Research Papers

Artificial intelligence (AI), particularly machine learning and deep learning models, has significantly impacted bioinformatics research by offering powerful tools for analyzing complex biological data. However, the lack of interpretability and transparency of these models presents challenges in leveraging these models for deeper biological insights and for generating testable hypotheses. Explainable AI (XAI) has emerged as a promising solution to enhance the transparency and interpretability of AI models in bioinformatics. This review provides a comprehensive analysis of various XAI techniques and their applications across various bioinformatics domains including DNA, RNA, and protein sequence analysis, structural analysis, gene expression and genome analysis, and bioimaging analysis. We introduce the most pertinent machine learning and XAI methods, then discuss their diverse applications and address the current limitations of available XAI tools. By offering insights into XAI's potential and challenges, this review aims to facilitate its practical implementation in bioinformatics research and help researchers navigate the landscape of XAI tools.

Recently, transformers have become incredibly popular in computer vision and vision-language tasks. This notable rise in their usage can be primarily attributed to the capabilities offered by attention mechanisms and the outstanding ability of transformers to adapt and apply themselves to a variety of tasks and domains. Their versatility and state-of-the-art performance have established them as indispensable tools for a wide array of applications. However, in the constantly changing landscape of machine learning, the assurance of the trustworthiness of transformers holds utmost importance. This paper conducts a thorough examination of vision-language transformers, employing three fundamental principles of responsible AI: Bias, Robustness, and Interpretability. The primary objective of this paper is to delve into the intricacies and complexities associated with the practical use of transformers, with the overarching goal of advancing our comprehension of how to enhance their reliability and accountability.

In this paper, we introduce an explainable algorithm designed from a multi-modal foundation model, that performs fast and explainable image classification. Drawing inspiration from CLIP-based Concept Bottleneck Models (CBMs), our method creates a latent space where each neuron is linked to a specific word. Observing that this latent space can be modeled with simple distributions, we use a Mixture of Gaussians (MoG) formalism to enhance the interpretability of this latent space. Then, we introduce CLIP-QDA, a classifier that only uses statistical values to infer labels from the concepts. In addition, this formalism allows for both local and global explanations. These explanations come from the inner design of our architecture, our work is part of a new family of greybox models, combining performances of opaque foundation models and the interpretability of transparent models. Our empirical findings show that in instances where the MoG assumption holds, CLIP-QDA achieves similar accuracy with state-of-the-art methods CBMs. Our explanations compete with existing XAI methods while being faster to compute.

The proliferation of Artificial Intelligence (AI) has sparked an overwhelming number of AI ethics guidelines, boards and codes of conduct. These outputs primarily analyse competing theories, principles and values for AI development and deployment. However, as a series of recent problematic incidents about AI ethics/ethicists demonstrate, this orientation is insufficient. Before proceeding to evaluate other professions, AI ethicists should critically evaluate their own; yet, such an evaluation should be more explicitly and systematically undertaken in the literature. I argue that these insufficiencies could be mitigated by developing a research agenda for a feminist metaethics of AI. Contrary to traditional metaethics, which reflects on the nature of morality and moral judgements in a non-normative way, feminist metaethics expands its scope to ask not only what ethics is but also what our engagement with it should be like. Applying this perspective to the context of AI, I suggest that a feminist metaethics of AI would examine: (i) the continuity between theory and action in AI ethics; (ii) the real-life effects of AI ethics; (iii) the role and profile of those involved in AI ethics; and (iv) the effects of AI on power relations through methods that pay attention to context, emotions and narrative.

This paper presents a reputation-based threat mitigation framework that defends potential security threats in electroencephalogram (EEG) signal classification during model aggregation of Federated Learning. While EEG signal analysis has attracted attention because of the emergence of brain-computer interface (BCI) technology, it is difficult to create efficient learning models for EEG analysis because of the distributed nature of EEG data and related privacy and security concerns. To address these challenges, the proposed defending framework leverages the Federated Learning paradigm to preserve privacy by collaborative model training with localized data from dispersed sources and introduces a reputation-based mechanism to mitigate the influence of data poisoning attacks and identify compromised participants. To assess the efficiency of the proposed reputation-based federated learning defense framework, data poisoning attacks based on the risk level of training data derived by Explainable Artificial Intelligence (XAI) techniques are conducted on both publicly available EEG signal datasets and the self-established EEG signal dataset. Experimental results on the poisoned datasets show that the proposed defense methodology performs well in EEG signal classification while reducing the risks associated with security threats.

Predictability and Comprehensibility in Post-Hoc XAI Methods: A User-Centered Analysis

Anahid Jalali, Bernhard Haslhofer, Simone Kriglstein +1

Post-hoc explainability methods aim to clarify predictions of black-box machine learning models. However, it is still largely unclear how well users comprehend the provided explanations and whether these increase the users ability to predict the model behavior. We approach this question by conducting a user study to evaluate comprehensibility and predictability in two widely used tools: LIME and SHAP. Moreover, we investigate the effect of counterfactual explanations and misclassifications on users ability to understand and predict the model behavior. We find that the comprehensibility of SHAP is significantly reduced when explanations are provided for samples near a model's decision boundary. Furthermore, we find that counterfactual explanations and misclassifications can significantly increase the users understanding of how a machine learning model is making decisions. Based on our findings, we also derive design recommendations for future post-hoc explainability methods with increased comprehensibility and predictability.

