Search

The Expert Finding (EF) task is critical in community Question&Answer (CQ&A) platforms, significantly enhancing user engagement by improving answer quality and reducing response times. However, biases, especially gender biases, have been identified in these platforms. This study investigates gender bias in state-of-the-art EF models and explores methods to mitigate it. Utilizing a comprehensive dataset from StackOverflow, the largest community in the StackExchange network, we conduct extensive experiments to analyze how EF models' candidate identification processes influence gender representation. Our findings reveal that models relying on reputation metrics and activity levels disproportionately favor male users, who are more active on the platform. This bias results in the underrepresentation of female experts in the ranking process. We propose adjustments to EF models that incorporate a more balanced preprocessing strategy and leverage content-based and social network-based information, with the aim to provide a fairer representation of genders among identified experts. Our analysis shows that integrating these methods can significantly enhance gender balance without compromising model accuracy. To the best of our knowledge, this study is the first to focus on detecting and mitigating gender bias in EF methods.

In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's catalog. A standard approach for such a problem is learning a feature space of images where Euclidean distances reflect similarity. Even without human annotations, which may be expensive to acquire, prior methods function reasonably well using unlabeled images for training. Our problem constraint takes this further to scenarios where the two domains do not necessarily share any common categories in training data. This can occur when the two domains in question come from different versions of some biometric sensor recording identities of different people. We posit a simple solution, which is to generate synthetic data to fill in these missing category examples across domains. This, we do via category preserving translation of images from one visual domain to another. We compare approaches specifically trained for this translation for a pair of domains, as well as those that can use large-scale pre-trained text-to-image diffusion models via prompts, and find that the latter can generate better replacement synthetic data, leading to more accurate cross-domain retrieval models. Our best SynCDR model can outperform prior art by up to 15\%. Code for our work is available at https://github.com/samarth4149/SynCDR ., Comment: Pre-print

All types of research, development, and policy work can have unintended, adverse consequences - work in responsible artificial intelligence (RAI), ethical AI, or ethics in AI is no exception.

Graph neural networks (GNNs) are increasingly used in critical human applications for predicting node labels in attributed graphs. Their ability to aggregate features from nodes' neighbors for accurate classification also has the capacity to exacerbate existing biases in data or to introduce new ones towards members from protected demographic groups. Thus, it is imperative to quantify how GNNs may be biased and to what extent their harmful effects may be mitigated. To this end, we propose two new GNN-agnostic interventions namely, (i) PFR-AX which decreases the separability between nodes in protected and non-protected groups, and (ii) PostProcess which updates model predictions based on a blackbox policy to minimize differences between error rates across demographic groups. Through a large set of experiments on four datasets, we frame the efficacies of our approaches (and three variants) in terms of their algorithmic fairness-accuracy tradeoff and benchmark our results against three strong baseline interventions on three state-of-the-art GNN models. Our results show that no single intervention offers a universally optimal tradeoff, but PFR-AX and PostProcess provide granular control and improve model confidence when correctly predicting positive outcomes for nodes in protected groups., Comment: Accepted to CIKM 2023

Common and important applications of person identification occur at distances and viewpoints in which the face is not visible or is not sufficiently resolved to be useful. We examine body shape as a biometric across distance and viewpoint variation. We propose an approach that combines standard object classification networks with representations based on linguistic (word-based) descriptions of bodies. Algorithms with and without linguistic training were compared on their ability to identify people from body shape in images captured across a large range of distances/views (close-range, 100m, 200m, 270m, 300m, 370m, 400m, 490m, 500m, 600m, and at elevated pitch in images taken by an unmanned aerial vehicle [UAV]). Accuracy, as measured by identity-match ranking and false accept errors in an open-set test, was surprisingly good. For identity-ranking, linguistic models were more accurate for close-range images, whereas non-linguistic models fared better at intermediary distances. Fusion of the linguistic and non-linguistic embeddings improved performance at all, but the farthest distance. Although the non-linguistic model yielded fewer false accepts at all distances, fusion of the linguistic and non-linguistic models decreased false accepts for all, but the UAV images. We conclude that linguistic and non-linguistic representations of body shape can offer complementary identity information for bodies that can improve identification in applications of interest., Comment: 9 pages, 5 figures, 4 tables

