Search or filter publications

Filter by type:

Filter by publication type

Filter by year:

to

Results

  • Showing results for:
  • Reset all filters

Search results

  • Conference paper
    Mihailescu I, Weng A, Sharma S, Ghitu M, Grewal D, Chew K, Ayoobi H, Potyka N, Toni Fet al., 2023,

    PySpArX - A Python library for generating Sparse Argumentative eXplanations for neural networks

    , ICLP 2023, Publisher: Open Publishing Association, Pages: 336-336, ISSN: 2075-2180
  • Conference paper
    Proietti M, Toni F, 2023,

    A roadmap for neuro-argumentative learning

    , 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2023), Publisher: CEUR Workshop Proceedings, Pages: 1-8, ISSN: 1613-0073

    Computational argumentation (CA) has emerged, in recent decades, as a powerful formalism for knowl-edge representation and reasoning in the presence of conflicting information, notably when reasoningnon-monotonically with rules and exceptions. Much existing work in CA has focused, to date, on rea-soning with given argumentation frameworks (AFs) or, more recently, on using AFs, possibly automat-ically drawn from other systems, for supporting forms of XAI. In this short paper we focus insteadon the problem of learning AFs from data, with a focus on neuro-symbolic approaches. Specifically,we overview existing forms of neuro-argumentative (machine) learning, resulting from a combinationof neural machine learning mechanisms and argumentative (symbolic) reasoning. We include in ouroverview neuro-symbolic paradigms that integrate reasoners with a natural understanding in argumen-tative terms, notably those capturing forms of non-monotonic reasoning in logic programming. We alsooutline avenues and challenges for future work in this spectrum.
  • Conference paper
    Potyka N, Yin X, Toni F, 2023,

    Explaining random forests using bipolar argumentation and Markov networks

    , AAAI 23, Pages: 9458-9460, ISSN: 2159-5399

    Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. We show that their decision process can be naturally represented as an argumentation problem, which allows creating global explanations via argumentative reasoning. We generalize sufficientand necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the explanation problems is high, we present an efficient approximation algorithm with probabilistic approximation guarantees.
  • Conference paper
    Jiang J, Leofante F, Rago A, Toni Fet al., 2023,

    Formalising the robustness of counterfactual explanations for neural networks

    , 37th AAAI Conference on Artificial Intelligence (AAAI 2023), Publisher: Association for the Advancement of Artificial Intelligence, Pages: 14901-14909, ISSN: 2374-3468

    The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanations may not be robust to changes in the underlying model (e.g., following retraining), which raises questions about their reliability in real-world applications. Existing attempts towards solving this problem are heuristic, and the robustness to model changes of the resulting CFXs is evaluated with only a small number of retrained models, failing to provide exhaustive guarantees. To remedy this, we propose the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks, that we call ∆-robustness. We introduce an abstraction framework based on interval neural networks to verify the ∆-robustness of CFXs against a possibly infinite set of changes to the model parameters, i.e., weights and biases. We then demonstrate the utility of this approach in two distinct ways. First, we analyse the ∆-robustness of a number of CFX generation methods from the literature and show that they unanimously host significant deficiencies in this regard. Second, we demonstrate how embedding ∆-robustness within existing methods can provide CFXs which are provably robust.
  • Conference paper
    Nguyen H-T, Goebel R, Toni F, Stathis K, Satoh Ket al., 2023,

    How well do SOTA legal reasoning models support abductive reasoning?

    , Logic Programming and Legal Reasoning Workshop@ICLP2023

    We examine how well the state-of-the-art (SOTA) models used in legal reasoning support abductivereasoning tasks. Abductive reasoning is a form of logical inference in which a hypothesis is formulatedfrom a set of observations, and that hypothesis is used to explain the observations. The ability toformulate such hypotheses is important for lawyers and legal scholars as it helps them articulate logicalarguments, interpret laws, and develop legal theories. Our motivation is to consider the belief thatdeep learning models, especially large language models (LLMs), will soon replace lawyers because theyperform well on tasks related to legal text processing. But to do so, we believe, requires some form ofabductive hypothesis formation. In other words, while LLMs become more popular and powerful, wewant to investigate their capacity for abductive reasoning. To pursue this goal, we start by building alogic-augmented dataset for abductive reasoning with 498,697 samples and then use it to evaluate theperformance of a SOTA model in the legal field. Our experimental results show that although thesemodels can perform well on tasks related to some aspects of legal text processing, they still fall short insupporting abductive reasoning tasks.
  • Conference paper
    Paulino Passos G, Satoh K, Toni F, 2023,

