mlsanityData to 7 Oct 2026

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

arXiv 2109.12872 ↗First posted 27 Sep 2021cs.CV cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs). We begin by developing a vanilla 1-bit GNN framework that binarizes both the GNN parameters and the graph features. Despite the lightweight architecture, we observed that this vanilla framework suffered from insufficient discriminative power in distinguishing graph topologies, leading to a dramatic drop in performance. This discovery motivates us to devise meta aggregators to improve the expressive power of vanilla binarized GNNs, of which the aggregation schemes can be adaptively changed in a learnable manner based on the binarized features. Towards this end, we propose two dedicated forms of meta neighborhood aggregators, an exclusive meta aggregator termed as Greedy Gumbel Neighborhood Aggregator (GNA), and a diffused meta aggregator termed as Adaptable Hybrid Neighborhood Aggregator (ANA). GNA learns to exclusively pick one single optimal aggregator from a pool of candidates, while ANA learns a hybrid aggregation behavior to simultaneously retain the benefits of several individual aggregators. Furthermore, the proposed meta aggregators may readily serve as a generic plugin module into existing full-precision GNNs. Experiments across various domains demonstrate that the proposed method yields results superior to the state of the art.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 56 of its 68 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

56 of 68 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  12. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
38 more
  1. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  4. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  6. 2020Benchmarking Graph Neural Networkscited by 672
  7. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  11. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  12. 2017Residual Gated Graph ConvNetscited by 341
  13. 2017Relation Networks for Object Detectioncited by 305
  14. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  15. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 249
  16. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  17. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  18. 2020Binary Neural Networks: A Surveycited by 184
  19. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  20. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  21. 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
  22. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  23. 2014A* Samplingcited by 150
  24. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  25. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  26. 2020Distilling Knowledge from Graph Convolutional Networkscited by 128
  27. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  28. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  29. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  30. 2019XNOR-Net++: Improved Binary Neural Networkscited by 94
  31. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 93
  32. 2019AdderNet: Do We Really Need Multiplications in Deep Learning?cited by 82
  33. 2020Factorizable Graph Convolutional Networkscited by 79
  34. 2018Amalgamating Knowledge towards Comprehensive Classificationcited by 38
  35. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  36. 2020Binary Graph Neural Networkscited by 32
  37. 2016Bitwise Neural Networkscited by 29
  38. 2021SPAGAN: Shortest Path Graph Attention Networkcited by 28

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 13; 2024: 4; 2025: 4; 2026: 2.

24 papers.

Sort:

By area:

  1. 2023DepGraph: Towards Any Structural Pruningcited by 202
  2. 2022Learning Graph Neural Networks for Image Style Transfercited by 29
  3. 2023Deep Graph Reprogrammingcited by 22
  4. 2025Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAGcited by 22
  5. 2023SlimSAM: 0.1% Data Makes Segment Anything Slimcited by 20
  6. 2023Segment Anything in Non-Euclidean Domains: Challenges and Opportunitiescited by 16
  7. 2023Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detectioncited by 13
  8. 2023Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalizationcited by 12
  9. 2023Lookaround Optimizer: k steps around, 1 step averagecited by 9
  10. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
  11. 2023Partial Network Cloningcited by 6
  12. 2023BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUscited by 4
12 more
  1. 2023rm A2Q: Aggregation-Aware Quantization for Graph Neural Networkscited by 3
  2. 2023Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradientscited by 3
  3. 2024ONNXPruner: ONNX-Based General Model Pruning Adaptercited by 3
  4. 2025GraphBridge: Towards Arbitrary Transfer Learning in GNNscited by 3
  5. 2025Efficient Mixed Precision Quantization in Graph Neural Networkscited by 3
  6. 2024Offline Behavior Distillationcited by 2
  7. 2023Schema Inference for Interpretable Image Classificationcited by 1
  8. 2023Message-passing selection: Towards interpretable GNNs for graph classificationcited by 1
  9. 2024Successive Refinement in Large-Scale Computation: Advancing Model Inference Applicationscited by 0
  10. 2024Acceleration Algorithms in GNNs: A Surveycited by 0
  11. 2026Towards High-Resolution Visual Perception via Hierarchical Entity Explorationcited by 0
  12. 2026TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Informationcited by 0