Among the seven key requirements to achieve trustworthy AI proposed by the High-Level Expert Group on Artificial Intelligence (AI-HLEG) established by the European Commission (EC), the fifth requirement ("Diversity, non-discrimination and fairness") declares: "In order to achieve Trustworthy AI, we must enable inclusion and diversity throughout the entire AI system's life cycle. [...] This requirement is closely linked with the principle of fairness". In this paper, we try to shed light on how closely these two distinct concepts, diversity and fairness, may be treated by focusing on information access systems and ranking literature. These concepts should not be used interchangeably because they do represent two different values, but what we argue is that they also cannot be considered totally unrelated or divergent. Having diversity does not imply fairness, but fostering diversity can effectively lead to fair outcomes, an intuition behind several methods proposed to mitigate the disparate impact of information access systems, i.e. recommender systems and search engines., Comment: Presented at the European Workshop on Algorithmic Fairness (EWAF'23) Winterthur, Switzerland, June 7-9, 2023

Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveillance cameras. Despite recent advances in deep convolutional neural networks (DCNNs), this remains challenging. Images or videos collected by long-range cameras often suffer from atmospheric turbulence, blur, low-resolution, unconstrained poses, and poor illumination. In this paper, we provide a brief survey of recent advances in person recognition at a distance. In particular, we review recent work in multi-spectral face verification, person re-identification, and gait-based analysis techniques. Furthermore, we discuss the merits and drawbacks of existing approaches and identify important, yet under explored challenges for deploying remote person recognition systems in-the-wild., Comment: This work has been accepted to the IEEE Asilomar Conference on Signals, Systems, and Computers (ACSSC) 2022

We present the results of a 12-week longitudinal user study wherein the participants, 110 subjects from Southern Europe, received on a daily basis Electronic Music (EM) diversified recommendations. By analyzing their explicit and implicit feedback, we show that exposure to specific levels of music recommendation diversity may be responsible for long-term impacts on listeners' attitudes. In particular, we highlight the function of diversity in increasing the openness in listening to EM, a music genre not particularly known or liked by the participants previous to their participation in the study. Moreover, we demonstrate that recommendations may help listeners in removing positive and negative attachments towards EM, deconstructing pre-existing implicit associations but also stereotypes associated with this music. In addition, our results show the significant clout that recommendation diversity has in generating curiosity in listeners.

