Luc De Raedt

• KU Leuven

Large language models have been used to translate natural language questions to SQL queries. Without hard constraints on syntax and database schema, they occasionally produce invalid queries that are not executable. These failures limit the usage of these systems in real-life scenarios. We propose a neurosymbolic framework that imposes SQL syntax a...

Neurosymbolic (NeSy) AI studies the integration of neural networks (NNs) and symbolic reasoning based on logic. Usually, NeSy techniques focus on learning the neural, probabilistic and/or fuzzy parameters of NeSy models. Learning the symbolic or logical structure of such models has, so far, received less attention. We introduce neurosymbolic decisi...

Algebraic model counting unifies many inference tasks on logic formulas by exploiting semirings. Rather than focusing on inference, we consider learning, especially in statistical-relational and neurosymbolic AI, which combine logical, probabilistic and neural representations. Concretely, we show that the very same semiring perspective of algebraic...

Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to...

Recent developments in AI have reinvigorated pursuits to advance the (life) sciences using AI techniques, thereby creating a renewed opportunity to bridge different fields and find synergies. Headlines for AI and the life sciences have been dominated by data-driven techniques, for instance, to solve protein folding with next to no expert knowledge....

Recent developments in AI have reinvigorated pursuits to advance the (life) sciences using AI techniques, thereby creating a renewed opportunity to bridge different fields and find synergies. Headlines for AI and the life sciences have been dominated by data-driven techniques, for instance, to solve protein folding with next to no expert knowledge....

Neural probabilistic logic systems follow the neuro-symbolic (NeSy) paradigm by combining the perceptive and learning capabilities of neural networks with the robustness of probabilistic logic. Learning corresponds to likelihood optimization of the neural networks. However, to obtain the likelihood exactly, expensive probabilistic logic inference i...

Neural probabilistic logic systems follow the neuro-symbolic (NeSy) paradigm by combining the perceptive and learning capabilities of neural networks with the robustness of probabilistic logic. Learning corresponds to likelihood optimization of the neural networks. However, to obtain the likelihood exactly, expensive probabilistic logic inference i...

Large Language Models (LLMs) are said to possess advanced reasoning abilities. However, some skepticism exists as recent works show how LLMs often bypass true reasoning using shortcuts. Current methods for assessing the reasoning abilities of LLMs typically rely on open-source benchmarks that may be overrepresented in LLM training data, potentially...

The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with gradient descent, we study the complexity of differentiating probabilistic reasoning. We prove that although approximating these...

While Graph Neural Networks (GNNs) are state-of-the-art models for graph learning, they are only as expressive as the first-order Weisfeiler-Leman graph isomorphism test algorithm. To enhance their expressiveness one can incorporate complex structural information as attributes of the nodes in input graphs. However, this typically demands significan...

Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge". Yet, obtaining plans that are both feasible (grounded in affordances) and cost-effective (in plan length), remains a challenge, despite recent progress. This contrasts with heuristic planning methods that employ domain knowledge (formal...

Decision making under uncertainty in dynamic environments is a fundamental AI problem in which agents need to determine which decisions (or actions) to make at each time step to maximise their expected utility. Dynamic decision networks (DDNs) are an extension of dynamic Bayesian networks with decisions and utilities. DDNs can be used to compactly...

The goal of learning from positive and unlabeled (PU) examples is to learn a classifier that predicts the posterior class probability. The challenge is that the available labels in the data are determined by (1) the true class, and (2) the labeling mechanism that selects which positive examples get labeled, where often certain examples have a highe...

Despite its successes, Deep Reinforcement Learning (DRL) yields non-interpretable policies. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with structural changes in its environment (such as increasing the number of objects). Meanwhile, Relational Reinforcement Learning inherits the relationa...

Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge". Yet, obtaining plans that are both feasible (grounded in affordances) and cost-effective (in plan length), remains a challenge, despite recent progress. This contrasts with heuristic planning methods that employ domain knowledge (formal...

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However, traditional shielding techniques are difficult to integrate with continuous, end-to-end deep RL methods. To this...

