Learning Relational Representations with Auto-encoding Logic Programs
Open accessAbstract
Deep learning methods capable of handling relational data have proliferated over the past years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these methods aim at re-representing symbolic relational data in Euclidean space. They offer better scalability, but can only approximate rich relational structures and are less flexible in terms of reasoning. This paper introduces a novel framework for relational representation learning that combines the best of both worlds. This framework, inspired by the auto-encoding principle, uses first-order logic as a data representation language, and the mapping between the the original and latent representation is done by means of logic programs instead of neural networks. We show how learning can be cast as a constraint optimisation problem for which existing solvers can be used. The use of logic as a representation language makes the proposed framework more accurate (as the representation is exact, rather than approximate), more flexible, and more interpretable than deep learning methods. We experimentally show that these latent representations are indeed beneficial in relational learning tasks.
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?
Predicate invention helps reduce the size of target programs, which in turn reduces sample complexity and improves predictive accuracy.
“Predicate invention has been shown to help reduce the size of target programs, which in turns reduces sample complexity and improves predictive accuracy (Cropper 2019; Dumancic et al. 2019).”
From Learning programs by learning from failures (2021) · cites this paper as Dumancic et al. 2019
Section 4.1 (page unavailable) reports improved predictive performance for models learned from the paper’s latent predicates. But Section 3.5’s reduction concerns candidate clauses pruned during search, not the size of target programs, and the copy does not establish reduced sample complexity or the claimed causal chain. (LLM, conf=0.86)
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
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · see citing works
Artificial intelligence: a modern approach
Kumar, D. A., Balasubramanian, S., Byeon, D. H., & Manerkar, P. G. V. (1995) · Choice Reviews Online · doi:10.5860/choice.33-1577 · Cited by 22,182 · see citing works
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928 · see citing works
(2016) · Cited by 11,679 · see citing works
The relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559 · see citing works
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · see citing works
Richardson, M., & Domingos, P. (2006) · Machine Learning · doi:10.1007/s10994-006-5833-1 · Cited by 2,676 · see citing works
A Review of Relational Machine Learning for Knowledge Graphs
Nickel, M., Murphy, K. P., Tresp, V., & Gabrilovich, E. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2483592 · Cited by 1,684 · see citing works
Inductive Logic Programming: Theory and methods
Muggleton, S., & de Raedt, L. (1994) · The Journal of Logic Programming · doi:10.1016/0743-1066(94)90035-3 · Cited by 1,537 · see citing works
The Semantics of Predicate Logic as a Programming Language
van Emden, M. H., & Kowalski, R. (1976) · Journal of the ACM · doi:10.1145/321978.321991 · Cited by 1,449 · see citing works
Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning
Heaton, J. (2017) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-017-9314-z · Cited by 1,062 · see citing works
A survey of very large-scale neighborhood search techniques
Ahuja, R. K., Ergün, Ö., Orlin, J. B., & Punnen, A. P. (2002) · Discrete Applied Mathematics · doi:10.1016/s0166-218x(01)00338-9 · Cited by 644 · see citing works
Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning)
Getoor, L., & Taskar, B. (2007) · The MIT Press eBooks · Cited by 502 · see citing works
Learning Explanatory Rules from Noisy Data
Evans, R., & Grefenstette, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5714 · Cited by 426 · see citing works
Handbook of Constraint Programming (Foundations of Artificial Intelligence)
Rossi, F., van Beek, P., & Walsh, T. (2006) · Elsevier eBooks · Cited by 330 · see citing works
