Explainable Cross-Domain Recommendations Through Relational Learning
Open accessAbstract
We propose a method to generate explainable recommendation rules on cross-domain problems. Our two main contributions are: i) using relational learning to generate the rules which are able to explain clearly why the items were recommended to the particular user, ii) using the user's preferences of items on different domains and item attributes to generate novel or unexpected recommendations for the user. To illustrate that our method is indeed feasible and applicable, we conducted experiments on music and movie domains.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
General-purpose LLMs often show uneven performance across medical tasks.
“Additionally, LLMs exhibit significant domain generalization issues: general-purpose models often show uneven performance across medical tasks.”
From Artificial intelligence-powered prediction of diabetic complications: from clinical data to molecular omics (2026) · cites this paper as [140]
The Research Methodology (p. 1) studies music recommendations based on movie preferences, and the Results and Discussion (p. 2) report accuracy for those recommendation methods. Searches for general-purpose LLMs, medical tasks, and medical domain generalization found no passage addressing the attributed claim. (LLM, conf=0.78)
Experimental — accuracy not yet measuredLLMs exhibit significant domain generalization issues.
“Additionally, LLMs exhibit significant domain generalization issues: general-purpose models often show uneven performance across medical tasks.”
From Artificial intelligence-powered prediction of diabetic complications: from clinical data to molecular omics (2026) · cites this paper as [140]
The Abstract (p. 1) describes a cross-domain recommender system tested on music and movies, and the Results and Discussion (p. 2) address its accuracy and scalability. Searches for LLMs, medical tasks, and domain generalization found no passage assessing whether general-purpose models perform unevenly across medical tasks. (LLM, conf=0.76)
Experimental — accuracy not yet measuredIn diabetic retinopathy grading tasks, ChatGPT-4 Omni performs well for proliferative diabetic retinopathy detection but shows markedly lower accuracy for mild or early-stage lesions.
“For instance, in DR grading tasks, ChatGPT-4 Omni performs well for PDR detection but shows markedly lower accuracy for mild or early-stage lesions [131], highlighting insufficient robustness under domain shift [140].”
From Artificial intelligence-powered prediction of diabetic complications: from clinical data to molecular omics (2026) · cites this paper as [140]
The Abstract and Research Methodology (p. 1) describe a cross-domain music-and-movie recommendation system, while Results and Discussion (p. 2) report recommendation accuracy. Searches for ChatGPT-4 Omni and diabetic retinopathy grading found no passage about PDR detection or mild or early-stage lesions. The claim is therefore not verifiable from this source. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Cross-Domain Recommender Systems
Iván Cantador, A., Fernández-Tobías, I., Berkovsky, S., & Cremonesi, P. (2015) · Springer eBooks · doi:10.1007/978-1-4899-7637-6_27 · Cited by 165 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- Catherine, R., and Cohen, W. 2016. Personalized recommendations using knowledge graphs: A probabilistic logic programming approach. In Proceedings of the 10th ACM Conference on Recommender Systems , RecSys '16, 325-332. New York, NY, USA: ACM.
- Ge, M.; Delgado-Battenfeld, C.; and Jannach, D. 2010. Beyond accuracy: Evaluating recommender systems by coverage and serendipity. In Proceedings of the Fourth ACM Conference on Recommender Systems , RecSys '10, 257-260. ACM.
- Kouki, P.; Fakhraei, S.; Foulds, J.; Eirinaki, M.; and Getoor, L. 2015. Hyper: A flexible and extensible probabilistic framework for hybrid recommender systems. In Proceedings of the 9th ACM Conference on Recommender Systems , RecSys '15, 99-106. ACM.
Cited by
Sorted by citations
Cross-Domain Recommendation: Challenges, Progress, and Prospects
Zhu, F., Wang, Y., Chen, C., Zhou, J. W., Li, L., & Liu, G. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/639 · Cited by 225 · see citing works
Futia, G., & Vetrò, A. (2020) · Information · doi:10.3390/info11020122 · Cited by 94 · see citing works
A Unified Framework for Cross-Domain and Cross-System Recommendations
Zhu, F., Wang, Y., Zhou, J., Chen, C., Li, L., & Liu, G. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3104873 · Cited by 86 · see citing works
A personalized cross-domain recommendation with federated meta learning
Zhao, P. F., Jin, Y., Ren, X., & Li, Y. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18495-3 · Cited by 14 · see citing works
Uncovering Cross-Domain Recommendation Ability of Large Language Models
Liu, X., Wang, R., Sun, D., Tür, D. H., & Abdelzaher, T. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3717850 · Cited by 12 · see citing works
Xie, X., Wu, C., Huang, Z., Zhou, Y., Huang, J., Dao, F., Yan, D., Deng, K., Lyu, H., Ma, C., et al. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag083 · Cited by 4 · see citing works
“For instance, in DR grading tasks, ChatGPT-4 Omni performs well for PDR detection but shows markedly lower accuracy for mild or early-stage lesions [131], highlighting insufficient robustness under domain shift [140].”
Boka, T. F., Niu, Z., Tewolde, T. T., & Duma, R. A. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107969 · Cited by 4 · see citing works
Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations
Amal, S., Adam, M., Brusilovsky, P. L., Minkov, E., & Kuflik, T. (2019) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3308557.3308702 · Cited by 3 · see citing works
Efficient and adaptive secure cross-domain recommendations
Liu, H., He, J., Xu, Z., Zhang, Y., & Zhao, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125154 · Cited by 1 · see citing works
- Authors
- Sopchoke, S., Fukui, K.-I., & Numao, M.
- Affiliations
- The University of Osaka (JP)
- The Institute of Scientific and Industrial Research, The University of Osaka (JP)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-29
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2805784666
- Cited by
- 10
- References
- 1
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 2 · 2021: 2 · 2020: 1 · 2019: 1
- FWCI
- 0.78
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Funders
- Japan Society for the Promotion of Science
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- explainable recommendation, cross-domain recommendation, relational learning, user preferences, item characteristics, music recommendation, movie recommendation
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
