3rd Workshop on Deep Learning for Recommender Systems DLRS 2018

征稿已开启

已截稿

注册已开启

已截止

活动简介

The workshop centers around the use of Deep learning technology in Recommender Systems and algorithms. DLRS 2018 builds upon the positively received traits of previous DLRS workshops. DLRS 2018 is a fast paced half-day workshop with a focus on high quality paper presentations and invited talks . We welcome original research using deep learning technology for problems promoters systems related problems (see the CFP for more details). This year we also encourage experimental experiments in new research directions and fields of application.

Deep learning is now one of the most quickly evolving and important research topics in Recommendation Systems technology. While the deep learning boom happened only (2016-2017) for recommender systems – with DLRS 2016 and 2017 also taking its share of popularizing the topic – It is now generally accepted that deep learning has a huge untapped potential for the recommendation domain as well. We would like to strengthen this idea further with DLRS 2018 and to help the community discover new ways of using deep learning for recommendations. The aim of the Workshop is to encourage the application of Deep Learning techniques in Recommender Systems, to further promote research in deep learning methods for Recommender Systems, and to bring together researchers from the Recommender Systems and Deep Learning communities.

组委会

ORGANIZING COMMITTEE

Balázs Hidasi (@balazshidasi)
Alexandros Karatzoglou (@alexk_z)
Oren Sar-Shalom (@oren_sarshalom)
Sander Dieleman (@sedielem)
Bracha Shapira (@brachashapira)
Flavian Vasile ()
Domonkos Tikk (@domonkostikk)

征稿信息

重要日期

2018-07-16

初稿截稿日期

2018-08-13

初稿录用日期

We encourage theoretical, experimental, and methodological developments advancing state-of-the-art knowledge in the area of Recommender Systems and Deep Learning. Areas of interest also encompass novel applications, using Deep Learning to solve the still-standing challenges in personalization technology, and applications of Deep Learning in related fields with clear relation to Recommender Systems. This year we further encourage exploring new research directions and application domains. Topics include, but are not limited to the following:

I. Generative models for recommendations

Recommending sets of items
Diversification of recommendations
Data augmentation

II. Novel domains and uses of recommendations made possible by deep learning

Novel domains
Privacy-aware recommendations

III. User and item representations

Enhancement of existing recommendation algorithms through deep learning methods
Learning representations of items and/or users using multiple information sources

IV. Dynamic behavior modeling

Dynamic temporal user behavior modeling
Session and intention modeling

V. Specialized recommendation methods using deep learning techniques

Incorporating unstructured data sources such as text, audio, video or image into recommendation algorithms
Context-aware recommender systems
Handling the cold-start problem with deep learning
Application specific deep learning based recommenders (e.g. music recommenders)

VI. Architecture

Novel deep neural network architectures for a particular recommendation task
Scalability of deep learning methods for real-time applications
Advances in deep learning technology for large scale recommendation
Special layers or units designed for recommender systems
Special activation functions or operators designed for recommender systems

VII. Novel evaluation and explanation techniques

Evaluation and comparison of deep learning implementations for a recommendation task
Modeling the state of the user
Sensitivity analysis of the network architecture
Explanation of recommendations based on deep learning

作者指南

Submissions and reviews are handled electronically via EasyChair at the following address: https://easychair.org/conferences/?conf=dlrs2018. Submissions should be prepared in PDF format according to the standard double-column ACM SIG proceedings format. Authors must submit their papers to arxiv.org simultaneously and send the assigned arxiv ID to workshop email address once it is assigned. Failing to send the arxiv ID within at most two weeks from the submission deadline will result in the rejection of the paper.

The ideal length of a paper for DLRS 2018 is between 4-8 pages, but submissions have no strict page limits. Although the authors should avoid submitting unnecessarily long papers in order not to overwhelm reviewers.

DLRS 2018 accepts original and novel contributions that are neither published nor under review in other venues. Self publishing of the submitted papers in public repositories is permitted and encouraged. We also encourage authors to make their code and datasets publicly available.

Papers must be electronically submitted through EasyChair by 23:59 (AoE timezone) on the 16 July, 2018. The authors must also submit their papers to arxiv.org simultaneously and email the arxiv ID to the organizers on the workshop’s email address.

All papers are peer reviewed by at least 3 members of the Program Committee consisting of researchers of deep learning and recommender systems.

Accepted papers are published in the workshop proceedings (published in ACM ICPS) and indexed in the ACM Digital Library. Accepted papers are given either an oral or a poster presentation slot at the workshop. At least one author of every accepted paper must attend the workshop And present their work.