A Survey of Graph Unlearning

Anwar Said, Ngoc N. Tran, Yuying Zhao +4

Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the \textit{right to be forgotten}. It is evident that graph machine learning exhibits sensitivity to data privacy and adversarial attacks, necessitating the application of graph unlearning techniques to address these concerns effectively. In this comprehensive survey paper, we present the first systematic review of graph unlearning approaches, encompassing a diverse array of methodologies and offering a detailed taxonomy and up-to-date literature overview to facilitate the understanding of researchers new to this field. To ensure clarity, we provide lucid explanations of the fundamental concepts and evaluation measures used in graph unlearning, catering to a broader audience with varying levels of expertise. Delving into potential applications, we explore the versatility of graph unlearning across various domains, including but not limited to social networks, adversarial settings, recommender systems, and resource-constrained environments like the Internet of Things, illustrating its potential impact in safeguarding data privacy and enhancing AI systems' robustness. Finally, we shed light on promising research directions, encouraging further progress and innovation within the domain of graph unlearning. By laying a solid foundation and fostering continued progress, this survey seeks to inspire researchers to further advance the field of graph unlearning, thereby instilling confidence in the ethical growth of AI systems and reinforcing the responsible application of machine learning techniques in various domains.

A fiduciary is a trusted agent that has the legal duty to act with loyalty and care towards a principal that employs them. When fiduciary organizations interact with users through a digital interface, or otherwise automate their operations with artificial intelligence, they will need to design these AI systems to be compliant with their duties. This article synthesizes recent work in computer science and law to develop a procedure for designing and auditing Fiduciary AI. The designer of a Fiduciary AI should understand the context of the system, identify its principals, and assess the best interests of those principals. Then the designer must be loyal with respect to those interests, and careful in an contextually appropriate way. We connect the steps in this procedure to dimensions of Trustworthy AI, such as privacy and alignment. Fiduciary AI is a promising means to address the incompleteness of data subject's consent when interacting with complex technical systems.

Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning.

Malnutrition is a serious and prevalent health problem in the older population, and especially in hospitalised or institutionalised subjects. Accurate and early risk detection is essential for malnutrition management and prevention. M-health services empowered with Artificial Intelligence (AI) may lead to important improvements in terms of a more automatic, objective, and continuous monitoring and assessment. Moreover, the latest Explainable AI (XAI) methodologies may make AI decisions interpretable and trustworthy for end users. This paper presents a novel AI framework for early and explainable malnutrition risk detection based on heterogeneous m-health data. We performed an extensive model evaluation including both subject-independent and personalised predictions, and the obtained results indicate Random Forest (RF) and Gradient Boosting as the best performing classifiers, especially when incorporating body composition assessment data. We also investigated several benchmark XAI methods to extract global model explanations. Model-specific explanation consistency assessment indicates that each selected model privileges similar subsets of the most relevant predictors, with the highest agreement shown between SHapley Additive ExPlanations (SHAP) and feature permutation method. Furthermore, we performed a preliminary clinical validation to verify that the learned feature-output trends are compliant with the current evidence-based assessment.

ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination

Dongfang Li, Jindi Yu, Baotian Hu +2

As ChatGPT and GPT-4 spearhead the development of Large Language Models (LLMs), more researchers are investigating their performance across various tasks. But more research needs to be done on the interpretability capabilities of LLMs, that is, the ability to generate reasons after an answer has been given. Existing explanation datasets are mostly English-language general knowledge questions, which leads to insufficient thematic and linguistic diversity. To address the language bias and lack of medical resources in generating rationales QA datasets, we present ExplainCPE (over 7k instances), a challenging medical benchmark in Simplified Chinese. We analyzed the errors of ChatGPT and GPT-4, pointing out the limitations of current LLMs in understanding text and computational reasoning. During the experiment, we also found that different LLMs have different preferences for in-context learning. ExplainCPE presents a significant challenge, but its potential for further investigation is promising, and it can be used to evaluate the ability of a model to generate explanations. AI safety and trustworthiness need more attention, and this work makes the first step to explore the medical interpretability of LLMs.The dataset is available at https://github.com/HITsz-TMG/ExplainCPE.

Counterfactual explanations are an increasingly popular form of post hoc explanation due to their (i) applicability across problem domains, (ii) proposed legal compliance (e.g., with GDPR), and (iii) reliance on the contrastive nature of human explanation. Although counterfactual explanations are normally used to explain individual predictive-instances, we explore a novel use case in which groups of similar instances are explained in a collective fashion using ``group counterfactuals'' (e.g., to highlight a repeating pattern of illness in a group of patients). These group counterfactuals meet a human preference for coherent, broad explanations covering multiple events/instances. A novel, group-counterfactual algorithm is proposed to generate high-coverage explanations that are faithful to the to-be-explained model. This explanation strategy is also evaluated in a large, controlled user study (N=207), using objective (i.e., accuracy) and subjective (i.e., confidence, explanation satisfaction, and trust) psychological measures. The results show that group counterfactuals elicit modest but definite improvements in people's understanding of an AI system. The implications of these findings for counterfactual methods and for XAI are discussed.