Technical and Regulatory Perspectives on Information Retrieval and Recommender Systems: Fairness, Transparency, and Privacy
Schedl, Markus, Anelli, Vito Walter, Lex, Elisabeth
相關主題
商品描述
This book provides an in-depth treatment of three important topical areas related to regulatory, ethical, and technical discussions in the context of information retrieval and recommender systems (IRRSs): (1) bias, fairness, and non-discrimination, (2) transparency and explainability, and (3) privacy and security. Sometimes referred to as trustworthiness dimensions, they are analyzed by taking an interdisciplinary perspective and incorporating views from computer science, social sciences, psychology, and law and by particularly considering the related technical challenges, societal impact, ethical considerations, and regulatory approaches.
After an introduction, the book first provides an overview of recent initiatives and already operational policies to regulate AI technology and discusses them in the context of IRRSs, focusing on regulations in Europe, the US, and China. Subsequent chapters present categories of biases, their relation to fairness and non-discrimination and ways to discover and mitigate harmful biases; major facets of transparency, with a focus on explainability (including common strategies to achieve it), traceability, and auditability; and privacy and security including technical approaches to mitigate privacy risks such as anonymization techniques and encryption methods. Eventually, the last chapter provides an outlook on the grand challenges in IRRSs, such as dealing with discrepancies between formal attempts, human perception, and regulatory frameworks for trustworthy IRRSs; understanding the capabilities and limitations of existing solutions in terms of fairness, transparency, and privacy; and adopting a multistakeholder perspective when developing solutions for fair, transparent, and privacy-preserving IRRSs.
The book targets a mostly technical readership and aims to equip it with the necessary understanding of the ethical implications of their research and development in IRRSs as well as of recent policy initiatives and regulatory approaches. While a basic knowledge of IRRSs is assumed to fully comprehend the more technical and algorithmic parts of the book, even a lay audience in terms of technical background should benefit from the book.
商品描述(中文翻譯)
本書深入探討三個與資訊檢索和推薦系統（IRRSs）相關的重要主題領域，這些領域涉及監管、倫理和技術討論：(1) 偏見、公平性和非歧視，(2) 透明度和可解釋性，以及 (3) 隱私和安全。有時被稱為可信度維度，這些主題透過跨學科的視角進行分析，並結合計算機科學、社會科學、心理學和法律的觀點，特別考慮相關的技術挑戰、社會影響、倫理考量和監管方法。
在介紹之後，本書首先概述了最近的倡議和已經運作的政策，以監管人工智慧技術，並在 IRRSs 的背景下討論這些政策，重點關注歐洲、美國和中國的監管情況。隨後的章節介紹了偏見的類別、它們與公平性和非歧視的關係，以及發現和減輕有害偏見的方法；透明度的主要面向，特別關注可解釋性（包括實現可解釋性的常見策略）、可追溯性和可審計性；以及隱私和安全，包括減輕隱私風險的技術方法，如匿名化技術和加密方法。最後一章提供了 IRRSs 中的重大挑戰展望，例如處理正式嘗試、人類感知和可信 IRRSs 的監管框架之間的差異；理解現有解決方案在公平性、透明度和隱私方面的能力和限制；以及在開發公平、透明和保護隱私的 IRRSs 解決方案時採取多方利益相關者的視角。
本書主要針對技術讀者，旨在使其具備對 IRRSs 研究和開發的倫理影響以及最近政策倡議和監管方法的必要理解。雖然假設讀者對 IRRSs 有基本的了解，以便充分理解書中更技術性和算法性的部分，但即使是技術背景較淺的讀者也應能從本書中受益。
作者簡介
Markus Schedl is a full professor at Johannes Kepler University (JKU) Linz, Austria, affiliated with the Institute of Computational Perception, leading the Multimedia Mining and Search Group. In addition, he is the head of the Human-centered AI group at the Linz Institute of Technology (LIT) AI Lab. His main research interests revolve around fairness, transparency, and privacy of recommender systems and language models. Markus is a key researcher in Austria's Cluster of Excellence project "Bilateral Artificial Intelligence" and has been the PI of numerous fundamental research projects.
Vito Walter Anelli is an assistant professor (researcher tenure track) at Politecnico di Bari, Italy. His research primarily focuses on recommender systems, knowledge representation, and user modeling. He has contributed to these fields with publications in highly recognized journals and conferences. A key area of his work involves the privacy and security of recommender systems, with particular emphasis on federated learning approaches and adversarial learning techniques. On these topics, he has delivered several tutorials and also authored a chapter of the Recommender Systems Handbook.
Elisabeth Lex is an associate professor at Graz University of Technology and principal investigator of the Recommender Systems and Social Computing Lab at the Institute of Interactive Systems and Data Science. Her research interests include recommender systems, user modeling, information retrieval, and data science, with a particular focus on psychology-informed and responsible recommender systems as well as human decision making. Elisabeth has authored numerous papers and delivered several tutorials on these topics in top venues. She also holds seminars jointly with legal scholars specialized in minority rights and non-discrimination.
作者簡介(中文翻譯)
馬庫斯·謝德爾（Markus Schedl）是奧地利林茲約翰·開普勒大學（Johannes Kepler University, JKU）的全職教授，隸屬於計算感知研究所，並領導多媒體挖掘與搜尋小組。此外，他還是林茲科技學院（Linz Institute of Technology, LIT）人工智慧實驗室人本中心人工智慧小組的負責人。他的主要研究興趣圍繞推薦系統和語言模型的公平性、透明性和隱私性。馬庫斯是奧地利卓越集群計畫「雙邊人工智慧」的關鍵研究人員，並曾擔任多個基礎研究項目的主要研究者。
維托·瓦爾特·阿內利（Vito Walter Anelli）是義大利巴里理工大學（Politecnico di Bari）的助理教授（研究者任期追蹤）。他的研究主要集中在推薦系統、知識表示和使用者建模。他在這些領域發表了多篇高水平的期刊和會議論文。其工作的一個關鍵領域涉及推薦系統的隱私和安全，特別強調聯邦學習方法和對抗學習技術。在這些主題上，他提供了多個教程，並撰寫了《推薦系統手冊》中的一章。
伊莉莎白·萊克斯（Elisabeth Lex）是格拉茨科技大學（Graz University of Technology）的副教授，並擔任互動系統與數據科學研究所推薦系統與社會計算實驗室的主要研究者。她的研究興趣包括推薦系統、使用者建模、資訊檢索和數據科學，特別關注心理學知識導向和負責任的推薦系統以及人類決策。伊莉莎白已發表多篇論文，並在頂尖會議上提供了多個相關主題的教程。她還與專注於少數群體權利和非歧視的法律學者共同舉辦研討會。
