Disentangled Graph Convolutional Networks

By Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, Wenwu Zhu. International Conference on Machine Learning, 2019

377 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/962cf7797614f2882d2084eb6cb56928e981bc26

How researchers see this paper

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

1. Xiang Wang
2. Xiangnan He
3. Yin-wei Wei
4. Tat-seng Chua
5. Xiao Wang
6. Lianghao Xia
7. Liqiang Nie
8. Chao Huang

Citations in the corpus

• Disentangled Graph Collaborative Filtering (2020, methodology): “We then apply an graph disentangling module equipped with neighbor routing [25, 29] and embedding propagation [9, 18, 39, 40] mechanisms.”
• Parameterized Explainer for Graph Neural Network (2020, background): “In recent work, GNNs broadly encode node features as messages and adopt the message passing mechanism to propagate and aggregate them along edges to learn node/graph representations, which are then utilized for downstream tasks [25, 10, 41, 29, 45, 34, 47].”
• Learning Disentangled Representations for Recommendation (2019, background): “Disentangled representation learning on relational data, such as graph-structured data, was not explored until recently [37].”
• Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, background): “Different intents should contain different information about user preference [23, 24].”
• 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].”
• Hypergraph Contrastive Collaborative Filtering (2022, background): “Additionally, inspired by the effectiveness of disentangled graph representation learning [23], DGCF [36] disentangles latent user interests with intent-aware user-item graph structures for embedding users.”
• Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback (2020, methodology): “• DisenGCN [24] Themethod could disentangle the representation of each node into several factors.”
• Learning to Drop: Robust Graph Neural Network via Topological Denoising (2020, unknown): “Multiple extensions were further proposed [9, 25, 28, 31, 39, 43].”
• Factorizable Graph Convolutional Networks (2020, background): “This scheme therefore contrasts to the prior approaches of [Ma et al., 2019a, Liu et al., 2019], where the disentanglement takes place only within a local neighborhood, without accounting for global contexts.”
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks (2020, background): “ity in tackling graph analytics problems, such as node classification [1, 31], graph classification [7, 37], link prediction [13, 36] and recommendation [6, 34]. The typical GCN [14] and its variants [11, 16, 27, 30, 36] usually follow a message-passing manner. A key step is feature aggregation, i.e”
• Robust Graph Convolutional Networks Against Adversarial Attacks (2019, background): “Further improvements include adding an attention mechanism to assign different weights in aggregating node neighborhoods [28, 30, 31, 34], adding residual and jumping connections [32], sampling to improve efficiency [4, 5, 14, 33] considering edge attributes [15, 23, 26], disentangling node represen”