When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning
Anirban Das, Irtaza Khalid, Rafael Peñaloza, Steven Schockaert
Abstract
Designing models that can learn to reason in a systematic way is an important and long-standing challenge. In recent years, a wide range of solutions have been proposed for the specific case of systematic relational reasoning, including Neuro-Symbolic approaches, variants of the Transformer architecture, and specialized Graph Neural Networks. However, existing benchmarks for systematic relational reasoning focus on an overly simplified setting, based on the assumption that reasoning can be reduced to composing relational paths. In fact, this assumption is hard-baked into the architecture of several recent models, leading to approaches that can perform well on existing benchmarks but are difficult to generalize to other settings. To support further progress in the field of systematic relational reasoning with neural networks, we introduce a new benchmark that adds several levels of difficulty, requiring models to go beyond path-based reasoning.
BibTeX
@inproceedings{
das2025when,
title={When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning},
author={Anirban Das and Irtaza Khalid and Rafael Pe{\~n}aloza and Steven Schockaert},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2025},
url={https://openreview.net/forum?id=HZJiIog5XH}
}