Tutorial on
Operationalizing Treatments against Bias: Challenges and Solutions

to be held as part of the 43rd European Conference on Information Retrieval (ECIR2021)

March 28, 2021 09:00 13:00 CEST - ONLINE EVENT

Watch the video pitch at https://www.youtube.com/embed/QY_OY3di1ro!

Introduction

In recent years, the increasing adoption of machine learning in information retrieval has naturally and frequently shown biased and even discriminatory impacts in various domains (e.g., commerce, employment, healthcare, and education). The goal of this tutorial is to provide attendees with an overview on concepts, methodologies, and tools used to understand and mitigate bias and discrimination against individuals or demographics groups (e.g., based on gender, race, or religion), when machine learning is applied to generate rankings of items.

The first part of the tutorial will introduce real-world examples of how a bias can impact our modern society, the conceptual foundations underlying the study of bias and fairness in algorithmic decision-making, mindful of its social and legal context, and the strategies to plan, uncover, assess, reduce, and evaluate a bias in an information retrieval system. The second part of the tutorial will provide practical case studies to attendees, where they will be engaged in uncovering sources of bias and in designing countermeasures for personalized rankings generated by collaborative filtering. Strong emphasis will be given to the practical knowledge and best practices, which will be showcased with Jupyter Notebooks.

Target Audience

This tutorial aims to provide attendees with a prominent and timely perspective to consider while inspecting information retrieval outputs, leaving attendees with a solid understanding on how to integrate bias-related countermeasures in their research pipeline. By means of use cases on personalized rankings, the presented algorithmic approaches would help not only academic researchers but also industrial practitioners to better develop systems that tackle bias constraints. Specifically, this tutorial will be driven by the following learning objective pillars:

  • raise awareness on the importance and the relevance of considering data and algorithmic bias issues in information retrieval;
  • play with personalized personalized ranking pipelines and conduct exploratory analysis aimed at uncovering sources of bias along them;
  • operationalize approaches that mitigate bias along with the personalized ranking pipeline and assess their influence on stakeholders;
  • provide an overview on the trends and challenges in bias-aware research and identify new research directions in information retrieval.

Outline

Due to the ongoing worldwide COVID-19 situation, the Bias tutorial will take place online on March 28, 2021, 09:00-13:00, CEST.

