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
    Leofante F, Potyka N, 2023,

    Promoting Counterfactual Robustness through Diversity

    , The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI24)
  • Conference paper
    Zhang D, Williams M, Toni F, 2023,

    Targeted activation penalties help CNNs ignore spurious signals

    , The 38th Annual AAAI Conference on Artificial Intelligence, Publisher: AAAI, ISSN: 2159-5399

    Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional ground-truth annotations of such signals. These methods may, however, let spurious signals re-emerge in deep convolutional NNs (CNNs). We propose Targeted Activation Penalty (TAP), a new method tackling the same problem by penalising activations to control the re-emergence of spurious signals in deep CNNs, while also lowering training times and memory usage. In addition, ground-truth annotations can be expensive to obtain. We show that TAP still works well with annotations generated by pre-trained models as effective substitutes of ground-truth annotations. We demonstrate the power of TAP against two state-of-the-art baselines on the MNIST benchmark and on two clinical image datasets, using four different CNN architectures.

  • Conference paper
    Tirsi C-G, Proietti M, Toni F, 2023,

    ABALearn: an automated logic-based learning system for ABA frameworks

    , AIxIA 2023, Publisher: Springer Nature, ISSN: 1687-7470

    We introduce ABALearn, an automated algorithm that learns Assumption-Based Argumentation (ABA) frameworks from training data consisting of positive and negative examples, and a given background knowledge. ABALearn’s ability to generate comprehensible rules for decision-making promotes transparency and interpretability, addressing the challenges associated with the black-box nature of traditional machine learning models. This implementation is based on the strategy proposed in a previous work. The resulting ABA frameworks can be mapped onto logicprograms with negation as failure. The main advantage of this algorithm is that it requires minimal information about the learning problem and it is also capable of learning circular debates. Our results show that this approach is competitive with state-of-the-art alternatives, demonstrat-ing its potential to be used in real-world applications. Overall, this work contributes to the development of automated learning techniques for argumentation frameworks in the context of Explainable AI (XAI) andprovides insights into how such learners can be applied to make predictions.

  • Conference paper
    Paulino Passos G, Toni F, 2023,

    Learning Case Relevance in Case-Based Reasoning with Abstract Argumentation

    , The 36th International Conference on Legal Knowledge and Information Systems
  • Conference paper
    Russo F, Toni F, 2023,

    Causal discovery and knowledge injection for contestable neural networks

    , 26th European Conference on Artificial Intelligence ECAI 2023, Publisher: IOS Press, Pages: 2025-2032, ISSN: 0922-6389

    Neural networks have proven to be effective at solvingmachine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug them. We propose a novelmethod overcoming these issues by allowing a two-way interactionwhereby neural-network-empowered machines can expose the underpinning learnt causal graphs and humans can contest the machinesby modifying the causal graphs before re-injecting them into the machines, so that the learnt models are guaranteed to conform to thegraphs and adhere to expert knowledge (some of which can also begiven up-front). By building a window into the model behaviour andenabling knowledge injection, our method allows practitioners to debug networks based on the causal structure discovered from the dataand underpinning the predictions. Experiments with real and synthetic tabular data show that our method improves predictive performance up to 2.4x while producing parsimonious networks, up to 7xsmaller in the input layer, compared to SOTA regularised networks.

  • Journal article
    Delaney B, Dominguez J, Prociuk D, Toni F, Curcin V, Darzi A, Marovic B, Cyras K, Cocarascu O, Ruiz F, Mi E, Mi E, Ramtale C, Rago Aet al., 2023,

    ROAD2H: development and evaluation of an open-sourceexplainable artificial intelligence approach for managingco-morbidity and clinical guidelines

