Embed2Sym - scalable neuro-symbolic reasoning via clustered embeddings
File(s)
Supporting information
Accepted version
Author(s)
Aspis, Y
Broda, K
Lobo, J
Russo, A
Type
Conference Paper
Abstract
Neuro-symbolic reasoning approaches proposed in recent years combine a neural perception component with a symbolic reasoning component to solve a downstream task. By doing so, these approaches can provide neural networks with symbolic reasoning capabilities, improve their interpretability and enable generalization beyond the training task. However, this often comes at the cost of poor training time, with potential scalability issues. In this paper, we propose a scalable neuro-symbolic approach, called Embed2Sym. We complement a two-stage (perception and reasoning) neural network architecture designed to solve a downstream task end-to-end with a symbolic optimisation method for extracting learned latent concepts. Specifically, the trained perception network generates clusters in embedding space that are identified and labelled using symbolic knowledge and a symbolic solver. With the latent concepts identified, a neuro-symbolic model is constructed by combining the perception network with the symbolic knowledge of the downstream task, resulting in a model that is interpretable and transferable. Our evaluation shows that Embed2Sym outperforms state-of-the-art neuro-symbolic systems on benchmark tasks in terms of training time by several orders of magnitude while providing similar if not better accuracy.
Date Issued
2022-08-05
Date Acceptance
2022-08-01
Citation
19th International Conference on Principles of Knowledge Representation and Reasoning, KR 2022, 2022, pp.421-431
ISBN
9781956792010
Publisher
K Proceedings
Start Page
421
End Page
431
Journal / Book Title
19th International Conference on Principles of Knowledge Representation and Reasoning, KR 2022
Copyright Statement
Copyright © 2022 International Joint Conferences on Artificial Intelligence Organization
Identifier
https://proceedings.kr.org/2022/44/
Source
The 19th International Conference on Principles of Knowledge Representation and Reasoning
Publication Status
Published
Start Date
2022-07-31
Finish Date
2022-08-05
Coverage Spatial
Haifa, Isral
Date Publish Online
2022-08-05