Markus SchedlJohannes Kepler University Linz | JKU · Institute of Computational Perception
Markus Schedl
D.I. Mag. Dr.
About
361
Publications
84,931
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
7,981
Citations
Publications
Publications (361)
In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attributes (e.g., gender or ethnicity) from these user embeddings even without explicit access to them, resulting in mod...
This chapter briefly synthesizes the key themes discussed throughout this work and outlines a roadmap for future research directions in this critical field.
This chapter outlines potential privacy and security risks inherent in IRRSs. It explores how personal data and models can be protected and discusses relevant regulations and corresponding technical solutions. The chapter closes by discussing open challenges related to privacy and security in IRRSs and points to additional related work.
This chapter discusses recent regulatory and ethical aspects of transparency, clarifies the relevant terminology, and highlights the benefits, challenges, and barriers to transparency in IRRSs. It then discusses techniques for enhancing transparency in IRRSs, outlines how transparency can be evaluated and achieved via documentation, and presents ho...
This chapter reviews existing regulations on discrimination, provides a multifaceted categorization of biases and fairness criteria, discusses techniques to measure popularity and demographic biases, presents methods to mitigate harmful biases, and concludes with a reflection on open challenges.
This chapter investigates regulatory activities and policies in the European Union, the USA, and—considering its highly different cultural and political background—China, where regulation of AI and IRRSs has quite different aims than in the Western world.
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased language model on a downstream task can reintroduce biases into the model. Additionally, existing debiasing meth...
In today's data-rich environment, visualization literacy—the ability to understand and communicate information through charts—is increasingly important. However, constructing effective charts can be challenging due to the numerous design choices involved. Off-the-shelf systems and libraries produce charts with carefully selected defaults that users...
Most recommender systems adopt collaborative filtering (CF) and provide recommendations based on past collective interactions. Therefore, the performance of CF algorithms degrades when few or no interactions are available, a scenario referred to as cold-start. To address this issue, previous work relies on models leveraging both collaborative data...
Cognitive biases have been studied in psychology, sociology, and behavioral economics for decades. Traditionally, they have been considered a negative human trait that leads to inferior decision-making, reinforcement of stereotypes, or can be exploited to manipulate consumers, respectively. We argue that cognitive biases also manifest in different...
Recent work suggests that music recommender systems are prone to disproportionally frequent recommendations of music from countries more prominently represented in the training data, notably the US. However, it remains unclear to what extent feedback loops in music recommendation influence the dynamics of such imbalance. In this work, we investigat...
Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit deteriorated performance if one or more modalities are missing. In this work, we propose a modality invariant multimod...
The advancements of technology have led to the use of multimodal systems in various real-world applications. Among them, the audiovisual systems are one of the widely used multimodal systems. In the recent years, associating face and voice of a person has gained attention due to presence of unique correlation between them. The Face-voice Associatio...
Users' interaction or preference data used in recommender systems carry the risk of unintentionally revealing users' private attributes (e.g., gender or race). This risk becomes particularly concerning when the training data contains user preferences that can be used to infer these attributes, especially if they align with common stereotypes. This...
Many IR systems project harmful societal biases, including gender bias, in their retrieved contents. Uncovering and addressing such biases requires grounded bias measurement principles. However, defining reliable bias metrics for search results is challenging, particularly due to the difficulties in capturing gender-related tendencies in the retrie...
Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often random noise is added to the data to ensure Differential Privacy (DP). However, to date, it is not well understood in which ways this impacts personalized recommendations. In this work, we study how DP affec...
The music domain is among the most important ones for adopting recommender systems technology. In contrast to most other recommendation domains, which predominantly rely on collaborative filtering (CF) techniques, music recommenders have traditionally embraced content-based (CB) approaches. In the past years, music recommendation models that levera...
In this chapter, we discuss how to utilize human memory models for the task of modeling music preferences for recommender systems. Therefore, we discuss the theoretical underpinnings of using cog-nitive models for user modeling and recommender systems in order to introduce a model based on the cognitive architecture ACT-R to predict the music genre...
Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often random noise is added to the data to ensure Differential Privacy (DP). However, to date, it is not well understood in which ways this impacts personalized recommendations. In this work, we study how DP affec...
The relationship between music and emotion has been addressed within several disciplines, from more historico-philosophical and anthropological ones, such as musicology and ethnomusicology, to others that are traditionally more empirical and technological, such as psychology and computer science. Yet, understanding the link between music and emotio...
Emotion is an important component of music investigated in music psychology. In recent years, the use of computational methods to assess the link between music and emotions has been promoted by advances in music emotion recognition. However, one of the main limitations of applying data-driven approaches to understand such a link is the scarce knowl...
The usefulness of computer-based tools in supporting singing pedagogy has been demonstrated. With the increasing use of artificial intelligence (AI) in education, machine learning (ML) has been applied in music-pedagogy related tasks too, e. g., singing technique recognition. Research has also shown that comparing ML performance with human percepti...
State-of-the-art recommender systems produce high-quality recommendations to support users in finding relevant content. However, through the utilization of users' data for generating recommendations, recommender systems threaten users' privacy. To alleviate this threat, often, differential privacy is used to protect users' data via adding random no...
Recommender systems (RSs) have become an integral part of the hiring process, be it via job advertisement ranking systems (job recommenders) for the potential employee or candidate ranking systems (candidate recommenders) for the employer. As seen in other domains, RSs are prone to harmful biases, unfair algorithmic behavior, and even discriminatio...
