Human-Centric Intelligent Systems - Call for Papers for the Special Issue: Towards Controllable, Interpretable, Robust Representation Learning for Data-driven Modeling
Guest Editors
Feng Zhao
Huazhong University of Science and Technology, Wuhan, China
Wei Wei
Huazhong University of Science and Technology, Wuhan, China
Lin Li
Wuhan University of Technology, Wuhan, China
Aims and Scope
The rise of online content has led to a surge in multi-modal data, including language, image, audio, and speech, which has given rise to the massive volume of data-driven fundamental theories and applications, such as pre-training modeling, visual question answering (VQA) and ChatGPT. This special issue focuses on all the topics highly-correlated to Controllable, Interpretable, Robust Representation Learning for Data-driven Modeling, and we accept only papers that meet the typical journal paper quality. It provides an opportunity to advance the development of data-driven modeling and to better universalize advanced techniques to a wider range of the general public, with a priority on cross-domain data modeling in complex scenarios for controllable generation, evaluation of deep learning models for model interpretability, de-noise/de-bias for model robustness.
Main topics and quality control
Topics of interest include, but are not limited to, the following:
NLP-domain:
- Explainable and interpretable models for NLP
- Conversational AI
- NLP, NLU and NLG for conversational sentiment detection
- NLP, NLU and NLG for conversational theme detection
- NLP, NLU and NLG for conversational personality detection
- NLP, NLU and NLG for conversational sarcasm, irony and humor
Multimedia-domain:
- Multimodal conversational AI
- Robust, efficient, or universal multimodal learning
- Multimodal transfer learning
- Multimodal metric learning
- Multimodal generation
- Sequential deep learning for visual question answering
- Reinforcement learning for visual question answering
- Temporal reasoning for video question answering
- Scene graph generation for visual question answering
- Real-world applications of cross-media analysis for visual question answering
Recommendation-domain:
- Multi-modal Recommendation
- Robust Recommendation
- Debiased Recommendation
- Explainable Recommendation
Information retrieval-domain:
- Cross-modal Retrieval
- Dense Retrieval
- Mining and Modeling Users
- Fairness and Bias in Search
- Personalization in Retrieval-Based Chatbots
Full papers will be subject to a strict review procedure for final selection to this special issue based on the following criteria:
1. Quality and originality in theory and methodology of the special issue.
2. Relevance to the topic of the special issue.
3. Application orientation which exhibits novelty.
Important date
Open Date: 30 August 2023
Close Date: 31 December 2024
Submit your paper
All papers have to be submitted via the Editorial Manager online submission and peer review system. Instructions will be provided on screen and you will be stepwise guided through the process of uploading all the relevant article details and files associated with your submission. During submission authors should indicate that their manuscript belongs to the special issue “Towards Controllable, Interpretable, Robust Representation Learning for Data-driven Modeling” (this question will appear at “Additional Information” step). All manuscripts must be in the English language.
To access the online submission site for the journal, please visit https://www.editorialmanager.com/hcin/default1.aspx (this opens in a new tab). Note that if this is the first time that you submit to the Human-Centric Intelligent Systems, you need to register as a user of the system first.
NOTE: Before submitting your paper, please make sure to review the journal's Author Guidelines (this opens in a new tab) first.
After Acceptance
This special issue will be published as a virtual collection that will be accessible at SpringerLink.
Accepted papers will be published online within about 20 days after acceptance, fully citable by DOI (Digital Object Identifier), prior to publication in the issue.
Introduction of the Guest Editors
Feng Zhao
Huazhong University of Science and Technology, Wuhan, China
Feng Zhao, professor and doctoral supervisor at Huazhong University of Science and Technology, has long been engaged in artificial intelligence, knowledge graph, cognitive computing, etc. He has published more than 60 papers in important journals/conferences at home and abroad such as ICDE, ICDM, EMNLP, CIKM, COLING and IEEE TBD, TSC, ACM TALLIP, and nearly 40 papers have been included in SCI. He has been authorized for 1 international invention patent and 20 national invention patents. Future research focuses on the low-resource knowledge graph and temporal knowledge graph.
Wei Wei
Huazhong University of Science and Technology, Wuhan, China
Dr. Wei Wei is a Professor, director of Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, in School of Computer Science and Technology at Huazhong University of Science and Technology (HUST), China. He received his Ph.D. degree in HUST, 2012. Prior to HUST, he is a research fellow in NTU and SMU, Singapore, respectively. His research interests include Natural Language Processing, Information Retrieval and Recommender, and Multi-modal Computing. He has published 90+ top journal/conference papers, e.g., ACL, AAAI, IJCAI, SIGKDD, SIGIR, WWW, SIGMOD, PVLDB, ICDE, CVPR, TKDE, TOIS, IEEE T-CYB and etc. He served as guest editor of JDSA, area-Chair of CCL’23/EMNLP’22, Post-Chair of SIGKDD’21 and PC/SPC of many top conferences.
Lin Li
Wuhan University of Technology, Wuhan, China
Lin Li is a Professor in School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China. Dr. Li received her MSc and BSc degrees in electrical engineering from Wuhan University of Technology, in 1999 and 2002, respectively, and Ph.D. degree in information science and technology from the University of Tokyo, Japan, in 2009. Her research interest covers Data analytics, Machine learning, Information retrieval, Web personalization & Recommendation, Social media mining, Natural language processing, and so forth. She has published over 100 research papers, including 20+ journal papers and papers at top-tier conferences.