Statistical relational AI and probabilistic logic programming have so far mostly focused on discrete probabilistic models. The reasons for this is that one needs to provide constructs to succinctly model the independencies in such models, and also provide efficient inference. Three types of independencies are important to represent and exploit for...

Despite numerous successes in Deep Reinforcement Learning (DRL), the learned policies are not interpretable. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with structural changes in its environment (such as increasing the number of objects). Relational Reinforcement Learning, on the other ha...

Argumentation problems are concerned with determining the acceptability of a set of arguments from their relational structure. When the available information is uncertain, probabilistic argumentation frameworks provide modelling tools to account for it. The first contribution of this paper is a novel interpretation of probabilistic argumentation fr...

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However, traditional shielding techniques are difficult to integrate with continuous, end-to-end deep RL methods. To this...

Over the past three decades, the logic programming paradigm has been successfully expanded to support probabilistic modeling, inference and learning. The resulting paradigm of probabilistic logic programming (PLP) and its programming languages owes much of its success to a declarative semantics, the so-called distribution semantics. However, the di...

Combinatorics math problems are often used as a benchmark to test human cognitive and logical problem-solving skills. These problems are concerned with counting the number of solutions that exist in a specific scenario that is sketched in natural language. Humans are adept at solving such problems as they can identify commonly occurring structures...

We propose a framework for learning a fragment of probabilistic computation tree logic (pCTL) formulae from a set of states that are labeled as safe or unsafe. We work in a relational setting and combine ideas from relational Markov Decision Processes with pCTL model-checking. More specifically, we assume that there is an unknown relational pCTL ta...

Combinatorial optimization problems are ubiquitous in artificial intelligence. Designing the underlying models, however, requires substantial expertise, which is a limiting factor in practice. The models typically consist of hard and soft constraints, or combine hard constraints with an objective function. We introduce a novel setting for learning...

Recent advances in neural-symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose DeepStochLog, an alternative neural-symbolic framework...

An issue that has so far received only limited attention in probabilistic logic programming (PLP) is the modelling of so-called epistemic uncertainty, the uncertainty about the model itself. Accurately quantifying this model uncertainty is paramount to robust inference, learning and ultimately decision making. We introduce BetaProbLog, a PLP langua...

Probabilistic model checking has been developed for verifying systems that have stochastic and nondeterministic behavior. Given a probabilistic system, a probabilistic model checker takes a property and checks whether or not the property holds in that system. For this reason, probabilistic model checking provide rigorous guarantees. So far, however...

Motivation Network-based driver identification methods that can exploit mutual exclusivity typically fail to detect rare drivers because of their statistical rigor. Propagation-based methods in contrast allow recovering rare driver genes, but the interplay between network topology and high-scoring nodes often results in spurious predictions. The sp...

Given the complexity of data science projects and related demand for human expertise, automation has the potential to transform the data science process.

Combinatorial optimisation problems are ubiquitous in artificial intelligence. Designing the underlying models, however, requires substantial expertise, which is a limiting factor in practice. The models typically consist of hard and soft constraints, or combine hard constraints with an objective function. We introduce a novel setting for learning...

Statistical relational AI and probabilistic logic programming have so far mostly focused on discrete probabilistic models. The reasons for this is that one needs to provide constructs to succinctly model the independencies in such models, and also provide efficient inference. Three types of independencies are important to represent and exploit for...

There is a broad consensus that both learning and reasoning are essential to achieve true artificial intelligence. This has put the quest for neural-symbolic artificial intelligence (NeSy) high on the research agenda. In the past decade, neural networks have caused great advances in the field of machine learning. Conversely, the two most prominent...

We introduce SMProbLog, a generalization of the probabilistic logic programming language ProbLog. A ProbLog program defines a distribution over logic programs by specifying for each clause the probability that it belongs to a randomly sampled program, and these probabilities are mutually independent. The semantics of ProbLog is given by the success...

We present Probabilistic Decision Model and Notation (pDMN), a probabilistic extension of Decision Model and Notation (DMN). DMN is a modeling notation for deterministic decision logic, which intends to be user-friendly and low in complexity. pDMN extends DMN with probabilistic reasoning, predicates, functions, quantification, and a new hit policy....