    , Learning Health Systems, ISSN: 2379-6146

    IntroductionClinical decision support (CDS) systems (CDSSs) that integrate clinical guidelines need to reflect real-world co-morbidity. In patient-specific clinical contexts, transparent recommendations that allow for contraindications and other conflicts arising from co-morbidity are a requirement. In this work, we develop and evaluate a non-proprietary, standards-based approach to the deployment of computable guidelines with explainable argumentation, integrated with a commercial electronic health record (EHR) system in Serbia, a middle-income country in West Balkans.MethodsWe used an ontological framework, the Transition-based Medical Recommendation (TMR) model, to represent, and reason about, guideline concepts, and chose the 2017 International global initiative for chronic obstructive lung disease (GOLD) guideline and a Serbian hospital as the deployment and evaluation site, respectively. To mitigate potential guideline conflicts, we used a TMR-based implementation of the Assumptions-Based Argumentation framework extended with preferences and Goals (ABA+G). Remote EHR integration of computable guidelines was via a microservice architecture based on HL7 FHIR and CDS Hooks. A prototype integration was developed to manage chronic obstructive pulmonary disease (COPD) with comorbid cardiovascular or chronic kidney diseases, and a mixed-methods evaluation was conducted with 20 simulated cases and five pulmonologists.ResultsPulmonologists agreed 97% of the time with the GOLD-based COPD symptom severity assessment assigned to each patient by the CDSS, and 98% of the time with one of the proposed COPD care plans. Comments were favourable on the principles of explainable argumentation; inclusion of additional co-morbidities was suggested in the future along with customisation of the level of explanation with expertise.ConclusionAn ontological model provided a flexible means of providing argumentation and explainable artificial intelligence for a long-term condition. Exte

  • 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

    , The 15th Asian Conference on Machine Learning
  • Conference paper
    Rago A, Gorur D, Toni F, 2023,

    ArguCast: a system for online multi-forecasting with gradual argumentation

    , Knowledge Representation 2023, Publisher: CEUR-WS.org, Pages: 40-51

    Judgmental forecasting is a form of forecasting which employs (human) users to make predictions about specied future events. Judgmental forecasting has been shown to perform better than quantitative methods for forecasting, e.g. when historical data is unavailable or causal reasoning is needed. However, it has a number of limitations, arising from users’ irrationality and cognitive biases. To mitigate against these phenomena, we leverage on computational argumentation, a eld which excels in the representation and resolution of conicting knowledge and human-like reasoning, and propose novel ArguCast frameworks (ACFs) and the novel online system ArguCast, integrating ACFs. ACFs and ArguCast accommodate multi-forecasting, by allowing multiple users to debate on multiple forecasting predictions simultaneously, each potentially admitting multiple outcomes. Finally, we propose a novel notion of user rationality in ACFs based on votes on arguments in ACFs, allowing the ltering out of irrational opinions before obtaining group forecasting predictions by means commonly used in judgmental forecasting.

  • Conference paper
    Kouvaros P, Leofante F, Edwards B, Chung C, Margineantu D, Lomuscio Aet al., 2023,

    Verification of semantic key point detection for aircraft pose estimation

    , The 20th International Conference on Principles of Knowledge Representation and Reasoning (KR2023), Publisher: IJCAI Organization, Pages: 757-762, ISSN: 2334-1033

    We analyse Semantic Segmentation Neural Networks running on an autonomous aircraft to estimate its pose during landing. We show that automated reasoning techniques from neural network verification can be used to analyse the conditions under which the networks can operate safely, thus providing enhanced assurance guarantees on the behaviour of the over-all pose estimation systems.

  • Conference paper
    Leofante F, Botoeva E, Rajani V, 2023,

    Counterfactual explanations and model multiplicity: a relational verification view

    , The 20th International Conference on Principles of Knowledge Representation and Reasoning (KR2023), Publisher: IJCAI Organization, Pages: 763-768, ISSN: 2334-1033

    We study the interplay between counterfactual explanationsand model multiplicity in the context of neural network clas-sifiers. We show that current explanation methods often pro-duce counterfactuals whose validity is not preserved undermodel multiplicity. We then study the problem of generatingcounterfactuals that are guaranteed to be robust to model multiplicity, characterise its complexity and propose an approach to solve this problem using ideas from relational verification.

  • Conference paper
    Rago A, Li H, Toni F, 2023,

    Interactive explanations by conflict resolution via argumentative exchanges

    , 20th International Conference on Principles of Knowledge Representation and Reasoning (KR2023), Publisher: IJCAI Organization, Pages: 582-592, ISSN: 2334-1033

    As the field of explainable AI (XAI) is maturing, calls forinteractive explanations for (the outputs of) AI models aregrowing, but the state-of-the-art predominantly focuses onstatic explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents’ quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine’s predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects ofcognitive biases in humans. We show experimentally (in asimulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.