    A Dataset of Contractual Events in Court Decisions

    , Logic Programming and Legal Reasoning Workshop @ ICLP 2023

    The promise of automation of legal reasoning is developing technology that reduces human time required for legal tasks or that improves human performance on such tasks. In order to do so, different methods and systems based on logic programming were developed. However, in order to apply such methods on legal data, it is necessary to provide an interface between human users and the legal reasoning system, and the most natural interface in the legal domain is natural language, in particular, written text. In order to perform reasoning in written text using logic programming methods, it is then necessary to map expressions in text to atoms and predicates in the formal language, a task referred generally as information extraction. In this work, we propose a new dataset for the task of information extraction, in particular event extraction, in court decisions, focusing on contracts. Our dataset captures contractual relations and events that affect them in some way, such as negotiations preceding a (possible) contract, the execution of a contract, or its termination. We conducted text annotation with law students and graduates, resulting in a dataset with 207 documents, 3934 sentences, 4627 entities, and 1825 events. We describe here this resource, the annotation process, its evaluation with inter-annotator agreement metrics, and discuss challenges during the development of this resource and for the future.
  • Conference paper
    Nguyen H-T, Toni F, Stathis K, Satoh Ket al., 2023,

    Beyond Logic Programming for Legal Reasoning

    , Logic Programming and Legal Reasoning Workshop@ICLP2023

    Logic programming has long being advocated for legal reasoning, and several approaches have been putforward relying upon explicit representation of the law in logic programming terms. In this positionpaper we focus on the PROLEG logic-programming-based framework for formalizing and reasoningwith Japanese presupposed ultimate fact theory. Specifically, we examine challenges and opportunitiesin leveraging deep learning techniques for improving legal reasoning using PROLEG, identifying fourdistinct options ranging from enhancing fact extraction using deep learning to end-to-end solutionsfor reasoning with textual legal descriptions. We assess advantages and limitations of each option,considering their technical feasibility, interpretability, and alignment with the needs of legal practitionersand decision-makers. We believe that our analysis can serve as a guideline for developers aiming tobuild effective decision-support systems for the legal domain, while fostering a deeper understanding ofchallenges and potential advancements by neuro-symbolic approaches in legal applications.
  • Journal article
    Lertvittayakumjorn P, Toni F, 2023,

    Argumentative explanations for pattern-based text classifiers

    , Argument and Computation, Vol: 14, Pages: 163-234, ISSN: 1946-2174

    Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not consider relations among the features, making the explanations hardly plausible to humans. Hence, we propose AXPLR, a novel explanation method using (forms of) computational argumentation to generate explanations (for outputs computed by PLR) which unearth model agreements and disagreements among the features. Specifically, we use computational argumentation as follows: we see features (patterns) in PLR as arguments in a form of quantified bipolar argumentation frameworks (QBAFs) and extract attacks and supports between arguments based on specificity of the arguments; we understand logistic regression as a gradual semantics for these QBAFs, used to determine the arguments’ dialectic strength; and we study standard properties of gradual semantics for QBAFs in the context of our argumentative re-interpretation of PLR, sanctioning its suitability for explanatory purposes. We then show how to extract intuitive explanations (for outputs computed by PLR) from the constructed QBAFs. Finally, we conduct an empirical evaluation and two experiments in the context of human-AI collaboration to demonstrate the advantages of our resulting AXPLR method.
  • Conference paper
    Leofante F, Lomuscio A, 2023,

    Towards robust contrastive explanations for human-neural multi-agent systems

    , International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023), Publisher: ACM, Pages: 2343-2345

    Generating explanations of high quality is fundamental to the development of trustworthy human-AI interactions. We here study the problem of generating contrastive explanations with formal robustness guarantees. We formalise a new notion of robustness and introduce two novel verification-based algorithms to (i) identify non-robust explanations generated by other methods and (ii) generate contrastive explanations augmented with provablerobustness certificates. We present an implementation and evaluate the utility of the approach on two case studies concerning neural agents trainedon credit scoring and image classification tasks.
  • Journal article
    Rago A, Russo F, Albini E, Toni F, Baroni Pet al., 2023,

