Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Abstract

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph -- a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to $90\%$. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.

References in corpus (18)

• Fast unfolding of communities in large networks
• Community structure in social and biological networks
• Community detection in graphs
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• struc2vec: Learning Node Representations from Structural Identity
• Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities
• VERSE: Versatile Graph Embeddings from Similarity Measures
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• Watch Your Step: Learning Node Embeddings via Graph Attention
• HARP: Hierarchical Representation Learning for Networks
• Empirical Comparison of Algorithms for Network Community Detection
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• Learning Edge Representations via Low-Rank Asymmetric Projections
• A Tutorial on Network Embeddings
• Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings
• Detecting Cohesive and 2-mode Communities in Directed and Undirected Networks
• From Node Embedding To Community Embedding

Cited by in corpus (27)

• Stacking Models for Nearly Optimal Link Prediction in Complex Networks
• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
• Graph Representation Learning Beyond Node and Homophily
• Unsupervised Differentiable Multi-aspect Network Embedding
• vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
• Large-Scale Network Embedding in Apache Spark
• Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling
• Multiple Kernel Representation Learning on Networks
• Topic-aware latent models for representation learning on networks
• Which way? Direction-Aware Attributed Graph Embedding
• Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks
• Graph Neighborhood Attentive Pooling
• Friendship is All we Need: A Multi-graph Embedding Approach for Modeling Customer Behavior
• Span-core Decomposition for Temporal Networks: Algorithms and Applications
• MUSE: Multi-faceted Attention for Signed Network Embedding
• Explainable Recommender Systems via Resolving Learning Representations
• Multi-Aspect Temporal Network Embedding: A Mixture of Hawkes Process View
• Pair-view Unsupervised Graph Representation Learning
• Multi-Facet Recommender Networks with Spherical Optimization
• mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding
• Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model
• Bot-Match: Social Bot Detection with Recursive Nearest Neighbors Search
• Graph Embedding with Hierarchical Attentive Membership
• HNet: Graphical Hypergeometric Networks