Search Results for author: Markus Schedl

Found 28 papers, 16 papers with code

Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters

1 code implementation29 Jan 2024 Shahed Masoudian, Cornelia Volaucnik, Markus Schedl, Navid Rekabsaz

Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing.

Fairness Retrieval

The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias

1 code implementation8 Jan 2024 Peter Müllner, Elisabeth Lex, Markus Schedl, Dominik Kowald

In this work, we study how DP impacts recommendation accuracy and popularity bias, when applied to the training data of state-of-the-art recommendation models.

Collaborative Filtering Recommendation Systems

A Study on Accuracy, Miscalibration, and Popularity Bias in Recommendations

3 code implementations1 Mar 2023 Dominik Kowald, Gregor Mayr, Markus Schedl, Elisabeth Lex

However, a study that relates miscalibration and popularity lift to recommendation accuracy across different user groups is still missing.

ReuseKNN: Neighborhood Reuse for Differentially-Private KNN-Based Recommendations

1 code implementation23 Jun 2022 Peter Müllner, Elisabeth Lex, Markus Schedl, Dominik Kowald

User-based KNN recommender systems (UserKNN) utilize the rating data of a target user's k nearest neighbors in the recommendation process.

Recommendation Systems

Unlearning Protected User Attributes in Recommendations with Adversarial Training

1 code implementation9 Jun 2022 Christian Ganhör, David Penz, Navid Rekabsaz, Oleg Lesota, Markus Schedl

We conduct experiments on the MovieLens-1M and LFM-2b-DemoBias datasets, and evaluate the effectiveness of the bias mitigation method based on the inability of external attackers in revealing the users' gender information from the model.

Collaborative Filtering

Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks

1 code implementation30 May 2022 Lukas Hauzenberger, Shahed Masoudian, Deepak Kumar, Markus Schedl, Navid Rekabsaz

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks.

Attribute Disentanglement

Do Perceived Gender Biases in Retrieval Results Affect Relevance Judgements?

no code implementations3 Mar 2022 Klara Krieg, Emilia Parada-Cabaleiro, Markus Schedl, Navid Rekabsaz

This work investigates the effect of gender-stereotypical biases in the content of retrieved results on the relevance judgement of users/annotators.

Information Retrieval Retrieval

Grep-BiasIR: A Dataset for Investigating Gender Representation-Bias in Information Retrieval Results

1 code implementation19 Jan 2022 Klara Krieg, Emilia Parada-Cabaleiro, Gertraud Medicus, Oleg Lesota, Markus Schedl, Navid Rekabsaz

To facilitate the studies of gender bias in the retrieval results of IR systems, we introduce Gender Representation-Bias for Information Retrieval (Grep-BiasIR), a novel thoroughly-audited dataset consisting of 118 bias-sensitive neutral search queries.

Information Retrieval Retrieval

Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?

no code implementations16 Aug 2021 Oleg Lesota, Alessandro B. Melchiorre, Navid Rekabsaz, Stefan Brandl, Dominik Kowald, Elisabeth Lex, Markus Schedl

In this work, in contrast, we propose to investigate popularity differences (between the user profile and recommendation list) in terms of median, a variety of statistical moments, as well as similarity measures that consider the entire popularity distributions (Kullback-Leibler divergence and Kendall's tau rank-order correlation).

Collaborative Filtering Music Recommendation +1

Predicting Music Relistening Behavior Using the ACT-R Framework

1 code implementation4 Aug 2021 Markus Reiter-Haas, Emilia Parada-Cabaleiro, Markus Schedl, Elham Motamedi, Marko Tkalcic, Elisabeth Lex

In this paper, we describe a psychology-informed approach to model and predict music relistening behavior that is inspired by studies in music psychology, which relate music preferences to human memory.

Recommendation Systems Retrieval

Content-driven Music Recommendation: Evolution, State of the Art, and Challenges

no code implementations25 Jul 2021 Yashar Deldjoo, Markus Schedl, Peter Knees

Based on a thorough literature analysis, we first propose an onion model comprising five layers, each of which corresponds to a category of music content we identified: signal, embedded metadata, expert-generated content, user-generated content, and derivative content.

