[AISWorld] CFP: Special issue of the International Journal of Computational Intelligence

[xiangmin zhang]

Computational Intelligence: An International Journal
Special Issue on Explainable AI for Recommender Systems

Guest Editors:
Xiangmin Zhang, Wayne State University, US, ae9101 at wayne.edu
Aixin Sun, Nanyang Technological University, Singapore, axsun at ntu.edu.sg
Jiashu Zhao, Wilfrid Laurier University, Canada, jzhao at wlu.ca
Sherry Zhu, AI Singapore, Singapore, sherryzhu0309 at gmail.com;
sherryzhu at aisingapore.org

Introduction:
With the rise of various e-commerce, online video sharing & social media
platforms, and many other web services, recommender systems have attracted
more and more attention in the past few decades. Recommender systems aim to
suggest relevant items to users by studying past behaviors, preferences,
ratings, and other relevant data. Despite the rapid advances of recommender
systems recently, the application of “black-box” decision mechanisms to
recommender systems has become one of the key challenges, lacking
explainability
and interpretability. This is especially problematic for downstream tasks in
industries such as healthcare, manufacturing, insurance, and autonomous
vehicles. Explainable artificial intelligence (XAI), which refers to a set
of methods that empower the decision-making process with accuracy,
transparency, and fairness while allowing users/ system designers to
understand and trust the results generated by machine learning algorithms,
is a possible solution to tackle the problems stated above.
By bringing these two concepts together, the aim of this special issue is
to engage top-tier researchers from recommender systems and explainable AI
communities, to combine perspectives across different domains, to deliver
the state-of-the-art research insights, and to tackle the existing and
foreseeable
challenges together. It will focus on various applications of explainable
AI techniques to recommender systems and different use cases. For example,
we can target the human-computer interaction perspective of explainable
recommendations with explainable information sources and display
explanation format. We can also target different machine learning models,
including but not limited to topic modeling, graph-based models, deep
learning-based models, and knowledge graph-based approaches, that generate
explainability for recommender systems. We can also extend explainable AI
to different downstream recommendation tasks, such as e-commerce, social
media, financial product recommendations, and medical recommendations.
This special
issue will present a stage for researchers to showcase their research on the
advancement and the next generation of explainable recommender
systems, thus promoting
human-in-the-loop AI applications and bringing high-quality research
results to the common public.

Topics of interest:
We solicit original contributions to developing explainable AI for
recommender systems, including but not limited to the following topics:
- Explainable models that deliver persuasive explanations on model outputs,
and/or generate faithful interpretations to reflect and justify the decision
-making process
- Using Explainable AI to identify bias in recommender systems
- Explainable recommender systems with low-quality data and/or uncertainties
- Explainability and Human-in-the-Loop development of AI in recommender
systems
- Explainable AI to support interactive recommender systems
- Presentation and personalization of AI explanations to the recommendation
results for different target groups
- Privacy-aware recommender systems, including but not limited to federated
learning, and privacy protection mechanisms for ranking.
- Explainable AI for transparency, fairness, and unbiased decision-making in
recommender systems
- The recommender system developers’ perspective on explainable AI
- The recommender system users’ perspective on explainable AI
- Surveys, evaluations, or benchmarking on the state-of-the-art research in
the area of explainable recommender systems

Submission Information:
The guest editors are organizing the International Workshop on Explainable
AI for Recommender Systems associated with the 21st IEEE/WIC/ACM
International Conference on Web Intelligence and Intelligent Agent
Technology (WI-IAT22) to be held on November 17-20, 2022. We will invite
the authors of high-quality papers accepted by the workshop to submit an
extended version of their paper for consideration to be published in
this special
issue. Besides, we will also invite high-quality individual submissions to
submit
directly to this special issue.

Important Dates:
● Submission deadline: Dec 31st , 2022
● Author notification: Mar 15th , 2023
● Revised paper submission: April 30th , 2023
● Final acceptance: June 15th , 2023
-------------- next part --------------
A non-text attachment was scrubbed...
Name: SpecialIssueProposal-ExplainableAIForRecSystems..pdf
Type: application/pdf
Size: 104888 bytes
Desc: not available
URL: <http://lists.aisnet.org/pipermail/aisworld_lists.aisnet.org/attachments/20220725/b1e85a31/attachment-0001.pdf>