William L. Hamilton · PaperMetrix

Inductive Relation Prediction by Subgraph Reasoning

2019 · arXiv (Cornell University)

The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the compositional logical rules underlying …

Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks

2021

Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data. However, GNNs are fundamentally limited by their tree-structured inductive bias: the WL-subtree kernel formulation bounds the representational capacity …

NodePiece: Compositional and Parameter-Efficient Representations of\n Large Knowledge Graphs

2021 · arXiv (Cornell University)

Conventional representation learning algorithms for knowledge graphs (KG) map\neach entity to a unique embedding vector. Such a shallow lookup results in a\nlinear growth of memory consumption for storing the embedding matrix and incurs\nhigh computational costs …

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

2018

Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds …

Hierarchical Graph Representation Learning with Differentiable Pooling

2018 · arXiv (Cornell University)

Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods …

Deep Graph Infomax

2018 · Apollo (University of Cambridge)