Learning Hierarchical Relational Representations through Relational Convolutions
This work addresses the problem of modeling hierarchical relations in data for researchers in deep learning, presenting a novel architecture that is incremental in building on existing relational representation methods.
The paper tackles the challenge of learning hierarchical relational representations by introducing relational convolutional networks, which use graphlet filters to capture complex relational patterns, and demonstrates their effectiveness on relational tasks with hierarchical structure.
An evolving area of research in deep learning is the study of architectures and inductive biases that support the learning of relational feature representations. In this paper, we address the challenge of learning representations of hierarchical relations--that is, higher-order relational patterns among groups of objects. We introduce "relational convolutional networks", a neural architecture equipped with computational mechanisms that capture progressively more complex relational features through the composition of simple modules. A key component of this framework is a novel operation that captures 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.