Robust Graph Representation Learning via Predictive CodingDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: Predictive coding, deep geometric learning, deep learning, machine learning, bio-inspired learning, neuroscience
TL;DR: For the first time, we use predictive coding in deep geometric learning and demonstrate that we can enhance the robustness of learning representation through energy minimization.
Abstract: Graph neural networks have recently shown outstanding results in diverse types of tasks in machine learning, providing interdisciplinary state-of-the-art performance on structured data. However, they have been proved to be vulnerable to imperceptible adversarial attacks and shown to be unfit for out-of-distribution generalisation. Here, we address this problem by introducing a novel message-passing scheme based on the theory of predictive coding, an energy-based alternative to back-propagation that has its roots in neuroscience. As both graph convolution and predictive coding can be seen as low-pass filtering mechanisms, we postulate that predictive coding adds a second efficient filter to the messaging passing process which enhances the robustness of the learned representation. Through an extensive set of experiments, we show that the proposed model attains comparable performance to its graph convolution network counterpart, delivering strictly better performance on inductive tasks. Most importantly, we show that the energy minimization enhances the robustness of the produced presentation and can be leveraged to further calibrate our models and provide representations that are more robust against advanced graph adversarial attacks.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
Supplementary Material: zip
9 Replies

Loading