  • Conference paper
    Nguyen H-T, Satoh K, Goebel R, Stathis K, Toni Fet al., 2023,

    Black-box analysis: GPTs across time in legal textual entailment task

    , ISAILD symposium - International Symposium on Artificial Intelligence and Legal Documents, Publisher: IEEE
  • Journal article
    Shah M, Inacio M, Lu C, Schiratti P-R, Zheng S, Clement A, Simoes Monteiro de Marvao A, Bai W, King A, Ware J, Wilkins M, Mielke J, Elci E, Kryukov I, McGurk K, Bender C, Freitag D, O'Regan Det al., 2023,

    Environmental and genetic predictors of human cardiovascular ageing

    , Nature Communications, Vol: 14, Pages: 1-15, ISSN: 2041-1723

    Cardiovascular ageing is a process that begins early in life and leads to a progressive change instructure and decline in function due to accumulated damage across diverse cell types, tissues andorgans contributing to multi-morbidity. Damaging biophysical, metabolic and immunological factors exceed endogenous repair mechanisms resulting in a pro-fibrotic state, cellular senescence andend-organ damage, however the genetic architecture of cardiovascular ageing is not known. Herewe use machine learning approaches to quantify cardiovascular age from image-derived traits ofvascular function, cardiac motion and myocardial fibrosis, as well as conduction traits from electrocardiograms, in 39,559 participants of UK Biobank. Cardiovascular ageing is found to be significantly associated with common or rare variants in genes regulating sarcomere homeostasis, myocardial immunomodulation, and tissue responses to biophysical stress. Ageing is accelerated bycardiometabolic risk factors and we also identify prescribed medications that are potential modifiersof ageing. Through large-scale modelling of ageing across multiple traits our results reveal insightsinto the mechanisms driving premature cardiovascular ageing and reveal potential molecular targetsto attenuate age-related processes.

  • Journal article
    Toni F, Rago A, Cyras K, 2023,

    Forecasting with jury-based probabilistic argumentation

    , Journal of Applied Non Classical Logics, Vol: 33, Pages: 224-243, ISSN: 1166-3081

    Probabilistic Argumentation supports a form of hybrid reasoning by integratingquantitative (probabilistic) reasoning and qualitative argumentation in a naturalway. Jury-based Probabilistic Argumentation supports the combination of opinionsby different reasoners. In this paper we show how Jury-based Probabilistic Abstract Argumentation (JPAA) and a form of Jury-based Probabilistic Assumptionbased Argumentation (JPABA) can naturally support forecasting, whereby subjective probability estimates are combined to make predictions about future occurrences of events. The form of JPABA we consider is an instance of JPAA andresults from integrating Assumption-Based Argumentation (ABA) and probabilityspaces expressed by Bayesian networks, under the so-called constellation approach.It keeps the underlying structured argumentation and probabilistic reasoning modules separate while integrating them. We show how JPAA and (the considered formof) JPABA can be used to support forecasting by 1) supporting different forecasters (jurors) to determine the probability of arguments (and, in the JPABA case,sentences) with respect to their own probability spaces, while sharing arguments(and their components); and 2) supporting the aggregation of individual forecaststo produce group forecasts.

  • Conference paper
    Leofante F, Henriksen P, Lomuscio A, 2023,

    Verification-friendly networks: the case for parametric ReLUs

    , International Joint Conference on Neural Networks (IJCNN 2023), Publisher: IEEE, Pages: 1-9

    It has increasingly been recognised that verification can contribute to the validation and debugging of neural networks before deployment, particularly in safety-critical areas. While progress has been made in the area of verification of neural networks, present techniques still do not scale to large ReLU-based neural networks used in many applications. In this paper we show that considerable progress can be made by employing Parametric ReLU activation functions in lieu of plain ReLU functions. We give training procedures that produce networks which achieve one order of magnitude gain in verification overheads and 30-100% fewer timeouts with VeriNet, a SoA Symbolic Interval Propagation-based verification toolkit, while not compromising the resulting accuracy. Furthermore, we show that adversarial training combined with our approachimproves certified robustness up to 36% compared to adversarial training performed on baseline ReLU networks.

  • Conference paper
    Lim BWT, Flageat M, Cully A, 2023,

    Efficient exploration using model-based quality-diversity with gradients

    , Conference on Artificial Life, Publisher: MIT Press, Pages: 1-10

    Exploration is a key challenge in Reinforcement Learning,especially in long-horizon, deceptive and sparse-reward environments. For such applications, population-based approaches have proven effective. Methods such as Quality-Diversity deals with this by encouraging novel solutions and producing a diversity of behaviours. However, these methods are driven by either undirected sampling (i.e. mutations) or use approximated gradients (i.e. Evolution Strategies) in the parameter space, which makes them highly sample-inefficient. In this paper, we propose Dynamics-Aware QD-Ext (DA-QD-ext) and Gradient and Dynamics Aware QD (GDA-QD), two model-based Quality-Diversity approaches. They extend existing QD methods to use gradients for efficient exploitation and leverage perturbations in imagination for efficient exploration.Our approach takes advantage of the effectiveness of QD algorithms as good data generators to train deep models and use these models to learn diverse and high-performing populations. We demonstrate that they outperform baseline RL approaches on tasks with deceptive rewards, and maintain the divergent search capabilities of QD approaches while exceeding their performance by ∼ 1.5 times and reaching the same results in 5 times less samples.

