Graph mining algorithms have been playing a significant role in myriad fields over the years. However, despite their promising performance on various graph analytical tasks, most of these algorithms lack fairness considerations. As a consequence, they could lead to discrimination towards certain populations when exploited in human-centered applications. Recently, algorithmic fairness has been extensively studied in graph-based applications. In contrast to algorithmic fairness on independent and identically distributed (i.i.d.) data, fairness in graph mining has exclusive backgrounds, taxonomies, and fulfilling techniques. In this survey, we provide a comprehensive and up-to-date introduction of existing literature under the context of fair graph mining. Specifically, we propose a novel taxonomy of fairness notions on graphs, which sheds light on their connections and differences. We further present an organized summary of existing techniques that promote fairness in graph mining. Finally, we summarize the widely used datasets in this emerging research field and provide insights on current research challenges and open questions, aiming at encouraging cross-breeding ideas and further advances.

Fairness in Graph Mining: A Survey

In many decision-making scenarios, ranging from recreational activities to healthcare and policing, the use of artificial intelligence coupled with the ability to learn from historical data is becoming ubiquitous. This widespread adoption of automated systems is accompanied by the increasing concerns regarding their ethical implications. Fundamental rights, such as the ones that require the preservation of privacy, do not discriminate based on sensible attributes (e.g., gender, ethnicity, political/sexual orientation), or require one to provide an explanation for a decision, are daily undermined by the use of increasingly complex and less understandable yet more accurate learning algorithms. For this purpose, in this work, we work toward the development of systems able to ensure trustworthiness by delivering privacy, fairness, and explainability by design. In particular, we show that it is possible to simultaneously learn from data while preserving the privacy of the individuals thanks to the use of Homomorphic Encryption, ensuring fairness by learning a fair representation from the data, and ensuring explainable decisions with local and global explanations without compromising the accuracy of the final models. We test our approach on a widespread but still controversial application, namely face recognition, using the recent FairFace dataset to prove the validity of our approach.

Toward Learning Trustworthily from Data Combining Privacy, Fairness, and Explainability: An Application to Face Recognition

Developing fair deep learning models for identity-sensitive applications (e.g., face attribute recognition) has gained increasing attention from the research community. Indeed, it has been observed that deep models can easily overfit to the bias of the training set, resulting in discriminative performance against certain demographic groups during test time. Motivated by the observation that a biased classifier could result in different adversarial robustness among training samples in different demographic groups (robustness bias), we argue that such adversarial robustness information of individual training samples could imply whether the training data distribution is fair among different demographic groups. In other words, under a fair classifier, the training samples from different demographic groups are expected to show similar or comparable adversarial robustness. Therefore, in this work, we propose to re-weight the training loss of individual training samples using their adversarial robustness, and provide the fairness-awareness in the training process. Extensive experimental results on CelebA dataset show that the face attribute classifiers could learn significantly greater demographic fairness under our proposed training objective and outperform other state-of-the-art re-weighting fairness algorithms on different face recognition applications. Moreover, our proposed method also reduces the non-trivial robustness bias among different demographic groups, preventing the under-represented demographic groups from higher adversarial threats. 

Fairness-aware training of face attribute classifiers via adversarial robustness

Face Recognition aims at identifying or confirming an individual's identity in a still image or video. Towards this end, machine learning and deep learning techniques have been successfully employed for face recognition. However, the response of the face recognition system often remains mysterious to the end-user. This paper aims to fill this gap by letting an end user know which features of the face has the model relied upon in recognizing a subject's face. In this context, we evaluate the interpretability of several face recognizers employing deep neural networks namely, LeNet-5, AlexNet, Inception-V3, and VGG16. For this purpose, a recently proposed explainable AI tool-Local Interpretable Model-Agnostic Explanations (LIME) is used. Benchmark datasets such as Yale, AT &T dataset, and Labeled Faces in the Wild (LFW) are utilized for this purpose. We are able to demonstrate that LIME indeed marks the features that are visually significant features for face recognition. 

/pdf/xai-fr-explainable-ai-based-face-recognition-using-deep-3dyc2md3.pdf

XAI-FR: Explainable AI-Based Face Recognition Using Deep Neural Networks

Recently, face recognition systems have demonstrated remarkable performances and thus gained a vital role in our daily life. They already surpass human face verification accountability in many scenarios. However, they lack explanations for their predictions. Compared to human operators, typical face recognition network system generate only binary decisions without further explanation and insights into those decisions. This work focuses on explanations for face recognition systems, vital for developers and operators. First, we introduce a confidence score for those systems based on facial feature distances between two input images and the distribution of distances across a dataset. Secondly, we establish a novel visualization approach to obtain more meaningful predictions from a face recognition system, which maps the distance deviation based on a systematic occlusion of images. The result is blended with the original images and highlights similar and dissimilar facial regions. Lastly, we calculate confidence scores and explanation maps for several state-of-the-art face verification datasets and release the results on a web platform. We optimize the platform for a user-friendly interaction and hope to further improve the understanding of machine learning decisions. The source code is available on GitHub11https://github.com/martlgap/x-face-verification, and the web platform is publicly available at http://explainable-face-verification.ey.r.appspot.com.

Explainable Model-Agnostic Similarity and Confidence in Face Verification

Deep fair models for complex data: Graphs labeling and explainable face recognition

/pdf/advances-in-artificial-neural-networks-machine-learning-and-3fw7be6m.pdf

Alp Ustundag

Papers

Deep fair models for complex data: Graphs labeling and explainable face recognition

Deep fair models for complex data: Graphs labeling and explainable face recognition

Advances in artificial neural networks, machine learning and computational intelligence