Research Papers

Biased datasets are ubiquitous and present a challenge for machine learning. For a number of categories on a dataset that are equally important but some are sparse and others are common, the learning algorithms will favor the ones with more presence. The problem of biased datasets is especially sensitive when dealing with minority people groups. How can we, from biased data, generate algorithms that treat every person equally? This work explores one way to mitigate bias using a debiasing variational autoencoder with experiments on facial expression recognition.

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation. Specifically, we first derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength, revealing that they are effective only when the inherent bias in the dataset is relatively weak. Next, we derive a necessary condition for the existence of any method that can remove attribute bias regardless of the bias strength. Inspired by this condition, we then propose a new method using an adversarial objective that directly filters out protected attributes in the input space while maximally preserving all other attributes, without requiring any specific target label. The proposed method achieves state-of-the-art performance in both strong and moderate bias settings. We provide extensive experiments on synthetic, image, and census datasets, to verify the derived theoretical bound and its consequences in practice, and evaluate the effectiveness of the proposed method in removing strong attribute bias.

Work in AI ethics and fairness has made much progress in regulating LLMs to reflect certain values, such as fairness, truth, and diversity. However, it has taken the problem of how LLMs might 'mean' anything at all for granted. Without addressing this, it is not clear what imbuing LLMs with such values even means. In response, we provide a general theory of meaning that extends beyond humans. We use this theory to explicate the precise nature of LLMs as meaning-agents. We suggest that the LLM, by virtue of its position as a meaning-agent, already grasps the constructions of human society (e.g. morality, gender, and race) in concept. Consequently, under certain ethical frameworks, currently popular methods for model alignment are limited at best and counterproductive at worst. Moreover, unaligned models may help us better develop our moral and social philosophy.

Towards Trustworthy Artificial Intelligence for Equitable Global Health

Hong Qin, Jude Kong, Wandi Ding +14

Artificial intelligence (AI) can potentially transform global health, but algorithmic bias can exacerbate social inequities and disparity. Trustworthy AI entails the intentional design to ensure equity and mitigate potential biases. To advance trustworthy AI in global health, we convened a workshop on Fairness in Machine Intelligence for Global Health (FairMI4GH). The event brought together a global mix of experts from various disciplines, community health practitioners, policymakers, and more. Topics covered included managing AI bias in socio-technical systems, AI's potential impacts on global health, and balancing data privacy with transparency. Panel discussions examined the cultural, political, and ethical dimensions of AI in global health. FairMI4GH aimed to stimulate dialogue, facilitate knowledge transfer, and spark innovative solutions. Drawing from NIST's AI Risk Management Framework, it provided suggestions for handling AI risks and biases. The need to mitigate data biases from the research design stage, adopt a human-centered approach, and advocate for AI transparency was recognized. Challenges such as updating legal frameworks, managing cross-border data sharing, and motivating developers to reduce bias were acknowledged. The event emphasized the necessity of diverse viewpoints and multi-dimensional dialogue for creating a fair and ethical AI framework for equitable global health.

The rapidly advancing domain of Explainable Artificial Intelligence (XAI) has sparked significant interests in developing techniques to make AI systems more transparent and understandable. Nevertheless, in real-world contexts, the methods of explainability and their evaluation strategies present numerous limitations.Moreover, the scope of responsible AI extends beyond just explainability. In this paper, we explore these limitations and discuss their implications in a boarder context of responsible AI when considering other important aspects, including privacy, fairness and contestability.

Causal machine learning methods which flexibly generate heterogeneous treatment effect estimates could be very useful tools for governments trying to make and implement policy. However, as the critical artificial intelligence literature has shown, governments must be very careful of unintended consequences when using machine learning models. One way to try and protect against unintended bad outcomes is with AI Fairness methods which seek to create machine learning models where sensitive variables like race or gender do not influence outcomes. In this paper we argue that standard AI Fairness approaches developed for predictive machine learning are not suitable for all causal machine learning applications because causal machine learning generally (at least so far) uses modelling to inform a human who is the ultimate decision-maker while AI Fairness approaches assume a model that is making decisions directly. We define these scenarios as indirect and direct decision-making respectively and suggest that policy-making is best seen as a joint decision where the causal machine learning model usually only has indirect power. We lay out a definition of fairness for this scenario - a model that provides the information a decision-maker needs to accurately make a value judgement about just policy outcomes - and argue that the complexity of causal machine learning models can make this difficult to achieve. The solution here is not traditional AI Fairness adjustments, but careful modelling and awareness of some of the decision-making biases that these methods might encourage which we describe.

