A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledge

TL;DR

This paper introduces a neuro-symbolic framework for sequence classification that incorporates relational and temporal knowledge, addressing the challenge of dynamic knowledge application over time, and compares it with neural-only models on a new benchmark.

Contribution

It presents a novel neuro-symbolic approach for temporal sequence classification that handles changing knowledge, filling a gap in existing static knowledge frameworks.

Findings

Neuro-symbolic models outperform neural-only models in temporal sequence tasks.

The new benchmark reveals the complexity and limitations of current neuro-symbolic methods.

Results highlight the need for further research in dynamic knowledge integration.

Abstract

One of the goals of neuro-symbolic artificial intelligence is to exploit background knowledge to improve the performance of learning tasks. However, most of the existing frameworks focus on the simplified scenario where knowledge does not change over time and does not cover the temporal dimension. In this work we consider the much more challenging problem of knowledge-driven sequence classification where different portions of knowledge must be employed at different timesteps, and temporal relations are available. Our experimental evaluation compares multi-stage neuro-symbolic and neural-only architectures, and it is conducted on a newly-introduced benchmarking framework. Results demonstrate the challenging nature of this novel setting, and also highlight under-explored shortcomings of neuro-symbolic methods, representing a precious reference for future research.