paper-with-me

홈 › Papers

Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives

2023-07-31 · Haoyang Liu, Maheep Chaudhary, Haohan Wang

The trustworthiness of machine learning has emerged as a critical topic in the field, encompassing various applications and research areas such as robustness, security, interpretability, and fairness. The last decade saw the development of numerous methods addressing these challenges. In this survey, we systematically review these advancements from a data-centric perspective, highlighting the shortcomings of traditional empirical risk minimization (ERM) training in handling challenges posed by the data. Interestingly, we observe a convergence of these methods, despite being developed independently across trustworthy machine learning subfields. Pearl's hierarchy of causality offers a unifying framework for these techniques. Accordingly, this survey presents the background of trustworthy machine learning development using a unified set of concepts, connects this language to Pearl's causal hierarchy, and finally discusses methods explicitly inspired by causality literature. We provide a unified language with mathematical vocabulary to link these methods across robustness, adversarial robustness, interpretability, and fairness, fostering a more cohesive understanding of the field. Further, we explore the trustworthiness of large pretrained models. After summarizing dominant techniques like fine-tuning, parameter-efficient fine-tuning, prompting, and reinforcement learning with human feedback, we draw connections between them and the standard ERM. This connection allows us to build upon the principled understanding of trustworthy methods, extending it to these new techniques in large pretrained models, paving the way for future methods. Existing methods under this perspective are also reviewed. Lastly, we offer a brief summary of the applications of these methods and discuss potential future aspects related to our survey. For more information, please visit http://trustai.one.

📄 PDF Abstract BibTeX arXiv:2307.16851

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessFairnessparameter-efficient fine-tuningSurvey

Similar Papers 제목 키워드 기반

A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness

2022-12-18 · Tiantian Feng, Rajat Hebbar, Nicholas Mehlman, Xuan Shi 외

Speech-centric machine learning systems have revolutionized many leading domains ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each othe…

Fairness

Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context

2020-07-17 · Ehsan Toreini, Mhairi Aitken, Kovila P. L. Coopamootoo, Karen Elliott 외

Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to address fairness, accountability, transparency an…

BIG-bench Machine LearningFairness

A Comprehensive Data-centric Overview of Federated Graph Learning

2025-07-22 · Zhengyu Wu, Xunkai Li, Yinlin Zhu, Zekai Chen 외 arxiv

In the era of big data applications, Federated Graph Learning (FGL) has emerged as a prominent solution that reconcile the tradeoff between optimizing the collective intelligence between decentralized datasets holders an…

Federated LearningGraph Learning

Trustworthy Federated Learning: A Survey

2023-05-19 · Asadullah Tariq, Mohamed Adel Serhani, Farag Sallabi, Tariq Qayyum 외

Federated Learning (FL) has emerged as a significant advancement in the field of Artificial Intelligence (AI), enabling collaborative model training across distributed devices while maintaining data privacy. As the impor…

FairnessFederated LearningSurvey

Machine Learning Robustness: A Primer

2024-04-01 · Houssem Ben Braiek, Foutse khomh

This chapter explores the foundational concept of robustness in Machine Learning (ML) and its integral role in establishing trustworthiness in Artificial Intelligence (AI) systems. The discussion begins with a detailed d…

software testingTransfer Learning