Designers increasingly rely on procedural generation for automatic generation of content in various industries. These techniques require extensive knowledge of the desired content, and about how to actually implement such procedural methods. Algorithms for learning interpretable generative models from example content could alleviate both difficulti...

Data comes in different formats in the real world and often requires data wrangling before a machine learning technique can use it. Users are expected to make sure these requirements are satisfied. Constraint satisfaction problems (CSPs) are widely used to model various real-world problems, such as scheduling or planning. Unfortunately, en-coding a...

DeepProbLog is a neural-symbolic framework that integrates probabilistic logic programming and neural networks. It is realized by providing an interface between the probabilistic logic and the neural networks. Inference in probabilistic neural symbolic methods is hard, since it combines logical theorem proving with probabilistic inference and neura...

Relational autocompletion is the problem of automatically filling out some missing values in multi-relational data. We tackle this problem within the probabilistic logic programming framework of Distributional Clauses (DCs), which supports both discrete and continuous probability distributions. Within this framework, we introduce DiceML – an approa...

This survey explores the integration of learning and reasoning in two different fields of artificial intelligence: neurosymbolic and statistical relational artificial intelligence. Neurosymbolic artificial intelligence (NeSy) studies the integration of symbolic reasoning and neural networks, while statistical relational artificial intelligence (Sta...

We revisit the problem of learning logical theories from examples, one of the most quintessential problems in machine learning. More specifically, we develop an approach to learn CNF-formulae from satisfiability. This is a setting in which the examples correspond to partial interpretations and an example is classified as positive when it is logical...

Mixed-integer linear programs (MILPs) are widely used in artificial intelligence and operations research to model complex decision problems like scheduling and routing. Designing such programs however requires both domain and modelling expertise. In this paper, we study the problem of acquiring MILPs from contextual examples, a novel and realistic...

Everybody wants to analyse their data, but only few posses the data science expertise to do this. Motivated by this observation, we introduce a novel framework and system VisualSynth for human-machine collaboration in data science. Its aim is to democratize data science by allowing users to interact with standard spreadsheet software in order to pe...

Recent advances in neural symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose DeepStochLog, an alternative neural symbolic framework...

Our goal in the frame of this project is to automate data science. To do so we combine multiple components in a single interactive framework called VisualSYNTH designed primarily to run in Spreadsheet Environments. VisualSYNTH, a framework that wants to democratize data science by enabling naive end-users to specify the data science tasks that matc...

Constraint satisfaction problems (CSPs) are used widely, especially in the field of operations research, to model various real world problems like scheduling or planning. However,modelling a problem as a CSP is not trivial, it is labour intensive and requires both modelling and domain expertise. The emerging field of constraint learning deals with...

Given the complexity of typical data science projects and the associated demand for human expertise, automation has the potential to transform the data science process. Key insights: * Automation in data science aims to facilitate and transform the work of data scientists, not to replace them. * Important parts of data science are already being aut...

A large part of the time invested in data science is spent on manual preparation of data. Transforming wrongly formatted columns into useful features takes up a significant part of this time. We present the avatar algorithm for automatically learning programs that perform this type of feature wrangling. Instead of relying on users to guide the wran...

Valuable data are often spread out over different similar spreadsheets. Consolidating this data for further analysis can take considerable effort for a spreadsheet user without programming skills. We introduce Spreadsheet Layout Constraint Integration (SpLyCI), a system to semi-automatically merge multiple spreadsheets and lay the result out in a s...

We present muppets, a framework for partitioning cells in a table in segments that fulfil the same semantic role or belong to the same semantic data type, similar to how image segmentation is used to group pixels that represent the same semantic object in computer vision. Flexible constraints can be imposed on these segmentations for different use...

We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that...

We introduce VisualSynth, a framework that wants to democratize data science by enabling naive end-users to specify the data science tasks that match their needs. In VisualSynth, the user and the spreadsheet application interact by highlighting parts of the data using colors. The colors define a partial specification of a data science task (such as...

