publications

2026

1. ICML

   On the Theoretical Limitations of Embedding-based Link Prediction

   Samy Badreddine, Emile van Krieken, and Luciano Serafini

   In International Conference on Machine Learning (ICML), 2026

   Abs arXiv HTML

   Many knowledge graph embedding (KGE) models for link prediction use powerful encoders. However, they often rely on a simple hidden vector-matrix multiplication to score subject-relation queries against candidate object entities. When the number of entities is larger than the model’s embedding dimension, which is often the case in practice by several orders of magnitude, we have a linear output layer with a rank bottleneck. Such bottlenecked layers limit model expressivity. We investigate both theoretically and empirically how rank bottlenecks affect KGEs. We find that, by limiting the set of feasible predictions, rank bottlenecks hurt the ranking accuracy and distribution fidelity of scores. Inspired by the language modelling literature, we propose KGE-MoS, a mixture-based output layer to break rank bottlenecks in many KGEs. Our experiments show that KGE-MoS improves ranking performance of KGE models on large-scale datasets at a low parameter cost.

2. CoLoRAI

   Where to Approximate in Neurosymbolic Inference?

   Samy Badreddine, Emile van Krieken, Luciano Serafini, and 1 more author

   In The 2nd Workshop on Connecting Low-rank Representations in AI (CoLoRAI) at the International Conference on Machine Learning (ICML), 2026

   HTML

2025

1. IJCAI

   Rewarding Explainability in Drug Repurposing with Knowledge Graphs

   Susana Nunes, Samy Badreddine, and Cátia Pesquita

   In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25), 2025

   Abs arXiv Code

   Knowledge graphs (KGs) are powerful tools for modelling complex, multi-relational data and supporting hypothesis generation, particularly in applications like drug repurposing. However, for predictive methods to gain acceptance as credible scientific tools, they must ensure not only accuracy but also the capacity to offer meaningful scientific explanations. This paper presents a novel approach REx, for generating scientific explanations based in link prediction in knowledge graphs. It employs reward and policy mechanisms that consider desirable properties of scientific explanation to guide a reinforcement learning agent in the identification of explanatory paths within a KG. The approach further enriches explanatory paths with domain-specific ontologies, ensuring that the explanations are both insightful and grounded in established biomedical knowledge. We evaluate our approach in drug repurposing using three popular knowledge graph benchmarks. The results clearly demonstrate its ability to generate explanations that validate predictive insights against biomedical knowledge and that outperform the state-of-the-art approaches in predictive performance, establishing REx as a relevant contribution to advance AI-driven scientific discovery.

2. AI4X

   Literature-based Hypothesis Generation: Predicting the Evolution of Scientific Literature to Support Scientists

   Tarek R Besold, Uchenna Akujuobi, Samy Badreddine, and 4 more authors

   In AI4X 2025 International Conference, 2025

2024

1. AIR

   Link prediction for hypothesis generation: an active curriculum learning infused temporal graph-based approach

   Uchenna Akujuobi, Priyadarshini Kumari, Jihun Choi, and 4 more authors

   Artificial Intelligence Review, 2024
2. NeSy (SPOTLIGHT)

   ULLER: A Unified Language for Learning and Reasoning

   Emile van Krieken, Samy Badreddine, Robin Manhaeve, and 1 more author

   In 18th International Conference on Neural-Symbolic Learning and Reasoning, 2024

   Abs arXiv

   The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks , each with its own specific language for expressing background knowledge and how to relate it to neural networks. This heterogeneity hinders accessibility for newcomers and makes comparing different NeSy frameworks challenging. We propose a unified language for NeSy, which we call ULLER, a Unified Language for LEarning and Reasoning. ULLER encompasses a wide variety of settings, while ensuring that knowledge described in it can be used in existing NeSy systems. ULLER has a neuro-symbolic first-order syntax for which we provide example semantics including classical, fuzzy, and probabilistic logics. We believe ULLER is a first step towards making NeSy research more accessible and comparable, paving the way for libraries that streamline training and evaluation across a multitude of semantics, knowledge bases, and NeSy systems.

