Deep Learning (DL) has recently been widely applied to user modeling for real-world applications such as context-aware recommendation or location-aware services. However, many studies focus on building DL models only in one or few domains and applying them to identical domains. Thus, how to build ubiquitous and multi-domain user models and increase their applicability in real-world contexts remain an open problem. Here, we refer to “ubiquitous” as the capability to adapt to, and therefore exist in diverse contexts, and “multi-domain” as the capability of training using data from multiple domains.
There are several challenges towards realizing ubiquitous and multi-domain user modeling, as follows:
- Real-world environment is a mixed environment in which many users and many objects are interacting in various ways. How to learn diverse contexts from user-object interaction data obtained from smartphones, IoT platforms, customer bases, and so on, is a challenge.
- Collecting personal data from multiple domains and aggregating them in one place become increasingly difficult due to privacy concerns or huge data volume. How to model different user behaviors in each individual domain, integrate the models to enhance every prediction and, consequently, improve modeling performance is another challenge.
- The relationships between multiple domains may change from time to time. Therefore, it will be a challenge to detect and adapt to such changes so that the performance of the models do not degrade.
We invite contributions to the workshop about topics related to UMUM (but not limited to):
- Personalization, Recommendation
- Context-aware Recommendation
- Cross-domain Recommendation
- Location-aware Services
- Deep Learning, Transfer Learning, Domain Adaptation, Multi-task Learning, Meta Learning
- Self-supervised Learning, Un/Semi/Weekly-supervised Learning, Representation Learning
- Knowledge Representation, Knowledge Reasoning
- Federated Learning, Privacy Preserving Data Mining
- Time Series Data Analysis, Spatio-temporal Data Mining
- Concept Drift
Paper Submission and Guidelines
- Papers should be submitted through EAI ‘Confy+‘ system (Please select ‘Springer regular paper‘ as paper length).
- All workshop papers should be prepared in the Springer format with 12-15+ pages.
- Reviewing system is double-blind, and thus the submitted paper should be anonymized. (You will be asked to supply identification in the camera-ready paper.)
- Paper templates are provided in
https://mobiquitous.eai-conferences.org/2021/submission/#authorskit (The same as Mobiquitous main conference)
- Paper submission open: 17th June, 2021.
- Paper submission deadline:
25th July, 2021 Extended to 10th August, 2021Extended to 1st September, 2021. (Time Zone: UTC)
- Author notification deadline:
29th August, 2021Extended to 20th September, 2021.
- (Firm) Camera-ready deadline:
14th September, 2021 Extended to 30th September, 2021 Extended to 10th October, 2021Extended to 17th October, 2021.
- Workshop day: 8th November, 2021.