Semantics of the Black-Box: Can Knowledge Graphs Help Make Deep Learning Systems More Interpretable and Explainable?
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
The recent series of innovations in deep learning (DL) have shown enormous potential to impact individuals and society, both positively and negatively. DL models utilizing massive computing power and enormous datasets have significantly outperformed prior historical benchmarks on increasingly difficult, well-defined research tasks across technology domains such as computer vision, natural language processing, and human-computer interactions. However, DL's black-box nature and over-reliance on massive amounts of data condensed into labels and dense representations pose challenges for interpretability and explainability. Furthermore, DLs have not proven their ability to effectively utilize relevant domain knowledge critical to human understanding. This aspect was missing in early data-focused approaches and necessitated knowledge-infused learning (K-iL) to incorporate computational knowledge. This article demonstrates how knowledge, provided as a knowledge graph, is incorporated into DL using K-iL. Through examples from natural language processing applications in healthcare and education, we discuss the utility of K-iL towards interpretability and explainability.
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
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×
“The terms explainability and interpretability are often used interchangeably in the prior research without clear distinctions and the different roles that they play.(1)”
MethodBeyond accuracy: behavioral testing of NLP models with CheckList
Ribeiro, M. T., Wu, T., Guestrin, C., & Singh, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.442 · Cited by 890
Mittelstadt, B., Russell, C., & Wachter, S. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287574 · Cited by 794 · cited 1×
“The terms explainability and interpretability are often used interchangeably in the prior research without clear distinctions and the different roles that they play [10][11][12].”
Backgrounde-SNLI: Natural language inference with natural language explanations
Camburu, O.-M., Rocktäschel, T., Lukasiewicz, T., & Blunsom, P. (2018) · arXiv · doi:10.48550/arxiv.1812.01193 · Cited by 367 · cited 1×
“In such scenarios, it is exceptionally challenging to probe the model’s mechanism without the support of background knowledge [1].”
BackgroundQuery2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
Ren, H., Hu, W., & Leskovec, J. (2020) · arXiv · doi:10.48550/arxiv.2002.05969 · Cited by 135
Cited by
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
Saeed, W., & Omlin, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110273 · Cited by 783
Nazir, S., Dickson, D. M., & Akram, M. U. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106668 · Cited by 283
“A knowledge infused learning (K-iL) proposed for knowledge graphs can be used with DNN [118].”
MethodŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 278
A Review on Explainability in Multimodal Deep Neural Nets
Joshi, G., Walambe, R., & Kotecha, K. (2021) · IEEE Access · doi:10.1109/access.2021.3070212 · Cited by 204
“knowledge base infusion in healthcare and educational sectors [195].”
BackgroundA review of some techniques for inclusion of domain-knowledge into deep neural networks
Dash, T., Chitlangia, S., Ahuja, A., & Srinivasan, A. (2022) · Scientific Reports · doi:10.1038/s41598-021-04590-0 · Cited by 196
“Fusing the information in a knowledge-graph in this way into various level of hidden representations in a deep network could also allow quantitative and qualitative assessment of its functioning, leading to knowledge-infused interpretability [42].”
Razi, A., Alsoubai, A., Kim, S., Ali, S., Stringhini, G., De Choudhury, M., & Wisniewski, P. J. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579522 · Cited by 52
“For example, a RF model would be represented as trees, SVM as the hyperplane plot with dots annotated with phrases, and CNN as sparse connected convolution matrix created in each layer[27].”
MethodDalal, S., Tilwani, D., Gaur, M., Jain, S., Shalin, V. L., & Sheth, A. P. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3483577 · Cited by 19
Self-citationRoy, K., Gaur, M., Soltani, M., Rawte, V., Kalyan, A., & Sheth, A. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1056728 · Cited by 18
“Hence, a method that effectively utilizes ProKnow will contribute to algorithmic explainability in the NLG process (Gaur et al., 2021; Sheth et al., 2021).”
MethodSelf-citation
Metadata
- Authors
- Gaur, M., Faldu, K., & Sheth, A.
- Venue
- IEEE Internet Computing
- Published
- 2021-01-01
- Volume
- 25
- Issue
- 1
- Pages
- 51-59
- ISSN
- 1089-7801 (ISSN-L)
- 1941-0131
- OpenAlex
- W3093463288
- Cited by
- 139
- References
- 6
- FWCI
- 9.26
- Type
- journal article
- Language
- en
- Open access
- green
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
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.