Collaborative Filtering Music Recommendation +1

A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models

1 code implementation25 Jun 2021 Oleg Lesota, Navid Rekabsaz, Daniel Cohen, Klaus Antonius Grasserbauer, Carsten Eickhoff, Markus Schedl

In contrast to the matching paradigm, the probabilistic nature of generative rankers readily offers a fine-grained measure of uncertainty.

Passage Re-Ranking Passage Retrieval +3

Current Challenges and Future Directions in Podcast Information Access

no code implementations17 Jun 2021 Rosie Jones, Hamed Zamani, Markus Schedl, Ching-Wei Chen, Sravana Reddy, Ann Clifton, Jussi Karlgren, Helia Hashemi, Aasish Pappu, Zahra Nazari, Longqi Yang, Oguz Semerci, Hugues Bouchard, Ben Carterette

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.

Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers

1 code implementation28 Apr 2021 Navid Rekabsaz, Simone Kopeinik, Markus Schedl

In this work, we first provide a novel framework to measure the fairness in the retrieved text contents of ranking models.

Disentanglement Fairness +5

TripClick: The Log Files of a Large Health Web Search Engine

1 code implementation14 Mar 2021 Navid Rekabsaz, Oleg Lesota, Markus Schedl, Jon Brassey, Carsten Eickhoff

As such, the collection is one of the few datasets offering the necessary data richness and scale to train neural IR models with a large amount of parameters, and notably the first in the health domain.

Information Retrieval Retrieval

Support the Underground: Characteristics of Beyond-Mainstream Music Listeners

1 code implementation24 Feb 2021 Dominik Kowald, Peter Muellner, Eva Zangerle, Christine Bauer, Markus Schedl, Elisabeth Lex

In this paper, we study the characteristics of beyond-mainstream music and music listeners and analyze to what extent these characteristics impact the quality of music recommendations provided.

Recommendation Systems

Listener Modeling and Context-aware Music Recommendation Based on Country Archetypes

no code implementations11 Sep 2020 Markus Schedl, Christine Bauer, Wolfgang Reisinger, Dominik Kowald, Elisabeth Lex

To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences.

Music Recommendation

Do Neural Ranking Models Intensify Gender Bias?

1 code implementation1 May 2020 Navid Rekabsaz, Markus Schedl

Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies.

Passage Retrieval Retrieval +1

Utilizing Human Memory Processes to Model Genre Preferences for Personalized Music Recommendations

no code implementations24 Mar 2020 Dominik Kowald, Elisabeth Lex, Markus Schedl

In this paper, we introduce a psychology-inspired approach to model and predict the music genre preferences of different groups of users by utilizing human memory processes.

Global and country-specific mainstreaminess measures: Definitions, analysis, and usage for improving personalized music recommendation systems

no code implementations14 Dec 2019 Christine Bauer, Markus Schedl

We conduct rating prediction experiments in which we tailor recommendations to a user's level of preference for the music mainstream using the proposed 6 mainstreaminess measures.

Music Recommendation Recommendation Systems

The Unfairness of Popularity Bias in Music Recommendation: A Reproducibility Study

3 code implementations10 Dec 2019 Dominik Kowald, Markus Schedl, Elisabeth Lex

The recent work of Abdollahpouri et al. in the context of movie recommendations has shown that this popularity bias leads to unfair treatment of both long-tail items as well as users with little interest in popular items.

Music Recommendation Recommendation Systems

Modeling Artist Preferences of Users with Different Music Consumption Patterns for Fair Music Recommendations

no code implementations23 Jul 2019 Dominik Kowald, Elisabeth Lex, Markus Schedl

Music recommender systems have become central parts of popular streaming platforms such as Last. fm, Pandora, or Spotify to help users find music that fits their preferences.

Collaborative Filtering Recommendation Systems

An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation

no code implementations2 Oct 2018 Hamed Zamani, Markus Schedl, Paul Lamere, Ching-Wei Chen

We further report and analyze the results obtained by the top performing teams in each track and explore the approaches taken by the winners.

Sequential Recommendation

Cannot find the paper you are looking for? You can Submit a new open access paper.