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

arXiv: https://arxiv.org/abs/2109.12872 · HTML: https://mlsanity.com/paper/2109.12872/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 68 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 30 of 56)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Residual Gated Graph ConvNets](https://mlsanity.com/paper/1711.07553/) (2017)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Revisiting Graph Neural Networks: All We Have is Low-Pass Filters](https://mlsanity.com/paper/1905.09550/) (2019)
- [DeeperGCN: All You Need to Train Deeper GCNs](https://mlsanity.com/paper/2006.07739/) (2020)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)

## Built on by (most cited first, 25 of 25)

- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Learning Graph Neural Networks for Image Style Transfer](https://mlsanity.com/paper/2207.11681/) (2022)
- [Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG](https://mlsanity.com/paper/2503.01222/) (2025)
- [Deep Graph Reprogramming](https://mlsanity.com/paper/2304.14593/) (2023)
- [SlimSAM: 0.1% Data Makes Segment Anything Slim](https://mlsanity.com/paper/2312.05284/) (2023)
- [Segment Anything in Non-Euclidean Domains: Challenges and Opportunities](https://mlsanity.com/paper/2304.11595/) (2023)
- [Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection](https://mlsanity.com/paper/2307.13529/) (2023)
- [Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization](https://mlsanity.com/paper/2305.19903/) (2023)
- [Lookaround Optimizer: k steps around, 1 step average](https://mlsanity.com/paper/2306.07684/) (2023)
- [Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning](https://mlsanity.com/paper/2503.01642/) (2025)
- [Partial Network Cloning](https://mlsanity.com/paper/2303.10597/) (2023)
- [BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs](https://mlsanity.com/paper/2305.02522/) (2023)
- [MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization](https://mlsanity.com/paper/2311.09775/) (2023)
- [GraphBridge: Towards Arbitrary Transfer Learning in GNNs](https://mlsanity.com/paper/2502.19252/) (2025)
- [rm A2Q: Aggregation-Aware Quantization for Graph Neural Networks](https://mlsanity.com/paper/2302.00193/) (2023)
- [Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients](https://mlsanity.com/paper/2310.15128/) (2023)
- [ONNXPruner: ONNX-Based General Model Pruning Adapter](https://mlsanity.com/paper/2404.08016/) (2024)
- [Efficient Mixed Precision Quantization in Graph Neural Networks](https://mlsanity.com/paper/2505.09361/) (2025)
- [Offline Behavior Distillation](https://mlsanity.com/paper/2410.22728/) (2024)
- [Schema Inference for Interpretable Image Classification](https://mlsanity.com/paper/2303.06635/) (2023)
- [Message-passing selection: Towards interpretable GNNs for graph classification](https://mlsanity.com/paper/2306.02081/) (2023)
- [Successive Refinement in Large-Scale Computation: Advancing Model Inference Applications](https://mlsanity.com/paper/2402.07229/) (2024)
- [Acceleration Algorithms in GNNs: A Survey](https://mlsanity.com/paper/2405.04114/) (2024)
- [Towards High-Resolution Visual Perception via Hierarchical Entity Exploration](https://mlsanity.com/paper/2607.00816/) (2026)
- [TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information](https://mlsanity.com/paper/2608.30394/) (2026)

## 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.