2023

1. Expert Syst. Appl.

   KitchenScale: Learning to predict ingredient quantities from recipe contexts

   Donghee Choi, Mogan Gim, Samy Badreddine, and 3 more authors

   Expert Systems with Applications, 2023
2. ICCC

   Recipe 2.0: Information Presentation for AI-Supported Culinary Idea Generation

   Angel Hwang, Samy Badreddine, Frederick Gifford, and 1 more author

   In Proceedings of the 14th International Conference on Computational Creativity (ICCC), 2023
3. NeSy (BEST PAPER)

   What’s Wrong with Gradient-based Complex Query Answering?

   Ouns El Harzli, Samy Badreddine, and Tarek R Besold

   In NeSy, 2023
4. Plos one

   Comparing molecular representations, e-nose signals, and other featurization, for learning to smell aroma molecules

   Tanoy Debnath, Samy Badreddine, Priyadarshini Kumari, and 1 more author

   Plos one, 2023
5. arXiv

   logLTN: Differentiable Fuzzy Logic in the Logarithm Space

   Samy Badreddine, Luciano Serafini, and Michael Spranger

   arXiv preprint arXiv:2306.14546, 2023

   Abs arXiv

   The AI community is increasingly focused on merging logic with deep learning to create Neuro-Symbolic (NeSy) paradigms and assist neural approaches with symbolic knowledge. A significant trend in the literature involves integrating axioms and facts in loss functions by grounding logical symbols with neural networks and operators with fuzzy semantics. Logic Tensor Networks (LTN) is one of the main representatives in this category, known for its simplicity, efficiency, and versatility. However, it has been previously shown that not all fuzzy operators perform equally when applied in a differentiable setting. Researchers have proposed several configurations of operators, trading off between effectiveness, numerical stability, and generalization to different formulas. This paper presents a configuration of fuzzy operators for grounding formulas end-to-end in the logarithm space. Our goal is to develop a configuration that is more effective than previous proposals, able to handle any formula, and numerically stable. To achieve this, we propose semantics that are best suited for the logarithm space and introduce novel simplifications and improvements that are crucial for optimization via gradient-descent. We use LTN as the framework for our experiments, but the conclusions of our work apply to any similar NeSy framework. Our findings, both formal and empirical, show that the proposed configuration outperforms the state-of-the-art and that each of our modifications is essential in achieving these results.

2022

1. AI Journal

   Logic tensor networks

   Samy Badreddine, Artur d’Avila Garcez, Luciano Serafini, and 1 more author

   Artificial Intelligence, 2022

   Abs Code

   Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art learning from data typically uses sub-symbolic distributed representations, reasoning is normally useful at a higher level of abstraction with the use of a first-order logic language for knowledge representation. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been on the increase. In this paper, we present Logic Tensor Networks (LTN), a neurosymbolic formalism and computational model that supports learning and reasoning through the introduction of a many-valued, end-to-end differentiable first-order logic called Real Logic as a representation language for deep learning. We show that LTN provides a uniform language for the specification and the computation of several AI tasks such as data clustering, multi-label classification, relational learning, query answering, semi-supervised learning, regression and embedding learning. We implement and illustrate each of the above tasks with a number of simple explanatory examples using TensorFlow 2.

2021

1. NeSy

   Extending Real Logic with Aggregate Functions.

   Samy Badreddine, and Michael Spranger

   In NeSy, 2021
2. Book chapter

   Logic tensor networks: Theory and applications

   Luciano Serafini, Artur Garcez, Samy Badreddine, and 3 more authors

   In Neuro-Symbolic Artificial Intelligence: The State of the Art, 2021

2019

1. NeSy

   Injecting prior knowledge for transfer learning into reinforcement learning algorithms using logic tensor networks

   Samy Badreddine, and Michael Spranger

   arXiv preprint arXiv:1906.06576, 2019