Context: Internet of Things (IoT) has become an important kind of distributed systems thanks to the wide-spread of cheap embedded devices equipped with different networking technologies. Although ubiquitous, developing IoT systems remains challenging. Inquiry: A recent field study with 194 IoT developers identifies debugging as one of the main challenges faced when developing IoT systems. This comes from the lack of debugging tools taking into account the unique properties of IoT systems such as non-deterministic data, and hardware restricted devices. On the one hand, offline debuggers allow developers to analyse post-failure recorded program information, but impose too much overhead on the devices while generating such information. Furthermore, the analysis process is also time-consuming and might miss contextual information relevant to find the root cause of bugs. On the other hand, online debuggers do allow debugging a program upon a failure while providing contextual information (e.g., stack trace). In particular, remote online debuggers enable debugging of devices without physical access to them. However, they experience debugging interference due to network delays which complicates bug reproducibility, and have limited support for dynamic software updates on remote devices. Approach: This paper proposes out-of-things debugging, an online debugging approach especially designed for IoT systems. The debugger is always-on as it ensures constant availability to for instance debug post-deployment situations. Upon a failure or breakpoint, out-of-things debugging moves the state of a deployed application to the developer's machine. Developers can then debug the application locally by applying operations (e.g., step commands) to the retrieved state. Once debugging is finished, developers can commit bug fixes to the device through live update capabilities. Finally, by means of a fine-grained flexible interface for accessing remote resources, developers have full control over the debugging overhead imposed on the device, and the access to device hardware resources (e.g., sensors) needed during local debugging. Knowledge: Out-of-things debugging maintains good properties of remote debugging as it does not require physical access to the device to debug it, while reducing debugging interference since there are no network delays on operations (e.g., stepping) issued on the debugger since those happen locally. Furthermore, device resources are only accessed when requested by the user which further mitigates overhead and opens avenues for mocking or simulation of non-accessed resources. Grounding: We implemented an out-of-things debugger as an extension to a WebAssembly Virtual Machine and benchmarked its suitability for IoT. In particular, we compared our solution to remote debugging alternatives based on metrics such as network overhead, memory usage, scalability, and usability in production settings. From the benchmarks, we conclude that our debugger exhibits competitive performance in addition to confining overhead without sacrificing debugging convenience and flexibility. Importance: Out-of-things debugging enables debugging of IoT systems by means of classical online operations (e.g., stepwise execution) while addressing IoT-specific concerns (e.g., hardware limitations). We show that having the debugger always-on does not have to come at cost of performance loss or increased overhead but instead can enforce a smooth-going and flexible debugging experience of IoT systems.

Deep convolutional neural networks (DCNNs) have achieved human-level accuracy in face identification (Phillips et al., 2018), though it is unclear how accurately they discriminate highly-similar faces. Here, humans and a DCNN performed a challenging face-identity matching task that included identical twins. Participants (N=87) viewed pairs of face images of three types: same-identity, general imposter pairs (different identities from similar demographic groups), and twin imposter pairs (identical twin siblings). The task was to determine whether the pairs showed the same person or different people. Identity comparisons were tested in three viewpoint-disparity conditions: frontal to frontal, frontal to 45-degree profile, and frontal to 90-degree profile. Accuracy for discriminating matched-identity pairs from twin-imposters and general imposters was assessed in each viewpoint-disparity condition. Humans were more accurate for general-imposter pairs than twin-imposter pairs, and accuracy declined with increased viewpoint disparity between the images in a pair. A DCNN trained for face identification (Ranjan et al., 2018) was tested on the same image pairs presented to humans. Machine performance mirrored the pattern of human accuracy, but with performance at or above all humans in all but one condition. Human and machine similarity scores were compared across all image-pair types. This item-level analysis showed that human and machine similarity ratings correlated significantly in six of nine image-pair types [range r=0.38 to r=0.63], suggesting general accord between the perception of face similarity by humans and the DCNN. These findings also contribute to our understanding of DCNN performance for discriminating high-resemblance faces, demonstrate that the DCNN performs at a level at or above humans, and suggest a degree of parity between the features used by humans and the DCNN.

The COVID-19 pandemic has fueled the spread of misinformation on social media and the Web as a whole. The phenomenon dubbed `infodemic' has taken the challenges of information veracity and trust to new heights by massively introducing seemingly scientific and technical elements into misleading content. Despite the existing body of work on modeling and predicting misinformation, the coverage of very complex scientific topics with inherent uncertainty and an evolving set of findings, such as COVID-19, provides many new challenges that are not easily solved by existing tools. To address these issues, we introduce SciLander, a method for learning representations of news sources reporting on science-based topics. SciLander extracts four heterogeneous indicators for the news sources; two generic indicators that capture (1) the copying of news stories between sources, and (2) the use of the same terms to mean different things (i.e., the semantic shift of terms), and two scientific indicators that capture (1) the usage of jargon and (2) the stance towards specific citations. We use these indicators as signals of source agreement, sampling pairs of positive (similar) and negative (dissimilar) samples, and combine them in a unified framework to train unsupervised news source embeddings with a triplet margin loss objective. We evaluate our method on a novel COVID-19 dataset containing nearly 1M news articles from 500 sources spanning a period of 18 months since the beginning of the pandemic in 2020. Our results show that the features learned by our model outperform state-of-the-art baseline methods on the task of news veracity classification. Furthermore, a clustering analysis suggests that the learned representations encode information about the reliability, political leaning, and partisanship bias of these sources.

Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem. The challenges include huge diversity of images due to different environmental scenarios, drastic variation in the appearance of the same location depending on the time of the day, weather, season, and more importantly, the prediction is made from a single image possibly having only a few geo-locating cues. For these reasons, most existing works are restricted to specific cities, imagery, or worldwide landmarks. In this work, we focus on developing an efficient solution to planet-scale single-image geo-localization. To this end, we propose TransLocator, a unified dual-branch transformer network that attends to tiny details over the entire image and produces robust feature representation under extreme appearance variations. TransLocator takes an RGB image and its semantic segmentation map as inputs, interacts between its two parallel branches after each transformer layer, and simultaneously performs geo-localization and scene recognition in a multi-task fashion. We evaluate TransLocator on four benchmark datasets - Im2GPS, Im2GPS3k, YFCC4k, YFCC26k and obtain 5.5%, 14.1%, 4.9%, 9.9% continent-level accuracy improvement over the state-of-the-art. TransLocator is also validated on real-world test images and found to be more effective than previous methods., Comment: Accepted in ECCV 2022

Facial morphs created between two identities resemble both of the faces used to create the morph. Consequently, humans and machines are prone to mistake morphs made from two identities for either of the faces used to create the morph. This vulnerability has been exploited in "morph attacks" in security scenarios. Here, we asked whether the "other-race effect" (ORE) -- the human advantage for identifying own- vs. other-race faces -- exacerbates morph attack susceptibility for humans. We also asked whether face-identification performance in a deep convolutional neural network (DCNN) is affected by the race of morphed faces. Caucasian (CA) and East-Asian (EA) participants performed a face-identity matching task on pairs of CA and EA face images in two conditions. In the morph condition, different-identity pairs consisted of an image of identity "A" and a 50/50 morph between images of identity "A" and "B". In the baseline condition, morphs of different identities never appeared. As expected, morphs were identified mistakenly more often than original face images. Moreover, CA participants showed an advantage for CA faces in comparison to EA faces (a partial ORE). Of primary interest, morph identification was substantially worse for cross-race faces than for own-race faces. Similar to humans, the DCNN performed more accurately for original face images than for morphed image pairs. Notably, the deep network proved substantially more accurate than humans in both cases. The results point to the possibility that DCNNs might be useful for improving face identification accuracy when morphed faces are presented. They also indicate the significance of the ORE in morph attack susceptibility in applied settings., Comment: 4 figures, 11 pages

Relevant and timely information collected from social media during crises can be an invaluable resource for emergency management. However, extracting this information remains a challenging task, particularly when dealing with social media postings in multiple languages. This work proposes a cross-lingual method for retrieving and summarizing crisis-relevant information from social media postings. We describe a uniform way of expressing various information needs through structured queries and a way of creating summaries answering those information needs. The method is based on multilingual transformers embeddings. Queries are written in one of the languages supported by the embeddings, and the extracted sentences can be in any of the other languages supported. Abstractive summaries are created by transformers. The evaluation, done by crowdsourcing evaluators and emergency management experts, and carried out on collections extracted from Twitter during five large-scale disasters spanning ten languages, shows the flexibility of our approach. The generated summaries are regarded as more focused, structured, and coherent than existing state-of-the-art methods, and experts compare them favorably against summaries created by existing, state-of-the-art methods.

