The international workshop IFUP 2018 will be co-located with WSDM 2018: The 11th ACM International Conference on Web Search and Data Mining, to be held in Los Angeles, California during Feb 6-8, 2018.
Serving billions of recommendations daily @ Twitter
Speakers: Ajeet Grewal @ajeet, Senior Manager; Yao Wu @_yaowu_, Software Engineer
Abstract: Twitter is what’s happening in the world and what people are talking about right now. Given the real-time nature of this platform, discovery or helping users find what they want at the right time is a key challenge. The Recommendation team at Twitter builds infrastructure and machine learning models to address these challenges for many products such as who-to-follow, push & email recommendation, etc. In this talk, we will discuss some of these problems and the interesting challenges they pose at scale, as well as diving into specific applications.
Ajeet Grewal (@ajeet) is a Sr. Manager at Twitter, where he leads the Recommendations team. It comprises of researchers and engineers who are building the next generation of algorithms and systems powering recommendation systems. He also leads the content understanding team at Twitter, which works on core NLP problems across many different languages. Earlier, he was a Sr. Research Engineer at Yahoo! working on systems powering content classification and named entity linking across the company.
Yao Wu (@_yaowu_) is currently a Machine Learning Engineer at Recommendations team of Twitter, where he is working on the infrastructure and relevance modeling that power all the user recommendations on Twitter. Prior to that, he obtained his PhD in Data Mining from Simon Fraser University in Canada.
Real-world systems accumulate large-scale and various kinds of multimodal information rapidly, including but not limited to text, image, video, audio, social relations, meta data, etc. Such information has been incorporated in many recommendation models and systems to promote the performance and user experience, giving rise to some of the recent and/or classical topics in recommender system, such as review-based recommendation, image-based recommendation, explainable recommendation, deep learning for recommendation, POI recommendation, video/music recommendation, and many others.
Integrating multimodal side information is not a trivial task, because information may be either homogenous or heterogeneous, which requires more advanced method for information fusion and alignment. Besides, different information may play distinct roles for different domains, users, and tasks, and the availability of new information source may even lead to completely new recommendation research tasks. As a result, it needs significant efforts from both the research community and industry to promote the recommendation system research and application in face of the various information sources.
IFUP 2018 aims to provide a dedicated forum for discussing open problems, challenges and innovative research approaches in fusing multi-dimensional information for user modelling and recommender systems. The major goal of this workshop is to promote advanced recommendation solutions that can be easily and readily deployed to meet industrial demands for personalized recommendation.
Topics of the workshop include but are not limited to:
We also welcome papers that are broadly related to the topics even if they are not explicitly listed above.
All workshop submissions must be formatted according to ACM SIG Proceedings template, and we welcome submissions either long or short format:
Authors should submit original papers in PDF format through the Easychair system at: https://easychair.org/conferences/?conf=ifup2018