To solve hard problems, AI relies on a variety of disciplines such as logic, probabilistic reasoning, machine learning and mathematical programming. Although it is widely accepted that solving real-world problems requires an integration amongst these, contemporary representation methodologies offer little support for this. In an attempt to alleviat...

Robotic agents should be able to learn from sub-symbolic sensor data and, at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a semantic world modeling approach based on bottom-up o...

Background We need high-quality data to assess the determinants for COVID-19 severity in people with MS (PwMS). Several studies have recently emerged but there is great benefit in aligning data collection efforts at a global scale. Objectives Our mission is to scale-up COVID-19 data collection efforts and provide the MS community with data-driven...

Modeling object representations derived from perceptual observations, in a way that is also semantically meaningful for humans as well as autonomous agents, is a prerequisite for joint human-agent understanding of the world. A practical approach that aims to model such representations is perceptual anchoring, which handles the problem of mapping su...

Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to ide...

Modeling object representations derived from perceptual observations, in a way that is also semantically meaningful for humans as well as autonomous agents, is a prerequisite for joint human-agent understanding of the world. A practical approach that aims to model such representations is perceptual anchoring, which handles the problem of mapping su...

Everybody wants to analyse their data, but only few posses the data science expertise to to this. Motivated by this observation we introduce a novel framework and system \textsc{VisualSynth} for human-machine collaboration in data science. It wants to democratize data science by allowing users to interact with standard spreadsheet software in order...

Combinatorial optimization problems are ubiquitous in artificial intelligence. Designing the underlying models, however, requires substantial expertise, which is a limiting factor in practice. The models typically consist of hard and soft constraints, or combine hard constraints with a preference function. We introduce a novel setting for learning...

We introduce SynthLog, an extension of the probabilistic logic programming language ProbLog, for synthesising inductive data models. Inductive data models integrate data with predictive and descriptive models, in a way that is reminiscent of inductive databases. SynthLog provides primitives for learning and manipulating inductive data models, it su...

Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to ide...

Robotic agents should be able to learn from sub-symbolic sensor data, and at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a semantic world modeling approach based on bottom-up o...

Spreadsheets are arguably the most accessible data-analysis tool and are used by millions of people. Despite the fact that they lie at the core of most business practices, working with spreadsheets can be error prone, usage of formulas requires training and, crucially, spreadsheet users do not have access to state-of-the-art analysis techniques off...

While any grasp must satisfy the grasping stability criteria, good grasps depend on the specific manipulation scenario: the object, its properties and functionalities, as well as the task and grasp constraints. We propose a probabilistic logic approach for robot grasping, which improves grasping capabilities by leveraging semantic object parts. It...

Integer programming (IP) is widely used within operations research to model and solve complex combinatorial problems such as personnel rostering and assignment problems. Modelling such problems is difficult for non-experts and expensive when hiring domain experts to perform the modelling. For many tasks, however, examples of working solutions are r...

Weighted Model Integration (WMI) is a popular technique for probabilistic inference that extends Weighted Model Counting (WMC) -- the standard inference technique for inference in discrete domains -- to domains with both discrete and continuous variables. However, existing WMI solvers each have different interfaces and use different formats for rep...

We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that...

Weighted model counting has recently been extended to weighted model integration, which can be used to solve hybrid probabilistic reasoning problems. Such problems involve both discrete and continuous probability distributions. We show how standard knowledge compilation techniques (to SDDs and d-DNNFs) apply to weighted model integration, and use i...

This paper addresses the topic of semantic world modeling by conjoining probabilistic reasoning and object anchoring. The proposed approach uses a so-called bottom-up object anchoring method that relies on rich continuous attribute values measured from perceptual sensor data. A novel anchoring matching function learns to maintain object entities in...

Human-robot interaction often occurs in the form of instructions given from a human to a robot. For a robot to successfully follow instructions, a common representation of the world and objects in it should be shared between humans and the robot so that the instructions can be grounded. Achieving this representation can be done via learning, where...