  • Conference paper
    Yin X, Potyka N, Toni F, 2023,

    Argument attribution explanations in quantitative bipolar argumentation frameworks

    , 26th European Conference on Artificial Intelligence ECAI 2023
  • Conference paper
    Ayoobi H, Potyka N, Toni F, 2023,

    SpArX: Sparse Argumentative Explanations for Neural Networks

    , European Conference on Artificial Intelligence 2023

    Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging. Existing approaches often focus on explaining how changing individual inputs affects NNs' outputs. However, an explanation that is consistent with the input-output behaviour of an NN is not necessarily faithful to the actual mechanics thereof. In this paper, we exploit relationships between multi-layer perceptrons (MLPs) and quantitative argumentation frameworks (QAFs) to create argumentative explanations for the mechanics of MLPs. Our SpArX method first sparsifies the MLP while maintaining as much of the original structure as possible. It then translates the sparse MLP into an equivalent QAF to shed light on the underlying decision process of the MLP, producing global and/or local explanations. We demonstrate experimentally that SpArX can give more faithful explanations than existing approaches, while simultaneously providing deeper insightsinto the actual reasoning process of MLPs.

  • Conference paper
    Sanguedolce G, Naylor PA, Geranmayeh F, 2023,

    Uncovering the potential for a weakly supervised end-to-end model in recognising speech from patient with post-stroke aphasia

    , 5th Clinical Natural Language Processing Workshop, Publisher: Association for Computational Linguistics, Pages: 182-190

    Post-stroke speech and language deficits (aphasia) significantly impact patients' quality of life. Many with mild symptoms remain undiagnosed, and the majority do not receive the intensive doses of therapy recommended, due to healthcare costs and/or inadequate services. Automatic Speech Recognition (ASR) may help overcome these difficulties by improving diagnostic rates and providing feedback during tailored therapy. However, its performance is often unsatisfactory due to the high variability in speech errors and scarcity of training datasets. This study assessed the performance of Whisper, a recently released end-to-end model, in patients with post-stroke aphasia (PWA). We tuned its hyperparameters to achieve the lowest word error rate (WER) on aphasic speech. WER was significantly higher in PWA compared to age-matched controls (10.3% vs 38.5%, p < 0.001). We demonstrated that worse WER was related to the more severe aphasia as measured by expressive (overt naming, and spontaneous speech production) and receptive (written and spoken comprehension) language assessments. Stroke lesion size did not affect the performance of Whisper. Linear mixed models accounting for demographic factors, therapy duration, and time since stroke, confirmed worse Whisper performance with left hemispheric frontal lesions. We discuss the implications of these findings for how future ASR can be improved in PWA.

  • Conference paper
    Grillotti L, Flageat M, Lim B, Cully Aet al., 2023,

    Don't bet on luck alone: enhancing behavioral reproducibility of quality-diversity solutions in uncertain domains

    , Genetic and Evolutionary Computation Conference (GECCO), Publisher: ACM

    Quality-Diversity (QD) algorithms are designed to generate collections of high-performing solutions while maximizing their diversity in a given descriptor space. However, in the presence of unpredictable noise, the fitness and descriptor of the same solution can differ significantly from one evaluation to another, leading to uncertainty in the estimation of such values. Given the elitist nature of QD algorithms, they commonly end up with many degeneratesolutions in such noisy settings. In this work, we introduce Archive Reproducibility Improvement Algorithm (ARIA); a plug-and-play approach that improves the reproducibility of the solutions present in an archive. We propose it as a separate optimization module, relying on natural evolution strategies, that can be executed on top of any QD algorithm. Our module mutates solutions to (1) optimize their probability of belonging to their niche, and (2) maximize their fitness. The performance of our method is evaluated on various tasks, including a classical optimization problem and two high-dimensional control tasks in simulated robotic environments. We show that our algorithm enhances the quality and descriptor space coverage of any given archive by at least 50%.

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=1&respub-action=search.html Current Millis: 1711655788736 Current Time: Thu Mar 28 19:56:28 GMT 2024