Timezone: »

Self-Supervised Representation Learning via Latent Graph Prediction
Yaochen Xie · Zhao Xu · Shuiwang Ji

Tue Jul 19 07:35 AM -- 07:40 AM (PDT) @ Room 327 - 329

Self-supervised learning (SSL) of graph neural networks is emerging as a promising way of leveraging unlabeled data. Currently, most methods are based on contrastive learning adapted from the image domain, which requires view generation and a sufficient number of negative samples. In contrast, existing predictive models do not require negative sampling, but lack theoretical guidance on the design of pretext training tasks. In this work, we propose the LaGraph, a theoretically grounded predictive SSL framework based on latent graph prediction. Learning objectives of LaGraph are derived as self-supervised upper bounds to objectives for predicting unobserved latent graphs. In addition to its improved performance, LaGraph provides explanations for recent successes of predictive models that include invariance-based objectives. We provide theoretical analysis comparing LaGraph to related methods in different domains. Our experimental results demonstrate the superiority of LaGraph in performance and the robustness to decreasing of training sample size on both graph-level and node-level tasks.

Author Information

Yaochen Xie (Texas A&M University)
Zhao Xu (Texas A&M University)
Shuiwang Ji (Texas A&M University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors