DLP-KDD 2020:

Virtual Conference

Aug 24th 8am-12pm PDT

Conference Zoom Link: Click here

Live Streaming (Youtube): Click here

Live Streaming (For Chinese users): Click here

Tentative Schedule

Time	Event	Title
08:00-08:45	Keynote #1	Ji Liu (Kwai Inc.) Hammer! A uniform model compression and NAS framework
08:45-08:55		Opening intro & Best paper announcement
08:55-09:10	Oral talk #1	(Best Paper Runner-Up) Learning-To-Rank with Context-Aware Position Debiasing
09:10-09:25	Oral talk #2	(Best Paper Runner-Up) DCAF: A Dynamic Computation Allocation Framework for Online Serving System
09:25-09:40	Oral talk #3	(Best Paper Award) COLD: Towards the Next Generation of Pre-Ranking System
09:40-10:10		Coffee break & Poster session
10:10-10:55	Keynote #2	Jingbo Shang (University of California, San Diego) Named Entity Recognition from a Data-Driven Perspective
10:55-11:10	Oral talk #4	Automated Model Selection for Time-Series Anomaly Detection
11:10-11:25	Oral talk #5	Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction
11:25-11:40	Oral talk #6	Selling Products by Machine: a User-Sensitive Adversarial Training method for Short Title Generation in Mobile E-Commerce
11:40-11:55	Oral talk #7	PinText 2: Attentive Bag of Annotations Embedding
11:55-12:00		Ending

All the accepted papers can be found here

Website for dlp-kdd2019 can be found here

Introduction

In the increasingly digitalized world, it is of utmost importance for various applications to harness the ability to process, understand, and exploit data collected from the Internet. For instance, in customer-centric applications such as personalized recommendation, online advertising, and search engines, interest/intention modeling from customers’ behavioral data can not only significantly enhance user experiences but also greatly contribute to revenues. Recently, we have witnessed that Deep Learning-based approaches began to empower these internet- scale applications by better leveraging the massive data. However, the data in these internet-scale applications are high dimensional and extremely sparse, which makes it different from many applications with dense data such as image classification and speech recognition where Deep Learning-based approaches have been extensively studied. For example, the training samples of a typical click-through rate (CTR) prediction task often involve billions of sparse features, how to mine, model and inference from such data becomes an interesting problem, and how to leverage such data in Deep Learning could be a new research direction. The characteristics of such data pose unique challenges to the adoption of Deep Learning in these applications, including modeling, training, and online serving, etc. More and more communities from both academia and industry have initiated the endeavors to solve these challenges. This workshop will provide a venue for both the research and engineering communities to discuss the challenges, opportunities, and new ideas in the practice of Deep Learning on high-dimensional sparse data.

Important Dates

Submission deadline: ~~May 20, 2020~~ ~~June 10, 2020~~ June 14, 2020 23:59 anywhere on earth (We extended the deadline due to current COVID-19 situation)
Acceptance notification: ~~June 15, 2020~~ July 12, 2020.
Workshop date: August 24, 2020 (San Diego Convention Center, San Diego, California USA)

Workshop Format and Schedule

Half day. We would like to hold a half-day workshop in order to have enough new ground to cover invited academic and industry talks with a focus on many deep learning related areas. The tentative program schedule includes the following components:

Ten oral presentations from paper submissions for 15 minutes each
A poster session if there are lots of submissions for 45 minutes
Four invited talks with a mix of industry and academia for 1 hour each ! A panel discussion with 45 minutes

Topics of Interest

Topics include but are not limited to deep learning based network architecture design, large scale deep learning training framework, high-performance online inference engine or toolkits that help breaking the black box of deep learning models, such as

Large Scale User Response Prediction Modeling
Representation Learning for High-dimensional Sparse Data
Embedding techniques, manifold learning and dictionary learning
User Behaviour Understanding
Large Scale Recommendation and Retrieval System
Model compression for industrial application
Scalable, Distributed and Parallel Training System for Deep Learning
High throughput and low latency real time Serving System
Applications of transfer learning, meta learning for sparse data
Auto Machine Learning, Auto feature selection
Explainable deep learning for high dimensional data
Data augmentation, Anomaly Detection for High-dimensional Sparse data
Generative Adversarial Network for sparse data
Other challenges encountered in real-world applications

Call for papers

Official call for papers page is on https://easychair.org/cfp/dlp-kdd2020

Submissions are invited on describing innovative research on real-world data systems and applications, industrial experiences and identification of challenges that deploy research ideas in practical applications. Work-in-progress papers are also encouraged.

Full-length papers (up to 9 pages) or extended abstracts (2-4 pages) are welcome. Submissions must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template.

Reviews are not double-blind, and author names and affiliations should be listed. Please use the KDD official guidelines to format your paper.

All submissions can be made through EasyChair using the following link: https://easychair.org/conferences/?conf=dlpkdd2020

For all the accepted paper, we provide the option that it could be archived in ACM Digtal Library. You may see the publication of last year at https://dl.acm.org/doi/proceedings/10.1145/3326937

If you have any questions about submissions or our workshop, please contact dlpkddworkshop@gmail.com