In today's data-rich environment, visualization literacy—the ability to understand and communicate information through charts—is increasingly important. However, constructing effective charts can be challenging due to the numerous design choices involved. Off-the-shelf systems and libraries produce charts with carefully selected defaults that users...
User-based KNN recommender systems ( UserKNN ) utilize the rating data of a target user’s k nearest neighbors in the recommendation process. This, however, increases the privacy risk of the neighbors, since the recommendations could expose the neighbors’ rating data to other users or malicious parties. To reduce this risk, existing work applies dif...
User-based KNN recommender systems (UserKNN ) utilize the rating data of a target user's k nearest neighbors in the recommendation process. This, however, increases the privacy risk of the neighbors since their rating data might be exposed to other users or malicious parties. To reduce this risk, existing work applies differential privacy by adding...
Music listening has experienced a sharp increase during the last decade thanks to music streaming and recommendation services. While they offer text-based search functionality and provide recommendation lists of remarkable utility, their typical mode of interaction is unidimensional, i.e., they provide lists of consecutive tracks, which are commonl...
Recent research has suggested different metrics to measure the inconsistency of recommendation performance, including the accuracy difference between user groups, miscalibration, and popularity lift. However, a study that relates miscalibration and popularity lift to recommendation accuracy across different user groups is still missing. Additionall...
Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model's parameters, effectively transferring the model to a new, irreversible debiased state. In this work, we propose a novel approac...
This article contributes to a more adequate modelling of emotions encoded in speech, by addressing four fallacies prevalent in traditional affective computing: First, studies concentrate on few emotions and disregard all other ones (‘closed world’). Second, studies use clean (lab) data or real-life ones but do not compare clean and noisy data in a...
When we appreciate a piece of music, it is most naturally because of
its content, including rhythmic, tonal, and timbral elements as well
as its lyrics and semantics. This suggests that the human affinity
for music is inherently content-driven. This kind of information is,
however, still frequently neglected by mainstream recommendation
models base...
When we appreciate a piece of music, it is most naturally because of its content, including rhythmic, tonal, and timbral elements as well as its lyrics and semantics. This suggests that the human affinity for music is inherently content-driven. This kind of information is, however, still frequently neglected by mainstream recommendation models base...
The most common way to listen to recorded music nowadays is via streaming platforms, which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of music recommender systems (MRSs) has become essential. Current real‐world MRSs are often quite complex and optimized for recommendat...
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 jud...
Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users, e.g. gender, race, and location. These encoded biases can influence the decision of a recommendation system (RS) towards further separation of the contents provided to various demograp...
This chapter studies state-of-the-art research related to multimedia recommender systems (MMRS), focusing on methods that integrate multimedia content as side information to various recommendation models. The multimedia features are then used by an MMRS to recommend either (1) media items from which the features were derived, or (2) non-media items...
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 jud...
The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendati...
The results of information retrieval (IR) systems on specific queries can reflect the existing societal biases and stereotypes, which will be further propagated and straightened through interactions of the uses with the systems. We introduce Grep-BiasIR, a novel thoroughly-audited dataset which aim to facilitate the studies of gender bias in the re...
Music recommender systems have become an integral part of music streaming services such as Spotify and Last.fm to assist users navigating the extensive music collections offered by them. However, while music listeners interested in mainstream music are traditionally served well by music recommender systems, users interested in music beyond the main...
Renaissance music constitutes a resource of immense richness for Western culture, as shown by its central role in digital humanities. Yet, despite the advance of computational musicology in analysing other Western repertoires, the use of computer-based methods to automatically retrieve relevant information from Renaissance music, e. g., identifying...
The extent to which the sequence of tracks in music playlists matters to listeners is a disputed question, nevertheless a very important one for tasks such as music recommendation (e. g., automatic playlist generation or continuation). While several user studies already approached this question, results are largely inconsistent. In contrast, in thi...
Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends with and shape our social circles. In this paper, we study homophily in an online music platform Last...
Although recommender systems (RSs) play a crucial role in our society, previous studies have revealed that the performance of RSs may considerably differ between groups of individuals with different characteristics or from different demographics. In this case, a RS is considered to be unfair when it does not perform equally well for different group...
Several studies have identified discrepancies between the popularity of items in user profiles and the corresponding recommendation lists. Such behavior, which concerns a variety of recommendation algorithms, is referred to as popularity bias. Existing work predominantly adopts simple statistical measures, such as the difference of mean or median p...
Providing suitable recommendations is of vital importance to improve the user satisfaction of music recommender systems. Here, users often listen to the same track repeatedly and appreciate recommendations of the same song multiple times. Thus, accounting for users' relistening behavior is critical for music recommender systems. In this paper, we d...
The music domain is among the most important ones for adopting recommender systems technology. In contrast to most other recommendation domains, which predominantly rely on collaborative filtering (CF) techniques, music recommenders have traditionally embraced content-based (CB) approaches. In the past years, music recommendation models that levera...
Societal biases resonate in the retrieved contents of informationretrieval (IR) systems, resulting in reinforcing existing stereotypes.Approaching this issue requires established measures of fairness inrespect to the representation of various social groups in retrieval re-sults, as well as methods to mitigate such biases, particularly in thelight o...
Existing neural ranking models follow the text matching paradigm, where document-to-query relevance is estimated through predicting the matching score. Drawing from the rich literature of classical generative retrieval models, we introduce and formalize the paradigm of deep generative retrieval models defined via the cumulative probabilities of gen...
Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators. The great strides in search and recommendation in research and industry have yet to see impact in the podcast space, where recommendations are still largely driv...