    Explaining classifiers’ outputs with causal models and argumentation

    , Journal of Applied Logics, Vol: 10, Pages: 421-449, ISSN: 2631-9810

    We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for mod-els’ outputs. The conceptualisation is based on reinterpreting properties of semantics of AFs as explanation moulds, which are means for characterising argumentative relations. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement in bipolar AFs, showing how the ex-tracted bipolar AFs may be used as relation-based explanations for the outputs of causal models. We then evaluate our method empirically when the causal models represent (Bayesian and neural network) machine learning models for classification. The results show advantages over a popular approach from the literature, both in highlighting specific relationships between feature and classification variables and in generating counterfactual explanations with respect to a commonly used metric.
  • Conference paper
    Santhirasekaram A, Kori A, Winkler M, Rockall A, Toni F, Glocker Bet al., 2023,

    Robust Hierarchical Symbolic Explanations in Hyperbolic Space for Image Classification

    , Computer Vision and Pattern Recognition
  • Journal article
    Albini E, Rago A, Baroni P, Toni Fet al., 2023,

    Achieving descriptive accuracy in explanations via argumentation: the case of probabilistic classifiers

    , Frontiers in Artificial Intelligence, Vol: 6, Pages: 1-18, ISSN: 2624-8212

    The pursuit of trust in and fairness of AI systems in order to enable human-centric goals has been gathering pace of late, often supported by the use of explanations for the outputs of these systems. Several properties of explanations have been highlighted as critical for achieving trustworthy and fair AI systems, but one that has thus far been overlooked is that of descriptive accuracy (DA), i.e., that the explanation contents are in correspondence with the internal working of the explained system. Indeed, the violation of this core property would lead to the paradoxical situation of systems producing explanations which are not suitably related to how the system actually works: clearly this may hinder user trust. Further, if explanations violate DA then they can be deceitful, resulting in an unfair behavior toward the users. Crucial as the DA property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalizing DA and of analyzing its satisfaction by explanation methods. We provide formal definitions of naive, structural and dialectical DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature, variants thereof and a novel form of explanation that we propose. We conduct experiments with a varied selection of concrete probabilistic classifiers and highlight the importance, with a user study, of our most demanding notion of dialectical DA, which our novel method satisfies by design and others may violate. We thus demonstrate how DA could be a critical component in achieving trustworthy and fair systems, in line with the principles of human-centric AI.
  • Journal article
    Flageat M, Chalumeau F, Cully A, 2023,

    Empirical analysis of PGA-MAP-Elites for neuroevolution in uncertain domains

    , ACM Transactions on Evolutionary Learning and Optimization, Vol: 3, Pages: 1-32, ISSN: 2688-299X

    Quality-Diversity algorithms, among which MAP-Elites, have emerged as powerful alternatives to performance-only optimisation approaches as they enable generating collections of diverse and high-performing solutions to an optimisation problem. However, they are often limited to low-dimensional search spaces and deterministic environments. The recently introduced Policy Gradient Assisted MAP-Elites (PGA-MAP-Elites) algorithm overcomes this limitation by pairing the traditional Genetic operator of MAP-Elites with a gradient-based operator inspired by Deep Reinforcement Learning. This new operator guides mutations toward high-performing solutions using policy-gradients. In this work, we propose an in-depth study of PGA-MAP-Elites. We demonstrate the benefits of policy-gradients on the performance of the algorithm and the reproducibility of the generated solutions when considering uncertain domains. We first prove that PGA-MAP-Elites is highly performant in both deterministic and uncertain high-dimensional environments, decorrelating the two challenges it tackles. Secondly, we show that in addition to outperforming all the considered baselines, the collections of solutions generated by PGA-MAP-Elites are highly reproducible in uncertain environments, approaching the reproducibility of solutions found by Quality-Diversity approaches built specifically for uncertain applications. Finally, we propose an ablation and in-depth analysis of the dynamic of the policy-gradients-based variation. We demonstrate that the policy-gradient variation operator is determinant to guarantee the performance of PGA-MAP-Elites but is only essential during the early stage of the process, where it finds high-performing regions of the search space.
  • Conference paper
    Chalumeau F, Boige R, Lim BWT, Mace V, Allard M, Flajolet A, Cully A, Pierrot Tet al., 2023,

    Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

    , The 11th International Conference on Learning Representations (ICLR) 2023
  • Conference paper
    Surana S, Lim BWT, Cully A, 2023,

    Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors

    , IEEE International Conference on Robotics and Automation, ISSN: 2152-4092
  • Journal article
    Cheng S, Chen J, Anastasiou C, Angeli P, Matar OKK, Guo Y-K, Pain CCC, Arcucci Ret al., 2023,

    Generalised latent assimilation in heterogeneous reduced spaces with machine learning surrogate models

    , Journal of Scientific Computing, Vol: 94, Pages: 1-37, ISSN: 0885-7474

    Reduced-order modelling and low-dimensional surrogate models generated using machine learning algorithms have been widely applied in high-dimensional dynamical systems to improve the algorithmic efficiency. In this paper, we develop a system which combines reduced-order surrogate models with a novel data assimilation (DA) technique used to incorporate real-time observations from different physical spaces. We make use of local smooth surrogate functions which link the space of encoded system variables and the one of current observations to perform variational DA with a low computational cost. The new system, named generalised latent assimilation can benefit both the efficiency provided by the reduced-order modelling and the accuracy of data assimilation. A theoretical analysis of the difference between surrogate and original assimilation cost function is also provided in this paper where an upper bound, depending on the size of the local training set, is given. The new approach is tested on a high-dimensional (CFD) application of a two-phase liquid flow with non-linear observation operators that current Latent Assimilation methods can not handle. Numerical results demonstrate that the proposed assimilation approach can significantly improve the reconstruction and prediction accuracy of the deep learning surrogate model which is nearly 1000 times faster than the CFD simulation.
  • Conference paper
    Jiang J, Lan J, Leofante F, Rago A, Toni Fet al., 2023,

    Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation.

    , Publisher: PMLR, Pages: 582-597
  • Conference paper
    Nguyen HT, Goebel R, Toni F, Stathis K, Satoh Ket al., 2023,

    LawGiBa – Combining GPT, knowledge bases, and logic programming in a legal assistance system

    , JURIX 2023: The Thirty-sixth Annual Conference, Maastricht, the Netherlands, 18–20 December 2023, Publisher: IOS Press, Pages: 371-374, ISSN: 0922-6389

    We present LawGiBa, a proof-of-concept demonstration system for legal assistance that combines GPT, legal knowledge bases, and Prolog’s logic programming structure to provide explanations for legal queries. This novel combination effectively and feasibly addresses the hallucination issue of large language models (LLMs) in critical domains, such as law. Through this system, we demonstrate how incorporating a legal knowledge base and logical reasoning can enhance the accuracy and reliability of legal advice provided by AI models like GPT. Though our work is primarily a demonstration, it provides a framework to explore how knowledge bases and logic programming structures can be further integrated with generative AI systems, to achieve improved results across various natural languages and legal systems.
  • Journal article
    Leofante F, 2023,

    OMTPlan: a tool for optimal planning modulo theories

    , Journal of Satisfiability, Boolean Modeling and Computation, Vol: 14, Pages: 17-23, ISSN: 1574-0617

    OMTPlan is a Python platform for optimal planning in numeric domains via reductions to Satis -ability Modulo Theories (SMT) and OptimizationModulo Theories (OMT). Currently, OMTPlan supports the expressive power of PDDL2.1 level 2 andfeatures procedures for both satis cing and optimal planning. OMTPlan provides an open, easyto extend, yet e cient implementation framework.These goals are achieved through a modular designand the extensive use of state-of-the-art systemsfor SMT/OMT solving.
  • Journal article
    Gong H, Cheng S, Chen Z, Li Q, Quilodran-Casas C, Xiao D, Arcucci Ret al., 2022,

    An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physics

    , ANNALS OF NUCLEAR ENERGY, Vol: 179, ISSN: 0306-4549

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://www.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=989&limit=20&page=3&respub-action=search.html Current Millis: 1726903359230 Current Time: Sat Sep 21 08:22:39 BST 2024

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk

SUBSCRIBE: Join our AI Talks mailing list and keep up to date with the latest news
For enquiries about student positions, please contact members from our People page.