Timing Content
09:00 09:05 Welcome and Presenters' Introduction
09:05 10:30 Session I: Foundations
Recommendation Principles
  • Recommendation principles. To introduce the problems associated to algorithmic bias, we will present the recommendation task as the generation of the most effective personalized ranking for a user, as in modern recommender systems.
  • Multi-sided recommendation aspects. Recommender systems have an impact on multiple actors, namely consumers, providers, system's owners. We will present these actors and the phases of the recommendation process where they have a role (design, algorithm, and evaluation).
Hands on Recommender Systems
  • Data preparation starting from public datasets (i.e., COCO and Movielens datasets).
  • Model definition (e.g., user/item embeddings, layers stacking) and training (e.g., epochs, loss, optimizer)
  • User-item relevance matrix computation from a pre-trained model (e.g., model load, predictions).
  • Model evaluation oriented to utility (e.g., NDCG, beyond-accuracy metrics).
Algorithmic Bias Foundations
  • Motivating examples. We will present real-world examples where bias can impact recommendation, considering domains such as music, education, social platforms, and recruiting.
  • Perspectives impacted by bias. Bias has an impact on several perspectives such as the economy, law, society, security, and psychology.
  • Ethical aspects influenced by bias. Bias can have an impact at the ethical level and lead to issues such as recommendation of inappropriate content, lack of privacy, violation of autonomy and identity, introduction of opacity, lack of fairness, or compromising social relationships.
  • Objectives influenced by bias. We will present recommendation objectives influenced by bias (utility, coverage, diversity, novelty, visibility, exposure) and provide examples of related work.
Bias through the Pipeline
  • Recommendation pipeline. We will provide an initial overview of the recommendation pipeline, to characterize how bias can exist at several stages, namely, data acquisition and storage, data preparation, model training, model prediction, model evaluation, and recommendation delivery.
  • Types of bias associated to the pipeline. We explore the types of bias that can emerge at different stages of the pipeline, i.e., those associated to the users, platforms, data collection, data preparation, model exploitation, and model evaluation.
10:30 11:00 Coffee Break
11:00 12:50 Session II: Mitigation
Bias Mitigation Design
  • Bias-aware process pipeline. Intervention strategies to mitigate algorithmic bias require an analysis of where and how bias might affect the system. We present a pipeline to support mitigation design.
  • Techniques for bias treatment. We will present the three main classes of mitigation techniques (pre-, in-, and post-processing), along with examples of solutions proposed for recommender systems.
  • Real-world applications. We will present examples of real-world platforms and of their approaches to deal with bias.
Hands on Item Popularity Bias
  • Definition and characterization of item popularity biases in interactions and recommendations.
  • Application of mitigation techniques based on pre-, in-, and post-processing.
  • Comparison of mitigation techniques based on bias and recommendation utility trade-offs.
  • Comparison of mitigation techniques on beyond-utility metrics (e.g., coverage, diversity, novelty).
Unfairness Mitigation Design
  • Types of discrimination. When bias affects users' sensitive attributes, it may lead to discrimination. We present concepts, such as direct/indirect discrimination, its granularity (group, individual, and subgroup discrimination), types of disparity (disparate treatment, impact, and mistreatment).
  • Definitions of fairness. We will present definitions of fairness and different classes in which thy can be categorized (equalized odds, equalized opportunity, demographic parity, fairness through (un)awareness, equality of treatment).
  • Techniques for unfairness treatment. We will present the three main classes of mitigation techniques (pre-, in-, and post-processing), along with examples of solutions proposed for recommender systems.
  • Real-world applications. We will present examples of real-world platforms and of their approaches to deal with unfairness.
Hands on Item Provider Fairness
  • Association of items to providers and sensitive attributes.
  • Characterization of providers representation in the catalog and in the interactions.
  • Identification of minority providers, both at individual and group level.
  • Definition and measurement of item provider unfairness on recommendations.
  • Application of mitigation techniques based on pre-, in-, and post-processing.
  • Comparison of mitigation techniques based on fairness and recommendation utility trade-offs.
  • Comparison of mitigation techniques on beyond-utility metrics (e.g., coverage, diversity, novelty).
12:50 13:00 Challenges, Final Remarks, and Discussion

Material

Presenters

Ludovico Boratto

Ludovico Boratto
EURECAT - Centre Tecnòlogic de Catalunya (Spain)

Ludovico Boratto is senior research scientist in at EURECAT. His research focuses on recommender systems and on their impact on stakeholders. His research has been published in top-tier conferences and journals. He is editor of the book "Group Recommender Systems: An Introduction" (Springer). He is editorial board member of the "Information Processing & Management" journal (Elsevier) and guest editor of other special issues. He is regularly PC member of the main Data Mining conferences. In 2012, he got a Ph.D. at the University of Cagliari, where he was research assistant until May 2016.



Mirko Marras

Mirko Marras
École Polytechnique Fédérale de Lausanne EPFL (Switzerland)

Mirko Marras is a Postdoctoral Researcher at the École Polytechnique Fédérale de Lausanne EPFL. His research focuses on data mining and machine learning for recommender systems, with attention to bias issues, mainly under online education settings. He authored papers in top-tier journals, such as Pattern Recognition Letters and Computers Human Behavior. He gave talks and demos at international conferences and workshops, e.g., TheWebConf2018, ECIR2019, and INTERSPEECH2019. He is PC member of major conferences, e.g., ACL, AIED, EDM, ECML-PKDD, EMNLP, ITICSE, ICALT, UMAP. He co-chaired the BIAS2020 workshop at ECIR2020 and gave a tutorial on Bias in Recommender Systems at UMAP2020 and ICDM2020. In 2020, he received a Doctoral Degree from University of Cagliari.

Contacts

Please, reaching out to us at ludovico.boratto@acm.org and mirko.marras@epfl.ch.

Past Editions

We also invite you to check out previous editions of our similar tutorials: