Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
The term "explainable AI" refers to the goal of producing artificially intelligent agents that are capable of providing explanations for their decisions. Some models (e.g., rule-based systems) are designed to be explainable, while others are less explicit "black boxes" for which their reasoning remains a mystery. One example of the latter is the neural network, and over the past few decades, researchers in the field of neural-symbolic integration (NSI) have sought to extract relational knowledge from such networks. Extraction from deep neural networks, however, has remained a challenge until recent years in which many methods of extracting distinct, salient features from input or hidden feature spaces of deep neural networks have been proposed. Furthermore, methods of identifying relationships between these features have also emerged. This article presents examples of old and new developments in extracting relational explanations in order to argue that the latter have analogies in the former and, as such, can be described in terms of long-established taxonomies and frameworks presented in early neural-symbolic literature. We also outline potential future research directions that come to light from this refreshed perspective.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 3×
“Simonyan et al. [5] present a gradient-based approach which provides two network visualization methods.”
BackgroundMethodOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 2×
“Layerwise relevance propagation (LRP) is one such method [8], [10].”
BackgroundMethodStriving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Methods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · cited 1×
“Numerous surveys on the wider work of explainability are available [16]–[19] and we do not seek to replace this literature but complement it by explaining the relevance of neural-symbolic extraction methods.”
Background
Cited by
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Kute, D. V., Pradhan, B., Shukla, N., & Alamri, A. (2021) · IEEE Access · doi:10.1109/access.2021.3086230 · Cited by 209
“Townsend et al. [93] presented a review of the old and new methods of extraction without relational explanation.”
MethodExplainable goal-driven agents and robots-a comprehensive review
Sado, F., Loo, C. K., Liew, W. S., Kerzel, M., & Wermter, S. (2023) · ACM Computing Surveys · doi:10.1145/3564240 · Cited by 79
“Neural-symbolic (NS) models combine the efficient learning and inference power of traditional NN and the interpretability of symbolic knowledge extraction and reasoning [70, 204].”
BackgroundMethodBorrego-Díaz, J., & Galán-Páez, J. (2022) · Minds and Machines · doi:10.1007/s11023-022-09603-z · Cited by 34
“«50» The undertaking of building models to support explanation -especially for intelligent systems based on ML-covers various techniques, ranging from those specialized in Deep Learning (cf. Townsend et al., 2019) to logical causal models (in the tradition of classical Expert Systems).”
MethodDíaz-Rodríguez, N., Lamas, A., Sanchez, J., Franchi, G., Donadello, I., Tabik, S., Filliat, D., Cruz, P., Montes, R., & Herrera, F. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.09.022 · Cited by 2
Metadata
- Authors
- Townsend, J., Chaton, T., & Monteiro, J. M.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2020-09
- Volume
- 31
- Issue
- 9
- Pages
- 3456-3470
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2988571238
- Cited by
- 78
- References
- 19
- FWCI
- 4.14
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective. https://app.cochat.ai/papers/10.1109/tnnls.2019.2944672
- The paper
- Townsend, J., Chaton, T., & Monteiro, J. M. (2020). Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/tnnls.2019.2944672
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.