Neural Algorithmic Reasoning Without Intermediate Supervision

TL;DR

This paper introduces a method for neural algorithmic reasoning that learns from input-output pairs alone, without intermediate supervision, achieving state-of-the-art results on algorithmic tasks and improving generalization to larger inputs.

Contribution

It proposes architectural enhancements and a self-supervised objective enabling neural models to learn algorithms solely from input-output data, bypassing the need for intermediate supervision.

Findings

Achieves competitive performance on CLRS benchmark tasks.

Sets new state-of-the-art results for sorting and other problems.

Demonstrates effective learning without intermediate algorithm steps.

Abstract

Neural algorithmic reasoning is an emerging area of machine learning focusing on building models that can imitate the execution of classic algorithms, such as sorting, shortest paths, etc. One of the main challenges is to learn algorithms that are able to generalize to out-of-distribution data, in particular with significantly larger input sizes. Recent work on this problem has demonstrated the advantages of learning algorithms step-by-step, giving models access to all intermediate steps of the original algorithm. In this work, we instead focus on learning neural algorithmic reasoning only from the input-output pairs without appealing to the intermediate supervision. We propose simple but effective architectural improvements and also build a self-supervised objective that can regularise intermediate computations of the model without access to the algorithm trajectory. We demonstrate that our approach is competitive to its trajectory-supervised counterpart on tasks from the CLRS Algorithmic Reasoning Benchmark and achieves new state-of-the-art results for several problems, including sorting, where we obtain significant improvements. Thus, learning without intermediate supervision is a promising direction for further research on neural reasoners.