# AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2007.02265 · HTML: https://mlsanity.com/paper/2007.02265/

## Key facts

- Cited by 121 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2020.

## Built on by (most cited first, 30 of 121)

- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration](https://mlsanity.com/paper/2109.14285/) (2021)
- [GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily](https://mlsanity.com/paper/2110.15777/) (2021)
- [Mining Latent Structures for Multimedia Recommendation](https://mlsanity.com/paper/2104.09036/) (2021)
- [How Framelets Enhance Graph Neural Networks](https://mlsanity.com/paper/2102.06986/) (2021)
- [Single Node Injection Attack against Graph Neural Networks](https://mlsanity.com/paper/2108.13049/) (2021)
- [Attention-driven Graph Clustering Network](https://mlsanity.com/paper/2108.05499/) (2021)
- [DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering](https://mlsanity.com/paper/2107.04768/) (2021)
- [Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection](https://mlsanity.com/paper/2204.11582/) (2022)
- [SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization](https://mlsanity.com/paper/2303.09778/) (2023)
- [Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN](https://mlsanity.com/paper/2207.00012/) (2022)
- [T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation](https://mlsanity.com/paper/2212.12738/) (2022)
- [Spiking Graph Convolutional Networks](https://mlsanity.com/paper/2205.02767/) (2022)
- [Multiplex Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2208.06129/) (2022)
- [The Expressive Power of Graph Neural Networks: A Survey](https://mlsanity.com/paper/2308.08235/) (2023)
- [Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation](https://mlsanity.com/paper/2205.13954/) (2022)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Self-Supervised Graph Structure Refinement for Graph Neural Networks](https://mlsanity.com/paper/2211.06545/) (2022)
- [On the Benefits of Attribute-Driven Graph Domain Adaptation](https://mlsanity.com/paper/2502.06808/) (2025)
- [Jointly Attacking Graph Neural Network and its Explanations](https://mlsanity.com/paper/2108.03388/) (2021)
- [Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation](https://mlsanity.com/paper/2111.00678/) (2021)
- [Structure-Preserving Graph Representation Learning](https://mlsanity.com/paper/2209.00793/) (2022)
- [Self-supervised Consensus Representation Learning for Attributed Graph](https://mlsanity.com/paper/2108.04822/) (2021)
- [Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily](https://mlsanity.com/paper/2112.13562/) (2021)
- [Deep Graph Learning for Anomalous Citation Detection](https://mlsanity.com/paper/2202.11360/) (2022)
- [Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily](https://mlsanity.com/paper/2203.10280/) (2022)
- [GraphFM: Graph Factorization Machines for Feature Interaction Modeling](https://mlsanity.com/paper/2105.11866/) (2021)
- [Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning](https://mlsanity.com/paper/2211.09155/) (2022)
- [The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection](https://mlsanity.com/paper/2210.12384/) (2022)

## Abstract (arXiv)

Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytics tasks on graph and network data. However, some recent studies raise concerns about whether GCNs can optimally integrate node features and topological structures in a complex graph with rich information. In this paper, we first present an experimental investigation. Surprisingly, our experimental results clearly show that the capability of the state-of-the-art GCNs in fusing node features and topological structures is distant from optimal or even satisfactory. The weakness may severely hinder the capability of GCNs in some classification tasks, since GCNs may not be able to adaptively learn some deep correlation information between topological structures and node features. Can we remedy the weakness and design a new type of GCNs that can retain the advantages of the state-of-the-art GCNs and, at the same time, enhance the capability of fusing topological structures and node features substantially? We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN). The central idea is that we extract the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embeddings. Our extensive experiments on benchmark data sets clearly show that AM-GCN extracts the most correlated information from both node features and topological structures substantially, and improves the classification accuracy with a clear margin.