Ensuring trust and accountability in Artificial Intelligence systems demands explainability of its outcomes. Despite significant progress in Explainable AI, human biases still taint a substantial portion of its training data, raising concerns about unfairness or discriminatory tendencies. Current approaches in the field of Algorithmic Fairness focus on mitigating such biases in the outcomes of a model, but few attempts have been made to try to explain \emph{why} a model is biased. To bridge this gap between the two fields, we propose a comprehensive approach that uses optimal transport theory to uncover the causes of discrimination in Machine Learning applications, with a particular emphasis on image classification. We leverage Wasserstein barycenters to achieve fair predictions and introduce an extension to pinpoint bias-associated regions. This allows us to derive a cohesive system which uses the enforced fairness to measure each features influence \emph{on} the bias. Taking advantage of this interplay of enforcing and explaining fairness, our method hold significant implications for the development of trustworthy and unbiased AI systems, fostering transparency, accountability, and fairness in critical decision-making scenarios across diverse domains.

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data and models, with a particular focus on bias in machine learning pipelines. The next chapter outlines a taxonomy and methods of Explainable AI as a way to justify predictions and control and improve the model. Then, as an example of a laborious manual data inspection and bias discovery process, a skin lesion dataset is manually examined. A Global Explanation for the Bias Identification method is proposed as an alternative semi-automatic approach to manual data exploration for discovering potential biases in data. Relevant numerical methods and metrics are discussed for assessing the effects of the identified biases on the model. Whereas identifying errors and bias is critical, improving the model and reducing the number of flaws in the future is an absolute priority. Hence, the second part of the thesis focuses on mitigating the influence of bias on ML models. Three approaches are proposed and discussed: Style Transfer Data Augmentation, Targeted Data Augmentations, and Attribution Feedback. Style Transfer Data Augmentation aims to address shape and texture bias by merging a style of a malignant lesion with a conflicting shape of a benign one. Targeted Data Augmentations randomly insert possible biases into all images in the dataset during the training, as a way to make the process random and, thus, destroy spurious correlations. Lastly, Attribution Feedback is used to fine-tune the model to improve its accuracy by eliminating obvious mistakes and teaching it to ignore insignificant input parts via an attribution loss. The goal of these approaches is to reduce the influence of bias on machine learning models, rather than eliminate it entirely.

When making strategic decisions, we are often confronted with overwhelming information to process. The situation can be further complicated when some pieces of evidence are contradicted each other or paradoxical. The challenge then becomes how to determine which information is useful and which ones should be eliminated. This process is known as meta-decision. Likewise, when it comes to using Artificial Intelligence (AI) systems for strategic decision-making, placing trust in the AI itself becomes a meta-decision, given that many AI systems are viewed as opaque "black boxes" that process large amounts of data. Trusting an opaque system involves deciding on the level of Trustworthy AI (TAI). We propose a new approach to address this issue by introducing a novel taxonomy or framework of TAI, which encompasses three crucial domains: articulate, authentic, and basic for different levels of trust. To underpin these domains, we create ten dimensions to measure trust: explainability/transparency, fairness/diversity, generalizability, privacy, data governance, safety/robustness, accountability, reproducibility, reliability, and sustainability. We aim to use this taxonomy to conduct a comprehensive survey and explore different TAI approaches from a strategic decision-making perspective.

In eXplainable Artificial Intelligence (XAI), counterfactual explanations are known to give simple, short, and comprehensible justifications for complex model decisions. However, we are yet to see more applied studies in which they are applied in real-world cases. To fill this gap, this study focuses on showing how counterfactuals are applied to employability-related problems which involve complex machine learning algorithms. For these use cases, we use real data obtained from a public Belgian employment institution (VDAB). The use cases presented go beyond the mere application of counterfactuals as explanations, showing how they can enhance decision support, comply with legal requirements, guide controlled changes, and analyze novel insights.

Contemporary automation through AI entails a substantial amount of behind-the-scenes human labour, which is often both invisibilised and underpaid. Since invisible labour, including labelling and maintenance work, is an integral part of contemporary AI systems, it remains important to sensitise users to its role. We suggest that this could be done through explainable AI (XAI) design, particularly feminist intersectional XAI. We propose the method of cartography, which stems from feminist intersectional research, to draw out a systemic perspective of AI and include dimensions of AI that pertain to invisible labour.

Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output labels, to update the model with new data and a limited number of old data. This avoids heavyweight training (from scratch) using conventional methods and saves storage space by reducing the number of old data to store. But it also leads to poor performance in fairness. In this paper, we show that CIL suffers both dataset and algorithm bias problems, and existing solutions can only partially solve the problem. We propose a novel framework, CILIATE, that fixes both dataset and algorithm bias in CIL. It features a novel differential analysis guided dataset and training refinement process that identifies unique and important samples overlooked by existing CIL and enforces the model to learn from them. Through this process, CILIATE improves the fairness of CIL by 17.03%, 22.46%, and 31.79% compared to state-of-the-art methods, iCaRL, BiC, and WA, respectively, based on our evaluation on three popular datasets and widely used ResNet models.