Statistical predicate invention
Kok, S., & Domingos, P. (2007) · International Conference on Machine Learning · doi:10.1145/1273496.1273551 · Cited by 270 · see citing works
Bottom-up learning of Markov logic network structure
Mihalkova, L. S., & Mooney, R. J. (2007) · International Conference on Machine Learning · doi:10.1145/1273496.1273575 · Cited by 168 · see citing works
Lifted Rule Injection for Relation Embeddings
Demeester, T., Rocktäschel, T., & Riedel, S. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1146 · Cited by 142 · see citing works
Learning Markov Logic Networks Using Structural Motifs
Kok, S., & Domingos, P. (2010) · Cited by 105 · see citing works
Adversarial Sets for Regularising Neural Link PredictorsPreprint
Minervini, P., Demeester, T., Rocktäschel, T., & Riedel, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.07596 · Cited by 66 · see citing works
Unsupervised learning by program synthesis
Ellis, K., Solar-Lezama, A., & Tenenbaum, J. B. (2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 49 · see citing works
Learning efficient logic programs
Cropper, A., & Muggleton, S. (2018) · Machine Learning · doi:10.1007/s10994-018-5712-6 · Cited by 33 · see citing works
Lifted generative learning of Markov logic networks
Haaren, J. V., den Broeck, G. V., Meert, W., & Davis, J. J. (2015) · Machine Learning · doi:10.1007/s10994-015-5532-x · Cited by 29 · see citing works
Self-citationLogical Rule Induction and Theory Learning Using Neural Theorem ProvingPreprint
Campero, A., Pareja, A., Klinger, T., Tenenbaum, J. B., & Riedel, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02193 · Cited by 21 · see citing works
RelNN: A Deep Neural Model for Relational LearningPreprint
Kazemi, S. M., & Poole, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.02831 · Cited by 18 · see citing works
On Inductive Abilities of Latent Factor Models for Relational Learning
Trouillon, T., Gaussier, É., Dance, C. R., & Bouchard, G. (2019) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11305 · Cited by 15 · see citing works
Flagged first, then by citations
2 of the 28 references couldn’t be matched to a known paper.
Research works printed but not linked: 7
- Steven Gay, Renaud Hartert, Christophe Lecoutre, and Pierre Schaus. Conflict ordering search for scheduling problems. In Principles and Practice of Con- straint Programming, pages 140-148. Springer, 2015.
- Lise Getoor and Ben Taskar. Intro- duction to Statistical Relational Learning (Adaptive Com- putation and Machine Learning). The MIT Press, 2007.
- Sumit Gulwani, Oleksandr Polozov, and Rishabh Singh. Program synthesis. Foundations and Trends R in Programming Languages, 4(1-2):1-119, 2017.
- William L. Hamilton, Rex Ying, and Jure Leskovec. Representation learning on graphs: Meth- ods and applications. IEEE Data Eng. Bull., 40(3):52-74, 2017.
- Manhaeve et al., 2018] Robin Manhaeve, Sebastijan Duman- cic, Angelika Kimmig, Thomas Demeester, and Luc De Raedt. Deepproblog: Neural probabilistic logic pro- gramming. In NeurIPS, pages 3749-3759. 2018.
- Rocktäschel and Riedel, 2017] Tim Rocktäschel and Sebas- tian Riedel. End-to-end differentiable proving. In NIPS, pages 3788-3800.
- Sourek et al., 2016] Gustav Sourek, Suresh Manandhar, Filip Zelezny, Steven Schockaert, and Ondrej Kuzelka. Learning Predictive Categories Using Lifted Relational Neural Networks, volume 10326 of LNAI. Springer Inter- national Publishing, 2016.
Cited by
Sorted by citations
Neural probabilistic logic programming in DeepProbLog
Manhaeve, R., Dumančić, S., Kimmig, A., Demeester, T., & De Raedt, L. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103504 · Cited by 131 · see citing works
From Statistical Relational to Neuro-Symbolic Artificial Intelligence
Raedt, L. D., Dumančić, S., Manhaeve, R., & Marra, G. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/688 · Cited by 117 · see citing works
Learning programs by learning from failures
Cropper, A., & Morel, R. (2021) · Machine Learning · doi:10.1007/s10994-020-05934-z · Cited by 86 · see citing works
“Predicate invention Predicate invention has been shown to help reduce the size of target programs, which in turns reduces sample complexity and improves predictive accuracy (Cropper 2019; Dumancic et al. 2019).”