Artificial Intelligence (AI) is increasingly used to build Decision Support Systems (DSS) across many domains. This paper describes a series of experiments designed to observe human response to different characteristics of a DSS such as accuracy and bias, particularly the extent to which participants rely on the DSS, and the performance they achieve. In our experiments, participants play a simple online game inspired by so-called "wildcat" (i.e., exploratory) drilling for oil. The landscape has two layers: a visible layer describing the costs (terrain), and a hidden layer describing the reward (oil yield). Participants in the control group play the game without receiving any assistance, while in treatment groups they are assisted by a DSS suggesting places to drill. For certain treatments, the DSS does not consider costs, but only rewards, which introduces a bias that is observable by users. Between subjects, we vary the accuracy and bias of the DSS, and observe the participants' total score, time to completion, the extent to which they follow or ignore suggestions. We also measure the acceptability of the DSS in an exit survey. Our results show that participants tend to score better with the DSS, that the score increase is due to users following the DSS advice, and related to the difficulty of the game and the accuracy of the DSS. We observe that this setting elicits mostly rational behavior from participants, who place a moderate amount of trust in the DSS and show neither algorithmic aversion (under-reliance) nor automation bias (over-reliance).However, their stated willingness to accept the DSS in the exit survey seems less sensitive to the accuracy of the DSS than their behavior, suggesting that users are only partially aware of the (lack of) accuracy of the DSS.

Recommender systems typically suggest to users content similar to what they consumed in the past. If a user happens to be exposed to strongly polarized content, she might subsequently receive recommendations which may steer her towards more and more radicalized content, eventually being trapped in what we call a "radicalization pathway". In this paper, we study the problem of mitigating radicalization pathways using a graph-based approach. Specifically, we model the set of recommendations of a "what-to-watch-next" recommender as a d-regular directed graph where nodes correspond to content items, links to recommendations, and paths to possible user sessions. We measure the "segregation" score of a node representing radicalized content as the expected length of a random walk from that node to any node representing non-radicalized content. High segregation scores are associated to larger chances to get users trapped in radicalization pathways. Hence, we define the problem of reducing the prevalence of radicalization pathways by selecting a small number of edges to "rewire", so to minimize the maximum of segregation scores among all radicalized nodes, while maintaining the relevance of the recommendations. We prove that the problem of finding the optimal set of recommendations to rewire is NP-hard and NP-hard to approximate within any factor. Therefore, we turn our attention to heuristics, and propose an efficient yet effective greedy algorithm based on the absorbing random walk theory. Our experiments on real-world datasets in the context of video and news recommendations confirm the effectiveness of our proposal., Comment: To appear in the Web conference 2022 (WWW '22)

In this paper, we study the effects of using an algorithm-based risk assessment instrument to support the prediction of risk of criminalrecidivism. The instrument we use in our experiments is a machine learning version ofRiskEval(name changed for double-blindreview), which is the main risk assessment instrument used by the Justice Department ofCountry(omitted for double-blind review).The task is to predict whether a person who has been released from prison will commit a new crime, leading to re-incarceration,within the next two years. We measure, among other variables, the accuracy of human predictions with and without algorithmicsupport. This user study is done with (1)generalparticipants from diverse backgrounds recruited through a crowdsourcing platform,(2)targetedparticipants who are students and practitioners of data science, criminology, or social work and professionals who workwithRiskEval. Among other findings, we observe that algorithmic support systematically leads to more accurate predictions fromall participants, but that statistically significant gains are only seen in the performance of targeted participants with respect to thatof crowdsourced participants. We also run focus groups with participants of the targeted study to interpret the quantitative results,including people who useRiskEvalin a professional capacity. Among other comments, professional participants indicate that theywould not foresee using a fully-automated system in criminal risk assessment, but do consider it valuable for training, standardization,and to fine-tune or double-check their predictions on particularly difficult cases.

