Research Papers

Do Perceived Gender Biases in Retrieval Results Affect Relevance Judgements?

Klara Krieg, Emilia Parada-Cabaleiro, Markus Schedl +1

This work investigates the effect of gender-stereotypical biases in the content of retrieved results on the relevance judgement of users/annotators. In particular, since relevance in information retrieval (IR) is a multi-dimensional concept, we study whether the value and quality of the retrieved documents for some bias-sensitive queries can be judged differently when the content of the documents represents different genders. To this aim, we conduct a set of experiments where the genders of the participants are known as well as experiments where the participants genders are not specified. The set of experiments comprise of retrieval tasks, where participants perform a rated relevance judgement for different search query and search result document compilations. The shown documents contain different gender indications and are either relevant or non-relevant to the query. The results show the differences between the average judged relevance scores among documents with various gender contents. Our work initiates further research on the connection of the perception of gender stereotypes in users with their judgements and effects on IR systems, and aim to raise awareness about the possible biases in this domain.

XAI Methods for Neural Time Series Classification: A Brief Review

Ilija Šimić, Vedran Sabol, Eduardo Veas

Deep learning models have recently demonstrated remarkable results in a variety of tasks, which is why they are being increasingly applied in high-stake domains, such as industry, medicine, and finance. Considering that automatic predictions in these domains might have a substantial impact on the well-being of a person, as well as considerable financial and legal consequences to an individual or a company, all actions and decisions that result from applying these models have to be accountable. Given that a substantial amount of data that is collected in high-stake domains are in the form of time series, in this paper we examine the current state of eXplainable AI (XAI) methods with a focus on approaches for opening up deep learning black boxes for the task of time series classification. Finally, our contribution also aims at deriving promising directions for future work, to advance XAI for deep learning on time series data.

In this work, we collect a moderate-sized representative corpus of tweets (200,000 approx.) pertaining Covid-19 vaccination spanning over a period of seven months (September 2020 - March 2021). Following a Transfer Learning approach, we utilize the pre-trained Transformer-based XLNet model to classify tweets as Misleading or Non-Misleading and validate against a random subset of results manually. We build on this to study and contrast the characteristics of tweets in the corpus that are misleading in nature against non-misleading ones. This exploratory analysis enables us to design features (such as sentiments, hashtags, nouns, pronouns, etc) that can, in turn, be exploited for classifying tweets as (Non-)Misleading using various ML models in an explainable manner. Specifically, several ML models are employed for prediction, with up to 90% accuracy, and the importance of each feature is explained using SHAP Explainable AI (XAI) tool. While the thrust of this work is principally exploratory analysis in order to obtain insights on the online discourse on Covid-19 vaccination, we conclude the paper by outlining how these insights provide the foundations for a more actionable approach to mitigate misinformation. The curated dataset and code is made available (Github repository) so that the research community at large can reproduce, compare against, or build upon this work.

A state-of-the-art systematic review on XAI applied to Prognostic and Health Management (PHM) of industrial asset is presented. This work provides an overview of the general trend of XAI in PHM, answers the question of accuracy versus explainability, the extent of human involvement, the explanation assessment and uncertainty quantification in PHM-XAI domain. Research articles associated with the subject, from 2015 to 2021 were selected from five known databases following PRISMA guidelines. Data was then extracted from the selected articles and examined. Several findings were synthesized. Firstly, while the discipline is still young, the analysis indicated the growing acceptance of XAI in PHM domain. Secondly, XAI functions as a double edge sword, where it is assimilated as a tool to execute PHM tasks as well as a mean of explanation, particularly in diagnostic and anomaly detection activities, implying a real need for XAI in PHM. Thirdly, the review showed that PHM-XAI papers produce either good or excellent result in general, suggesting that PHM performance is unaffected by XAI. Fourthly, human role, evaluation metrics and uncertainty management are areas requiring further attention by the PHM community. Adequate assessment metrics to cater for PHM need are urgently needed.Finally, most case study featured on the accepted articles are based on real, industrial data, indicating that the available PHM-XAI blends are fit to solve complex,real-world challenges, increasing the confidence in AI adoption in the industry.

Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasing demand for explainability in AI (XAI) in recent years. Saliency-based feature attribution methods, which highlight important parts of images that contribute to decisions by classifiers, are often used as XAI methods, especially in the field of computer vision. In order to compare various saliency-based XAI methods quantitatively, several approaches for automated evaluation schemes have been proposed; however, there is no guarantee that such automated evaluation metrics correctly evaluate explainability, and a high rating by an automated evaluation scheme does not necessarily mean a high explainability for humans. In this study, instead of the automated evaluation, we propose a new human-based evaluation scheme using crowdsourcing to evaluate XAI methods. Our method is inspired by a human computation game, "Peek-a-boom", and can efficiently compare different XAI methods by exploiting the power of crowds. We evaluate the saliency maps of various XAI methods on two datasets with automated and crowd-based evaluation schemes. Our experiments show that the result of our crowd-based evaluation scheme is different from those of automated evaluation schemes. In addition, we regard the crowd-based evaluation results as ground truths and provide a quantitative performance measure to compare different automated evaluation schemes. We also discuss the impact of crowd workers on the results and show that the varying ability of crowd workers does not significantly impact the results.

