![]() |
| |||||||||||||||
SML 2019 : ICSC-2019 Semantic Machine Learning Workshop | |||||||||||||||
Link: https://ist.gmu.edu/~hpurohit/events/sml19/ | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
5th International Workshop on Semantic Machine Learning (SML-2019)
Co-located with IEEE ICSC-2019 Jan 30 – Feb 1, 2019 Newport Beach, California, USA Website: http://ist.gmu.edu/~hpurohit/events/sml19 Submissions due: Dec 07, 2018 (extended) ------------------ Aim and Scope ------------------ Learning is an important attribute of an AI system that enables it to adapt to new circumstances and to detect and extrapolate patterns. Machine Learning (ML), a field that formalizes and investigates computational learning, has seen a tremendous growth during the last few years due in part to the successful commercial deployments in products developed by major companies such as Google, Apple and Facebook. The interest has also being fuelled by the recent research breakthroughs brought about by deep learning. ML is however not a silver bullet as it is made out to be, and currently has several limitations in complex real-life situations. Some of these limitations include: i) many ML algorithms require large number of training data that are often too expensive to obtain in real-life, ii) significant effort is often required to do feature engineering to achieve high performance, iii) many ML methods are limited in their ability to exploit background knowledge, and iv) lack of a seamless way to integrate and use heterogeneous data from diverse knowledge bases. Approaches that formalize data, functional and domain semantics, can tremendously aid addressing some of these limitations. The so-called semantic approaches have been increasingly investigated by various research communities and applied at various layers of ML. For instance, deep learning can be considered as an approach to model representational semantics in vector space using deep neural architectures. An example of an approach using domain semantics for ML include the ontology-based ML methods, often investigated by the Data Mining researchers and bioinformaticians, and also by the Semantic Web and Semantic Computing community. The latter community, in particular, has made significant progress recently in establishing widely-accepted semantic technologies and standards that not only can facilitate greater industry adoption but can also enable incorporation of reasoning and inference in ML. Furthermore, advanced ML research can assist in addressing the limitations of background knowledge bases, including: a.) quality of structured knowledge and evolution, b.) sparsity of knowledge base attributes, and c.) heterogeneity of information representations across knowledge bases. This workshop will build upon the lessons from previous successful workshops for Semantic Machine Learning, including the last one at IJCAI 2017. This year’s focus is to generate interest towards making Machine Learning knowledgeable in terms of incorporating structured knowledge from various application domains and enhance the learning process at different stages of information processing. The event will bring together researchers and practitioners working on different aspects of semantic ML, to share their experiences, exchange new ideas for applying semantic ML in various application domains as well as to identify key emerging topics for future directions. Topics -------- Research papers are invited on all aspects of Semantic Machine Learning, including but not limited to the following: Semantic Modelling for ML Semantics and Deep Learning Ontology-based ML Using Linked Open Data and other Semantic Graphs for ML Link prediction from large graphs ML for Constructing and Maintaining Semantic Knowledge Bases Design, Development & Reuse of Semantic Resources for ML Semantic Reasoning and Inference in ML Semantic Feature Engineering Representational Semantics in ML Semantics and Transfer Learning Dynamic Knowledge graph Scalability in Semantic ML Theory and Analysis of Semantic ML Demos and Case Studies Applications to Web, Social Media, Mobile, Language Technologies, Vision, Healthcare, etc. Work-in-progress, industry applications/experiences and position papers are also welcome. Please submit your paper using the SML-2019 EasyChair site: https://easychair.org/conferences/?conf=sml19 Author Instructions: ------------------------ Manuscripts should be prepared according to the IEEE Author Guidelines (Check IEEE ICSC-19 Formatting Guidelines for LaTex Styles and Word Template: http://ieee-icsc.org). Submissions must be in English and provided as a PDF file. The length of manuscripts can be up to 6 pages. Work-in-process, Demo or Position papers may be shorter in length (2-4 pages) but, if accepted, are required to be expanded to 6 pages based on reviews. For more details: http://ist.gmu.edu/~hpurohit/events/sml19 Each manuscript will be judged on its originality, significance, technical quality, relevance, and presentation and will be peer reviewed. Authors are required to certify that their paper represents original work and is previously unpublished. Submitting a paper to SML-2019 workshop implies that if the paper is accepted, at least one author will register and attend the conference to present the paper. Prospective authors are strongly encouraged to get in touch with the chairs and express their interest and seek clarifications on their queries early. Important Dates ------------------- Paper Submission: Dec. 07, 2018 (extended) Author Notification: Dec. 18, 2018 Camera ready: Dec. 21, 2018 (All deadlines are 11:59PM Hawaii time.) Workshop Organization ---------------------- Chairs: Rajaraman Kanagasabai, Institute for Infocomm Research (I2R), Singapore Hemant Purohit, George Mason University, USA Ahsan Morshed, Swinburne University of Technology, Melbourne, Australia Advisory Committee: Prof. Amit Sheth, Wright State University, USA Prof. Fausto Giunchiglia, University of Trento, Trento, Italy Prof. Timos Sellis, Swinburne University of Technology, Australia |
|