Composition-based Multi-Relational Graph Convolutional Networks

By Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. Talukdar. International Conference on Learning Representations, 2019

1,165 citations recorded by the source corpus.

Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.

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

View Paper: https://www.semanticscholar.org/paper/4b244a6778c95b1df8e9e02332ff8d22e675f628

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

In Molecular Biology

In Statistical and Nonlinear Physics

Citations in the corpus

Multi-omics single-cell data integration and regulatory inference with graph-linked embedding (2022, background): “Beyond canonical graph convolution, more advanced graph neural network architectures 59–61 may also be adopted to extract richer information from the regulatory graph.”
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning (2021, methodology): “Since each KG is a multi-relational graph and GCN is a powerful model for the graphstructured data [28, 30, 36, 42], an ω-layer relation-aware GCN is used to model the structural dependencies.”
Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey (2023, background): “To further enhance graph attention networks (GATs) and capture both entity and relation features within any entity′s neighborhood, another model is proposed for attentionbased feature embedding[210].”
Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph (2020, methodology): “We follow Vashishth et al. (2020) and use a non-parametric compositional operation φ ( · ) to combine the node embedding and the relation embedding.”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, neutral): “t al. [61] introduced graph attention networks with multi-head attention as encoder to capture multi-hop neighborhood features by inputing the concatenation of entity and relation embeddings. CompGCN [62] proposes entity-relation composition operations over each edge in the neighborhood of a central”
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts (2022, methodology): “We follow Vashishth et al. (2020) and Ji et al. (2020) to use a non-parametric compositional operation ϕ ( · ) to combine the concept node embedding and the relation embedding.”
HittER: Hierarchical Transformers for Knowledge Graph Embeddings (2020, methodology): “Vashishth et al. (2020) explore the idea of using existing knowledge graph embedding methods to improve the entity-relation composition in various Graph Convolutional Network-based methods.”
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction (2021, methodology): “For link prediction, the prevalent frameworks [32, 48, 12, 59] adopt an auto-encoder formulation, which uses GNNs to encode node representations, and decodes edges as a function over node pairs.”
Deep Generative Models in Engineering Design: A Review (2021, methodology): “Graph neural networks (GNNs) [42,43,44,45,46] provide an excellent tool for machine learning on graphs.”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “…use relation-aware GCN as the encoder and DisMult as the decoder M-GNN (Wang et al., 2019b) replace the mean aggregator in R-GCN with a MLP CompGCN (Vashishth et al., 2020b) incorporate entity and relation embeddings into the aggregator function KBGAT (Nathani et al., 2019) incorporate a triplet…”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “To name a few, ChronoTranslate [205] learns a universal representation of entities and time-speciﬁc representations of the Temporal KGs, respectively.”
ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations (2019, methodology): “…to perform tasks such as node classiﬁcation (Kipf and Welling 2017; Veliˇckovi´c et al. 2017) and link prediction (Schlichtkrull et al. 2017; Vashishth et al. 2019), others focus on learning graph-level representations for tasks like graph classiﬁcation (Bruna et al. 2013; Henaff, Bruna,…”