Music listening in today's digital spaces is highly characterized by the availability of huge music catalogues, accessible by people all over the world. In this scenario, recommender systems are designed to guide listeners in finding tracks and artists that best fit their requests, having therefore the power to influence the diversity of the music they listen to. Albeit several works have proposed new techniques for developing diversity-aware recommendations, little is known about how people perceive diversity while interacting with music recommendations. In this study, we interview several listeners about the role that diversity plays in their listening experience, trying to get a better understanding of how they interact with music recommendations. We recruit the listeners among the participants of a previous quantitative study, where they were confronted with the notion of diversity when asked to identify, from a series of electronic music lists, the most diverse ones according to their beliefs. As a follow-up, in this qualitative study we carry out semi-structured interviews to understand how listeners may assess the diversity of a music list and to investigate their experiences with music recommendation diversity. We report here our main findings on 1) what can influence the diversity assessment of tracks and artists' music lists, and 2) which factors can characterize listeners' interaction with music recommendation diversity.

Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an attribute. This might contribute to bias. Building on this intuition, we propose a novel distillation-based approach called Distill and De-bias (D&D) to enforce a network to attend to similar face regions, irrespective of the attribute category. In D&D, we train a teacher network on images from one category of an attribute; e.g. light skintone. Then distilling information from the teacher, we train a student network on images of the remaining category; e.g., dark skintone. A feature-level distillation loss constrains the student network to generate teacher-like representations. This allows the student network to attend to similar face regions for all attribute categories and enables it to reduce bias. We also propose a second distillation step on top of D&D, called D&D++. Here, we distill the `un-biasedness' of the D&D network into a new student network, the D&D++ network, while training this new network on all attribute categories; e.g., both light and dark skintones. This helps us train a network that is less biased for an attribute, while obtaining higher face verification performance than D&D. We show that D&D++ outperforms existing baselines in reducing gender and skintone bias on the IJB-C dataset, while obtaining higher face verification performance than existing adversarial de-biasing methods. We evaluate the effectiveness of our proposed methods on two state-of-the-art face recognition networks: ArcFace and Crystalface.

People recommender systems may affect the exposure that users receive in social networking platforms, influencing attention dynamics and potentially strengthening pre-existing inequalities that disproportionately affect certain groups. In this paper we introduce a model to simulate the feedback loop created by multiple rounds of interactions between users and a link recommender in a social network. This allows us to study the long-term consequences of those particular recommendation algorithms. Our model is equipped with several parameters to control (i) the level of homophily in the network, (ii) the relative size of the groups, (iii) the choice among several state-of-the-art link recommenders, and (iv) the choice among three different user behavior models, that decide which recommendations are accepted or rejected. Our extensive experimentation with the proposed model shows that a minority group, if homophilic enough, can get a disproportionate advantage in exposure from all link recommenders. Instead, when it is heterophilic, it gets under-exposed. Moreover, while the homophily level of the minority affects the speed of the growth of the disparate exposure, the relative size of the minority affects the magnitude of the effect. Finally, link recommenders strengthen exposure inequalities at the individual level, exacerbating the "rich-get-richer" effect: this happens for both the minority and the majority class and independently of their level of homophily., Comment: To appear in ICWSM 2022

This paper describes SciClops, a method to help combat online scientific misinformation. Although automated fact-checking methods have gained significant attention recently, they require pre-existing ground-truth evidence, which, in the scientific context, is sparse and scattered across a constantly-evolving scientific literature. Existing methods do not exploit this literature, which can effectively contextualize and combat science-related fallacies. Furthermore, these methods rarely require human intervention, which is essential for the convoluted and critical domain of scientific misinformation. SciClops involves three main steps to process scientific claims found in online news articles and social media postings: extraction, clustering, and contextualization. First, the extraction of scientific claims takes place using a domain-specific, fine-tuned transformer model. Second, similar claims extracted from heterogeneous sources are clustered together with related scientific literature using a method that exploits their content and the connections among them. Third, check-worthy claims, broadcasted by popular yet unreliable sources, are highlighted together with an enhanced fact-checking context that includes related verified claims, news articles, and scientific papers. Extensive experiments show that SciClops tackles sufficiently these three steps, and effectively assists non-expert fact-checkers in the verification of complex scientific claims, outperforming commercial fact-checking systems., Comment: Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM '21). November 1-5, 2021. QLD, Australia