Relational Convolutional Networks: A framework for learning representations of hierarchical relations

Awni Altabaa, John Lafferty

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

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.

Keywords: representation learning, relational architectures, relational representation learning, hierarchical feature representations, compositionality, higher-order relations, convolutions

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A neural architecture is proposed for learning representations of hierarchical relational features through a form of convolution.

Abstract: A maturing area of research in deep learning is the development of architectures that can learn explicit representations of relational features. In this paper, we focus on the problem of learning representations of *hierarchical* relations, proposing an architectural framework we call "relational convolutional networks". Given a sequence of objects, a "multi-dimensional inner product relation" module produces a relation tensor describing all pairwise relations. A "relational convolution" layer then transforms the relation tensor into a sequence of new objects, each describing the relations within some group of objects at the previous layer. Graphlet filters, analogous to filters in convolutional neural networks, represent a template of relations against which the relation tensor is compared at each grouping. Repeating this yields representations of higher-order, hierarchical relations. We present the motivation and details of the architecture, together with a set of experiments to demonstrate how relational convolutional networks can provide an effective framework for modeling relational tasks that have hierarchical structure.

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.

Submission Number: 8566