Although modern machine learning and deep learning methods allow for complex and in-depth data analytics, the predictive models generated by these methods are often highly complex, and lack transparency. Explainable AI (XAI) methods are used to improve the interpretability of these complex models, and in doing so improve transparency. However, the inherent fitness of these explainable methods can be hard to evaluate. In particular, methods to evaluate the fidelity of the explanation to the underlying black box require further development, especially for tabular data. In this paper, we (a) propose a three phase approach to developing an evaluation method; (b) adapt an existing evaluation method primarily for image and text data to evaluate models trained on tabular data; and (c) evaluate two popular explainable methods using this evaluation method. Our evaluations suggest that the internal mechanism of the underlying predictive model, the internal mechanism of the explainable method used and model and data complexity all affect explanation fidelity. Given that explanation fidelity is so sensitive to context and tools and data used, we could not clearly identify any specific explainable method as being superior to another.

Causal Learning for Socially Responsible AI

Lu Cheng, Ahmadreza Mosallanezhad, Paras Sheth +1

There have been increasing concerns about Artificial Intelligence (AI) due to its unfathomable potential power. To make AI address ethical challenges and shun undesirable outcomes, researchers proposed to develop socially responsible AI (SRAI). One of these approaches is causal learning (CL). We survey state-of-the-art methods of CL for SRAI. We begin by examining the seven CL tools to enhance the social responsibility of AI, then review how existing works have succeeded using these tools to tackle issues in developing SRAI such as fairness. The goal of this survey is to bring forefront the potentials and promises of CL for SRAI.

Mobile applications are often used by an international audience and therefore receive a high daily amount of user reviews from various countries. Previous work found evidence that app store reviews contain helpful information for software evolution processes. However, the cultural diversity of the reviews and its consequences on specific user feedback characteristics has only been researched to a limited extent so far. In this paper, we examine the influence of two cultural dimensions, Individualism and Uncertainty Avoidance on user feedback in Apple app store reviews written in different languages. For this purpose, we collected 647,141 reviews from eight countries and written in five languages over a period of six months. We then used manual content analysis and automated processing to examine a sample of 3,120 reviews. The results show that there is a statistically significant influence of Individualism and Uncertainty Avoidance on user feedback characteristics. The results of this study will help researchers and practitioners to reduce algorithm bias caused by less diversified training and test data and to raise awareness of the importance of analyzing diversified user feedback.

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.

Over the past few years, deep neural networks have shown excellent results in multiple tasks, however, there is still an increasing need to address the problem of interpretability to improve model transparency, performance, and safety. Achieving eXplainable Artificial Intelligence (XAI) by combining neural networks with continuous logic and multi-criteria decision-making tools is one of the most promising ways to approach this problem: by this combination, the black-box nature of neural models can be reduced. The continuous logic-based neural model uses so-called Squashing activation functions, a parametric family of functions that satisfy natural invariance requirements and contain rectified linear units as a particular case. This work demonstrates the first benchmark tests that measure the performance of Squashing functions in neural networks. Three experiments were carried out to examine their usability and a comparison with the most popular activation functions was made for five different network types. The performance was determined by measuring the accuracy, loss, and time per epoch. These experiments and the conducted benchmarks have proven that the use of Squashing functions is possible and similar in performance to conventional activation functions. Moreover, a further experiment was conducted by implementing nilpotent logical gates to demonstrate how simple classification tasks can be solved successfully and with high performance. The results indicate that due to the embedded nilpotent logical operators and the differentiability of the Squashing function, it is possible to solve classification problems, where other commonly used activation functions fail.

Black-box adversarial attack has attracted a lot of research interests for its practical use in AI safety. Compared with the white-box attack, a black-box setting is more difficult for less available information related to the attacked model and the additional constraint on the query budget. A general way to improve the attack efficiency is to draw support from a pre-trained transferable white-box model. In this paper, we propose a novel setting of transferable black-box attack: attackers may use external information from a pre-trained model with available network parameters, however, different from previous studies, no additional training data is permitted to further change or tune the pre-trained model. To this end, we further propose a new algorithm, EigenBA to tackle this problem. Our method aims to explore more gradient information of the black-box model, and promote the attack efficiency, while keeping the perturbation to the original attacked image small, by leveraging the Jacobian matrix of the pre-trained white-box model. We show the optimal perturbations are closely related to the right singular vectors of the Jacobian matrix. Further experiments on ImageNet and CIFAR-10 show that even the unlearnable pre-trained white-box model could also significantly boost the efficiency of the black-box attack and our proposed method could further improve the attack efficiency.

On Controllability of AI

Roman V. Yampolskiy

Invention of artificial general intelligence is predicted to cause a shift in the trajectory of human civilization. In order to reap the benefits and avoid pitfalls of such powerful technology it is important to be able to control it. However, possibility of controlling artificial general intelligence and its more advanced version, superintelligence, has not been formally established. In this paper, we present arguments as well as supporting evidence from multiple domains indicating that advanced AI can't be fully controlled. Consequences of uncontrollability of AI are discussed with respect to future of humanity and research on AI, and AI safety and security.