Learning Hierarchical Relational Representations through Relational Convolutions
Abstract: A maturing area of research in deep learning is the study of architectures and inductive biases for learning 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". The key to the framework is a novel operation that captures the relational patterns in groups of objects by convolving graphlet filters—learnable templates of relational patterns—against subsets of the input. Composing relational convolutions gives rise to a deep architecture that learns 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.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Blake_Aaron_Richards1
Submission Number: 2877
Loading