Factorizable Graph Convolutional Networks

By Yiding Yang, Zunlei Feng, Mingli Song, Xinchao Wang. 2020

172 citations recorded by the source corpus.

Graphs have been widely adopted to denote structural connections between entities. The relations are in many cases heterogeneous, but entangled together and denoted merely as a single edge between a pair of nodes. For example, in a social network graph, users in different latent relationships like friends and colleagues, are usually connected via a bare edge that conceals such intrinsic connections. In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network(FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs, each of which represents a latent and disentangled relation among nodes. The features of the nodes are then aggregated separately in each factorized latent space to produce disentangled features, which further leads to better performances for downstream tasks. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets, and demonstrate that it yields truly encouraging results in terms of both disentangling and feature aggregation. Code is publicly available at this https URL.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xinchao Wang
2. Dacheng Tao
3. Jiashi Feng
4. Daquan Zhou
5. Mingli Song
6. Dongze Lian
7. Jingwen Ye
8. Jie Song

In Molecular Biology

1. Xinchao Wang
2. Dacheng Tao
3. Mingli Song
4. Huihui Liu
5. Yiding Yang
6. Jiashi Feng
7. Yongcheng Jing

In Statistical and Nonlinear Physics

1. Xinchao Wang
2. Dacheng Tao
3. Huihui Liu
4. Yiding Yang
5. Jiashi Feng

Citations in the corpus

• Learning with Recoverable Forgetting (2022, positive): “It has been successfully conducted in deep model compression [61], incremental learning [37], continual learning [25,57] and other tasks other than classification [5,53,22,50,36,60,51,55,23].”
• Factorizing Knowledge in Neural Networks (2022, background): “Therefore, a recent line of research argues the importance of finding disentangled variables in representation learning [4,49,45,36,63,13] while providing invariance in learning [14,1,23].”
• Overcoming Catastrophic Forgetting in Graph Neural Networks (2020, background): “Many other GNN models (Yang et al. 2019, 2020a) have been explored recently, demonstrating promising performances on graph applications (Qiu et al. 2020; Wang et al. 2014) Continual Learning.”
• Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning (2022, methodology): “Convolution has been used for a long time as the main module to extract the image features in computer vision tasks, and CNN-based architectures have been studied [49, 18, 59, 39, 60, 37, 63] with extension on graph-based data [62, 61, 36].”
• Progressive Network Grafting for Few-Shot Knowledge Distillation (2020, unknown): “The works of (Song et al. 2019, 2020), on the other hand, focus on estimating knowledge transferability across different tasks, while those of (Yang et al. 2020b,a) explore distillation on the graph domain.”
• Amalgamating Knowledge from Heterogeneous Graph Neural Networks (2021, background): “Graph neural networks (GNNs) have achieved unprecedented advances in recent years, showing promising performance in handling graph data lying in the non-Euclidean domain [16, 37, 53, 44, 6, 41, 19, 23, 36, 13, 18, 25, 42].”