mlsanityData to 7 Oct 2026

Towards User-Centered Metrics for Trustworthy AI in Immersive Cyberspace

arXiv 2203.03718 ↗First posted 22 Feb 2022cs.CY cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

AI plays a key role in current cyberspace and future immersive ecosystems that pinpoint user experiences. Thus, the trustworthiness of such AI systems is vital as failures in these systems can cause serious user harm. Although there are related works on exploring trustworthy AI (TAI) metrics in the current cyberspace, ecosystems towards user-centered services, such as the metaverse, are much more complicated in terms of system performance and user experience assessment, thus posing challenges for the applicability of existing approaches. Thus, we give an overlook on fairness, privacy and robustness, across the historical path from existing approaches. Eventually, we propose a research agenda towards systematic yet user-centered TAI in immersive ecosystems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 65 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

13 of 65 references.

References · 13

  1. 2016Universal adversarial perturbationscited by 774
  2. 2016Wide & Deep Learning for Recommender Systemscited by 745
  3. 2018Fairness of Exposure in Rankingscited by 189
  4. 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 137
  5. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  6. 2021All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agendacited by 67
  7. 2018Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systemscited by 37
  8. 2018Reducing Disparate Exposure in Ranking: A Learning To Rank Approachcited by 33
  9. 2018Adversarial Training Towards Robust Multimedia Recommender Systemcited by 27
  10. 2018User Fairness in Recommender Systemscited by 20
  11. 2018Bias Disparity in Recommendation Systemscited by 12
  12. 2020Learn to Schedule (LEASCH): A Deep reinforcement learning approach for radio resource scheduling in the 5G MAC layercited by 8
1 more
  1. 2020Towards Augmented Reality-driven Human-City Interaction: Current Research on Mobile Headsets and Future Challengescited by 6

Built on by

Not cited yet.