Attention-based Iterative Decomposition for Tensor Product Representation

In recent research, Tensor Product Representation (TPR) is applied for the systematic generalization task of deep neural networks by learning the compositional structure of data. However, such prior works show limited performance in discovering and representing the symbolic structure from unseen test data because their decomposition to the structural representations was incomplete. In this work, we propose an Attention-based Iterative Decomposition (AID) module designed to enhance the decomposition operations for the structured representations encoded from the sequential input data with TPR. Our AID can be easily adapted to any TPR-based model and provides enhanced systematic decomposition through a competitive attention mechanism between input features and structured representations. In our experiments, AID shows effectiveness by significantly improving the performance of TPR-based prior works on the series of systematic generalization tasks. Moreover, in the quantitative and qualitative evaluations, AID produces more compositional and well-bound structural representations than other works. Humans can understand the compositional properties of the surrounding world and, based on their understanding, systematically generalize over unfamiliar things. This systematic generalization ability is one of the main characteristics of human intelligence and also the central issue of deep neural network research. However, the systematic generalization performance of deep neural networks is still far from human-level generalization (Fodor & Pylyshyn, 1988; Lake & Baroni, 2018; Hupkes et al., 2020; O'Reilly et al., 2022; Smolensky et al., 2022). Therefore, to improve the generalization performance, researchers have integrated symbolic system methodologies, such as Tensor Product Representation (TPR) (Smolensky, 1990), into neural networks. TPR is a general method that explicitly encodes the symbolic structure of data with distributed representations. It is constituted by the tensor product of roles vectors and fillers vectors, where each encodes structural information and content of data.