable performance demonstrates the effectiveness of the proposed Conjoint Attentions.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

38 of 61 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  10. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  11. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  12. 2019Simplifying Graph Convolutional Networkscited by 1,470
26 more
  1. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  2. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  3. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  4. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  5. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  7. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  8. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  9. 2020Benchmarking Graph Neural Networkscited by 672
  10. 2015LINE: Large-scale Information Network Embeddingcited by 582
  11. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  12. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  13. 2019Diffusion Improves Graph Learningcited by 414
  14. 2016Learning Convolutional Neural Networks for Graphscited by 314
  15. 2015Diffusion-Convolutional Neural Networkscited by 268
  16. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  17. 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
  18. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  19. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  20. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  21. 2013A Survey on Multi-view Learningcited by 152
  22. 2018Hyperbolic Attention Networkscited by 122
  23. 2019Session-based Social Recommendation via Dynamic Graph Attention Networkscited by 76
  24. 2019Improving Graph Attention Networks with Large Margin-based Constraintscited by 34
  25. 2019Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservationcited by 17
  26. 2020PushNet: Efficient and Adaptive Neural Message Passingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 3; 2024: 8; 2025: 6; 2026: 2.

26 papers.

Sort:

  1. 2022A Survey on Graph Representation Learning Methodscited by 66
  2. 2023Towards Deep Attention in Graph Neural Networks: Problems and Remediescited by 24
  3. 2022Improving Graph Neural Networks with Learnable Propagation Operatorscited by 19
  4. 2023Causality and Independence Enhancement for Biased Node Classificationcited by 13
  5. 2024Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learningcited by 9
  6. 2026A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysiscited by 9
  7. 2024Tensor Graph Convolutional Network for Dynamic Graph Representation Learningcited by 8
  8. 2022Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learningcited by 6
  9. 2022Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregatorscited by 3
  10. 2022Spiking GATs: Learning Graph Attentions via Spiking Neural Networkcited by 3
  11. 2024Graph Triple Attention Network: A Decoupled Perspectivecited by 2
  12. 2025Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learningcited by 2
14 more
  1. 2022A Bird's-Eye Tutorial of Graph Attention Architecturescited by 1
  2. 2024Neighbor Overlay-Induced Graph Attention Networkcited by 1
  3. 2026Attention-based graph neural networks: a surveycited by 1
  4. 2021Customizing Graph Neural Networks using Path Reweightingcited by 0
  5. 2023A Unified Framework for Exploratory Learning-Aided Community Detection Under Topological Uncertaintycited by 0
  6. 2024IENE: Identifying and Extrapolating the Node Environment for Out-of-Distribution Generalization on Graphscited by 0
  7. 2024Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learningcited by 0
  8. 2024Graph Clustering with Cross-View Feature Propagationcited by 0
  9. 2024A Novel Spatiotemporal Coupling Graph Convolutional Networkcited by 0
  10. 2025High-order Graph Neural Networks with Common Neighbor Awareness for Link Predictioncited by 0
  11. 2025A Conjoint Graph Representation Learning Framework for Hypertension Comorbidity Risk Predictioncited by 0
  12. 2025Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learningcited by 0
  13. 2025Causal Heterogeneous Graph Learning Method for Chronic Obstructive Pulmonary Disease Predictioncited by 0
  14. 2025A Novel Graph-Sequence Learning Model for Inductive Text Classificationcited by 0