Timezone: »

 
Poster
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
Leonardo Cotta · Carlos H. C. Teixeira · Ananthram Swami · Bruno Ribeiro

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1420

Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in the graph. Although such approaches have shown advances in downstream node classification tasks, they are ineffective in jointly representing larger k-node sets, k{>}2. We propose MHM-GNN, an inductive unsupervised graph representation approach that combines joint k-node representations with energy-based models (hypergraph Markov networks) and GNNs. To address the intractability of the loss that arises from this combination, we endow our optimization with a loss upper bound using a finite-sample unbiased Markov Chain Monte Carlo estimator. Our experiments show that the unsupervised joint k-node representations of MHM-GNN produce better unsupervised representations than existing approaches from the literature.

Author Information

Leonardo Cotta (Purdue University)
Carlos H. C. Teixeira (Universidade Federal de Minas Gerais)
Ananthram Swami (Army Research Laboratory, Adelphi)
Bruno Ribeiro (Purdue)

More from the Same Authors