Human-robot interaction often occurs in the form of instructions given from a human to a robot. For a robot to successfully follow instructions, a common representation of the world and objects in it should be shared between humans and the robot so that the instructions can be grounded. Achieving this representation can be done via learning, where...

This paper addresses the topic of semantic world modeling by conjoining probabilistic reasoning and object anchoring. The proposed approach uses a so-called bottom-up object anchoring method that relies on the rich continuous data from perceptual sensor data. A novel anchoring matching function method learns to maintain object entities in space and...

Dynamic models analyzing gene regulation and metabolism face challenges when adapted to modeling signal transduction networks. During signal transduction, molecular reactions and mechanisms occur in different spatial and temporal frames and involve feedbacks. This impedes the straight-forward use of methods based on Boolean networks, Bayesian appro...

A simple but non-trivial setting for automating data science is introduced. Given are a set of worksheets in a spreadsheet and the goal is to automatically complete some values. We also outline elements of the Synth framework that tackles this task: Synth-a-Sizer, an automated data wrangling system for automatically transforming the problem into at...

To help automate the important pre-processing step in machine learning and data mining, we introduce synth-a-sizer, a tool for semi-automatically wrangling spreadsheets into attribute-value format, so that they can be used by popular machine learning tools, only requiring the user to mark cells belonging to one single example. synth-a-sizer is base...

In probabilistic reasoning, the traditionally discrete domain has been elevated to the hybrid domain encompassing additionally continuous random variables. Inference in the hybrid domain, however, usually necessitates to condone trade-offs on either the inference on discrete or continuous random variables. We introduce a novel approach based on wei...

We introduce the problem of learning SMT(LRA) constraints from data. SMT(LRA) extends propositional logic with (in)equalities between numerical variables. Many relevant formal verification problems can be cast as SMT(LRA) instances and SMT(LRA) has supported recent developments in optimization and counting for hybrid Boolean and numerical domains....

Many problems in operations research require that constraints be specified in the model. Determining the right constraints is a hard and laborsome task. We propose an approach to automate this process using artificial intelligence and machine learning principles. So far there has been only little work on learning constraints within the operations r...

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques can be adapted for the new language. Our experiments demonstrate that DeepProbLog supports both symbolic and subsymbolic representations and inference, 1) program...

While constraints are ubiquitous in artificial intelligence and constraints are also commonly used in machine learning and data mining, the problem of learning constraints from examples has received less attention. In this paper, we discuss the problem of constraint learning in detail, indicate some subtle differences with standard machine learning...

The concept of affordances has been used in robotics to model action opportunities of a robot and as a basis for making decisions involving objects. Affordances capture the interdependencies between the objects and their properties, the executed actions on those objects, and the effects of those respective actions. However, existing affordance mode...

Motivated by an analogy with matrix factorization, we introduce the problem of factorizing relational data. In matrix factorization, one is given a matrix and has to factorize it as a product of other matrices. In relational data factorization, the task is to factorize a given relation as a conjunctive query over other relations, i.e., as a combina...

We study planning in relational Markov decision processes involving discrete and continuous states and actions, and an unknown number of objects. This combination of hybrid relational domains has so far not received a lot of attention. While both relational and hybrid approaches have been studied separately, planning in such domains is still challe...

We introduce kProbLog as a declarative logical language for machine learning. kProbLog is a simple algebraic extension of Prolog with facts and rules annotated by semi-ring labels. It allows to elegantly combine algebraic expressions with logic programs. We introduce the semantics of kProbLog, its inference algorithm, its implementation and provide...

Spreadsheet data is widely used today by many different people and across industries. However, writing, maintaining and identifying good formulae for spreadsheets can be time consuming and error-prone. To address this issue we have introduced the TaCLe system (Tabular Constraint Learner). The system tackles an inverse learning problem: given a plai...

Pattern sampling has been proposed as a potential solution to the infamous pattern explosion. Instead of enumerating all patterns that satisfy the constraints, individual patterns are sampled proportional to a given quality measure. Several sampling algorithms have been proposed, but each of them has its limitations when it comes to 1) flexibility...