KDD 2017 已于近日落下帷幕，作為數(shù)據(jù)科學(xué)、信息檢索、數(shù)據(jù)挖掘和機(jī)器學(xué)習(xí)的頂級(jí)會(huì)議，KDD 為學(xué)術(shù)界和工業(yè)界提供了一個(gè)寶貴的交流機(jī)會(huì)。

一直以來，谷歌都是 KDD 的積極參與者，自然，今年的 KDD 也不例外，一起和雷鋒網(wǎng) AI 科技評(píng)論來看看谷歌是如何深度參與 KDD 的吧。

以下是谷歌深度參與或介入的 KDD 活動(dòng)議程全名單，雷鋒網(wǎng)AI科技評(píng)論編譯如下：

組織委員會(huì)

Panel 主席: Andrew Tomkins 

研究程序委員會(huì)主席: Ravi Kumar 

應(yīng)用數(shù)據(jù)科學(xué)程序委員會(huì)主席: Roberto J. Bayardo 

研究程序委員會(huì): Sergei Vassilvitskii, Alex Beutel, Abhimanyu Das, Nan Du, Alessandro Epasto, Alex Fabrikant, Silvio Lattanzi, Kristen Lefevre, Bryan Perozzi, Karthik Raman, Steffen Rendle, Xiao Yu

應(yīng)用數(shù)據(jù)科學(xué)程序委員會(huì): 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

博士論文獎(jiǎng)

Bryan Perozzi  

論文名稱：Local Modeling of Attributed Graphs: Algorithms and Applications

論文地址：http://perozzi.net/publications/16_thesis.pdf

SIGKDD 2017 的博士論文獎(jiǎng)被谷歌的 Bryan Perozzi 摘得，這一獎(jiǎng)項(xiàng)被授予在數(shù)據(jù)挖掘和知識(shí)發(fā)現(xiàn)領(lǐng)域有所建樹的杰出博士生。

這一獎(jiǎng)項(xiàng)是為了肯定他在石溪大學(xué)跟隨 Steven Skiena 教授所做的圖表機(jī)器學(xué)習(xí)研究課題《Local Modeling of Attributed Graphs: Algorithms and Applications》，其中的一部分內(nèi)容是 Perozzi 在 Google 實(shí)習(xí)期間完成的。

這一研究課題使用局限圖原語（例如 ego－network 和截取的隨機(jī)散列）有效地利用每個(gè)頂點(diǎn)周圍的信息進(jìn)行分類、聚類和異常檢測(cè)。值得一提的是，這項(xiàng)工作在 DeepWalk 中采用了神經(jīng)網(wǎng)絡(luò)圖形嵌入的隨機(jī)游走范式。

《DeepWalk: Online Learning of Social Representations》實(shí)際上是 Bryan Perozzi 最初在 KDD』14 投遞的一篇論文，論文使用從截?cái)嗟碾S機(jī)游走獲得的一系列本地信息，以學(xué)習(xí)圖中節(jié)點(diǎn)的潛在表征（如社交網(wǎng)絡(luò)用戶）的方法。其核心思想是將隨機(jī)游走的每一段都視為「圖形語言中」（ 「in the language of the graph」 ）的句子，然后可以使用這些片段作為神經(jīng)網(wǎng)絡(luò)模型的輸入來學(xué)習(xí)圖形節(jié)點(diǎn)的表征。這項(xiàng)研究將繼續(xù)在谷歌進(jìn)行，比如最近的 Learning Edge Representations via Low-Rank Asymmetric Projections。

博士論文獎(jiǎng)候選

Alex Beutel

論文名稱：User Behavior Modeling with Large-Scale Graph Analysis

論文地址：http://alexbeutel.com/papers/CMU-CS-16-105.pdf

錄用論文

（斜體為非谷歌員工）

• Ego-Splitting Framework: from Non-Overlapping to Overlapping Clusters

Alessandro Epasto, Silvio Lattanzi, Renato Paes Leme

論文地址：http://www.kdd.org/kdd2017/papers/view/ego-splitting-framework-from-non-overlapping-to-overlapping-clusters

• HyperLogLog Hyperextended: Sketches for Concave Sublinear Frequency Statistics

Edith Cohen

論文地址：http://www.kdd.org/kdd2017/papers/view/hyperloglog-hyper-extended-sketches-for-concave-sublinear-frequency-statist

• Google Vizier: A Service for Black-Box Optimization

Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, D. Sculley

論文地址：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

論文地址：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

論文地址：http://www.kdd.org/kdd2017/papers/view/tfx-a-tensorflow-based-production-scale-machine-learning-platform

• Construction of Directed 2K Graphs
  

Balint Tillman, Athina Markopoulou, Carter T. Butts, Minas Gjoka

論文地址：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

論文地址：http://www.kdd.org/kdd2017/papers/view/a-practical-algorithm-for-solving-the-incoherence-problem-of-topic-models-i

• 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

論文地址：http://www.kdd.org/kdd2017/papers/view/train-and-distribute-managing-simplicity-vs.-flexibility-in-high-level-mach

• 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

論文地址：http://www.kdd.org/kdd2017/papers/view/learning-to-count-mosquitoes-for-the-sterile-insect-technique

Workshops

• 13th International Workshop on Mining and Learning with Graphs

受邀講者：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

Tutorial

• TensorFlow

Rajat Monga, Martin Wicke, Daniel ‘Wolff’ Dobson, Joshua Gordon

更多精彩內(nèi)容敬請(qǐng)關(guān)注雷鋒網(wǎng)AI科技評(píng)論。

雷峰網(wǎng)版權(quán)文章，未經(jīng)授權(quán)禁止轉(zhuǎn)載。詳情見轉(zhuǎn)載須知。