BackgroundInductive Logic Programming At 30: A New Introduction
Cropper, A., & Dumančić, S. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13507 · Cited by 83 · see citing works
“For instance, Auto-encoding logic programs (ALPs)(Dumančić et al., 2019) invent predicates by simultaneously learning a pair of logic programs: an encoder that maps the examples given as interpretations to new interpretations defined entirely in terms of invented predicates(10), and a decoder that reconstructs the ori…”
BackgroundInfluentialTurning 30: New Ideas in Inductive Logic Programming
Cropper, A., Dumančić, S., & Muggleton, S. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/673 · Cited by 78 · see citing works
Inductive logic programming at 30
Cropper, A., Dumančić, S., Evans, R., & Muggleton, S. H. (2022) · Machine Learning · doi:10.1007/s10994-021-06089-1 · Cited by 61 · see citing works
Towards Data-And Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing
Wang, W., Yang, Y., & Wu, F. Q. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3483273 · Cited by 92 · see citing works
Rules, L. O.-R., & A, F. A. L. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48751-4 · Cited by 24 · see citing works
From Statistical Relational to Neuro-Symbolic Artificial Intelligence
Marra, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30294 · Cited by 22 · see citing works
Weakly Supervised Neural Symbolic Learning for Cognitive Tasks
Tian, J., Li, Y., Chen, W., Xiao, L., He, H., & Jin, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20533 · Cited by 10 · see citing works
Top program construction and reduction for polynomial time Meta-Interpretive learning
Patsantzis, S., & Muggleton, S. (2021) · Machine Learning · doi:10.1007/s10994-020-05945-w · Cited by 7 · see citing works
Predicate Invention by Learning From FailuresPreprint
Cropper, A., & Morel, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.14426 · Cited by 7 · see citing works
A study of continuous vector representations for theorem proving
Purgał, S. J., Parsert, J., & Kaliszyk, C. (2021) · Journal of Logic and Computation · doi:10.1093/logcom/exab006 · Cited by 4 · see citing works
Learning Logic Programs by Combining Programs
Cropper, A., & Hocquette, C. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230309 · Cited by 4 · see citing works
From statistical relational to neurosymbolic artificial intelligence: A survey
Marra, G., Dumančić, S., Manhaeve, R., & Raedt, L. D. (2024) · Artificial Intelligence · doi:10.1016/j.artint.2023.104062 · Cited by 81 · see citing works
Knowledge Refactoring for Inductive Program Synthesis
Dumancic, S., Guns, T., & Cropper, A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16893 · Cited by 2 · see citing works
Self-citationPropositionalization of Relational Data
Nada Lavrač, A., Podpečan, V., & Robnik‐Šikonja, M. (2021) · Springer eBooks · doi:10.1007/978-3-030-68817-2_4 · Cited by 2 · see citing works
Knowledge Refactoring for Program InductionPreprint
Dumančić, S., & Cropper, A. (2020) · arXiv (Cornell University) · Cited by 2 · see citing works
Learning Logic Programs by Discovering Where Not to Search
Cropper, A., & Hocquette, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i5.25774 · Cited by 1 · see citing works
Forgetting to Learn Logic Programs
Cropper, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5776
Neuro-Psychological Approaches for Artificial Intelligence
Dheer, S., Tripathi, S., & Kim, E. (2023) · Advances in environmental engineering and green technologies book series · doi:10.4018/978-1-6684-6366-6.ch003
HorNets: Learning from Discrete and Continuous Signals with Routing Neural NetworksPreprint
Koloski, B., Nada Lavrač, A., & Škrlj, B. (2025) · Qeios · doi:10.32388/22i1po
HorNets: learning from discrete and continuous signals with routing neural networks
Koloski, B., Nada Lavrač, A., & Škrlj, B. (2025) · Machine Learning · doi:10.1007/s10994-024-06673-1
- Authors
- Dumancic, S., Guns, T., Meert, W., & Blockeel, H.
- Affiliations
- KU Leuven,Belgium
- Vrije Universiteit Brussel (BE)
- KU Leuven (BE)
- Venue
- Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
- Published
- 2019-08
- Pages
- 6081-6087
- OpenAlex
- W2938001473
- Cited by
- 27
- References
- 28
- Citations by year
- 2025: 2 · 2024: 3 · 2023: 3 · 2022: 2 · 2021: 10 · 2020: 6
- FWCI
- 1.72
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Lirias (KU Leuven) (submittedVersion)
- VUBIR (Vrije Universiteit Brussel) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Agentschap Innoveren en Ondernemen
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- first-order logic, logic programs, relational data, constraint optimisation, latent representations, symbolic reasoning, interpretability
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
