How to transfer algorithmic reasoning knowledge to learn new algorithms?

Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work <cit.> has shown that to enable systematic generalisation on graph algorithms it is critical to have access to the intermediate steps of the program/algorithm. In many reasoning tasks, where algorithmic-style reasoning is important, we only have access to the input and output examples. Thus, inspired by the success of pre-training on similar tasks or data in Natural Language Processing (NLP) and Computer Vision, we set out to study how we can transfer algorithmic reasoning knowledge. Specifically, we investigate how we can use algorithms for which we have access to the execution trace to learn to solve similar tasks for which we do not. We investigate two major classes of graph algorithms, parallel algorithms such as breadth-first search and Bellman-Ford and sequential greedy algorithms such as Prim and Dijkstra. Due to the fundamental differences between algorithmic reasoning knowledge and feature extractors such as used in Computer Vision or NLP, we hypothesise that standard transfer techniques will not be sufficient to achieve systematic generalisation. To investigate this empirically we create a dataset including 9 algorithms and 3 different graph types. We validate this empirically and show how instead multi-task learning can be used to achieve the transfer of algorithmic reasoning knowledge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/23/2023

Neural Algorithmic Reasoning Without Intermediate Supervision

Neural Algorithmic Reasoning is an emerging area of machine learning foc...
research
07/04/2023

All in One: Multi-task Prompting for Graph Neural Networks

Recently, ”pre-training and fine-tuning” has been adopted as a standard ...
research
09/22/2022

A Generalist Neural Algorithmic Learner

The cornerstone of neural algorithmic reasoning is the ability to solve ...
research
02/09/2023

Dual Algorithmic Reasoning

Neural Algorithmic Reasoning is an emerging area of machine learning whi...
research
05/17/2022

When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning

Transfer learning (TL) in natural language processing (NLP) has seen a s...
research
07/01/2023

Recursive Algorithmic Reasoning

Learning models that execute algorithms can enable us to address a key p...
research
12/10/2022

Algorithmic progress in computer vision

We investigate algorithmic progress in image classification on ImageNet,...

Please sign up or login with your details

Forgot password? Click here to reset