KDD 2017 已于近日落下帷幕,作为数据科学、信息检索、数据挖掘和机器学习的顶级会议,KDD 为学术界和工业界提供了一个宝贵的交流机会。
一直以来,谷歌都是 KDD 的积极参与者,自然,今年的 KDD 也不例外,一起和雷锋网 AI 科技评论来看看谷歌是如何深度参与 KDD 的吧。
以下是谷歌深度参与或介入的 KDD 活动议程全名单,雷锋网AI科技评论编译如下:
Panel 主席: Andrew Tomkins
研究程序委员会主席: Ravi Kumar
应用数据科学程序委员会主席: Roberto J. Bayardo
研究程序委员会: Sergei Vassilvitskii, Alex Beutel, Abhimanyu Das, Nan Du, Alessandro Epasto, Alex Fabrikant, Silvio Lattanzi, Kristen Lefevre, Bryan Perozzi, Karthik Raman, Steffen Rendle, Xiao Yu
应用数据科学程序委员会: Edith Cohen, Ariel Fuxman, D. Sculley, Isabelle Stanton, Martin Zinkevich, Amr Ahmed, Azin Ashkan, Michael Bendersky, James Cook, Nan Du, Balaji Gopalan, Samuel Huston, Konstantinos Kollias, James Kunz, Liang Tang, Morteza Zadimoghaddam
Bryan Perozzi
论文名称:Local Modeling of Attributed Graphs: Algorithms and Applications
论文地址:http://perozzi.net/publications/16_thesis.pdf
SIGKDD 2017 的博士论文奖被谷歌的 Bryan Perozzi 摘得,这一奖项被授予在数据挖掘和知识发现领域有所建树的杰出博士生。
这一奖项是为了肯定他在石溪大学跟随 Steven Skiena 教授所做的图表机器学习研究课题《Local Modeling of Attributed Graphs: Algorithms and Applications》,其中的一部分内容是 Perozzi 在 Google 实习期间完成的。
这一研究课题使用局限图原语(例如 ego-network 和截取的随机散列)有效地利用每个顶点周围的信息进行分类、聚类和异常检测。值得一提的是,这项工作在 DeepWalk 中采用了神经网络图形嵌入的随机游走范式。
《DeepWalk: Online Learning of Social Representations》实际上是 Bryan Perozzi 最初在 KDD』14 投递的一篇论文,论文使用从截断的随机游走获得的一系列本地信息,以学习图中节点的潜在表征(如社交网络用户)的方法。其核心思想是将随机游走的每一段都视为「图形语言中」( 「in the language of the graph」 )的句子,然后可以使用这些片段作为神经网络模型的输入来学习图形节点的表征。这项研究将继续在谷歌进行,比如最近的 Learning Edge Representations via Low-Rank Asymmetric Projections。
Alex Beutel
论文名称:User Behavior Modeling with Large-Scale Graph Analysis
论文地址:http://alexbeutel.com/papers/CMU-CS-16-105.pdf
(斜体为非谷歌员工)
Ego-Splitting Framework: from Non-Overlapping to Overlapping Clusters
Alessandro Epasto, Silvio Lattanzi, Renato Paes Leme
HyperLogLog Hyperextended: Sketches for Concave Sublinear Frequency Statistics
Edith Cohen
Google Vizier: A Service for Black-Box Optimization
Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, D. Sculley
论文地址:http://dl.acm.org/citation.cfm?id=3098043
Quick Access: Building a Smart Experience for Google Drive
Sandeep Tata, Alexandrin Popescul, Marc Najork, Mike Colagrosso, Julian Gibbons, Alan Green, Alexandre Mah, Michael Smith, Divanshu Garg, Cayden Meyer, Reuben KanPapers
论文地址:http://www.kdd.org/kdd2017/papers/view/quick-access-building-a-smart-experience-for-google-drive
TFX: A TensorFlow Based Production Scale Machine Learning Platform
Denis Baylor, Eric Breck, Heng-Tze Cheng, Noah Fiedel, Chuan Yu Foo, Zakaria Haque, Salem Haykal, Mustafa Ispir, Vihan Jain, Levent Koc, Chiu Yuen Koo, Lukasz Lew, Clemens Mewald, Akshay Modi, Neoklis Polyzotis, Sukriti Ramesh, Sudip Roy, Steven Whang, Martin Wicke, Jarek Wilkiewicz, Xin Zhang, Martin Zinkevich
Construction of Directed 2K Graphs
Balint Tillman, Athina Markopoulou, Carter T. Butts, Minas Gjoka
论文地址:http://www.kdd.org/kdd2017/papers/view/construction-of-directed-2k-graphs
A Practical Algorithm for Solving the Incoherence Problem of Topic Models In Industrial Applications
Amr Ahmed, James Long, Dan Silva, Yuan Wang
Train and Distribute: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks
Heng-Tze Cheng, Lichan Hong, Mustafa Ispir, Clemens Mewald, Zakaria Haque, Illia Polosukhin, Georgios Roumpos, D Sculley, Jamie Smith, David Soergel, Yuan Tang, Philip Tucker, Martin Wicke, Cassandra Xia, Jianwei Xie
Learning to Count Mosquitoes for the Sterile Insect Technique
Yaniv Ovadia, Yoni Halpern, Dilip Krishnan, Josh Livni, Daniel Newburger, Ryan Poplin, Tiantian Zha, D. Sculley
论文地址:http://www.kdd.org/kdd2017/papers/view/learning-to-count-mosquitoes-for-the-sterile-insect-technique
13th International Workshop on Mining and Learning with Graphs
受邀讲者:Vahab Mirrokni - Distributed Graph Mining: Theory and Practice
contributed talks:
HARP: Hierarchical Representation Learning for Networks
Haochen Chen, Bryan Perozzi, Yifan Hu and Steven Skiena
Fairness, Accountability, and Transparency in Machine Learning
Contributed talks:
Fair Clustering Through Fairlets
Flavio Chierichetti, Ravi Kumar, Silvio Lattanzi, Sergei Vassilvitskii
Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
Alex Beutel, Jilin Chen, Zhe Zhao, Ed H. Chi
TensorFlow
Rajat Monga, Martin Wicke, Daniel ‘Wolff’ Dobson, Joshua Gordon
更多精彩内容敬请关注雷锋网AI科技评论。