Program

Session 1

Chair: Krzysztof Dembczynski

9:15 - 10:00 AM

Invited Talk: Manik Varma

Extreme Classification: Tagging on Wikipedia, Recommendation on Amazon & Advertising on Bing [PDF]

10:00 - 10:20 AM

Regular Paper Talk:

Cold Start Thread Recommendation as Extreme Multi-label Classification [PDF]

Kishaloy Halder, Lahari Poddar and Min-Yen Kan

Session 2

Chair: Marius Kloft

11:00 - 11:40 AM

Invited Talk: Anshumali Shrivastava

Training 100,000 classes on a Single Titan X in 7 hours or 15 minutes with 25 Titan Xs [PDF]

11:40 - 12:00 PM

Regular Paper Talk:

Learning Large Scale Ordinal Ranking Model via Divide-and-Conquer Technique

Lu Tang, Sougata Chaudhuri, Abraham Bagherjeiran and Ling Zhou

12:00 - 12:20

Extended Abstract Talk:

Deep F-measure Maximization in Multi-label Classification: A Comparative Study [PDF]

Stijn Decubber, Thomas Mortier, and Willem Waegeman

Session 3

Chair: Aasish Pappu

1:40 - 2:20 PM

Invited Talk: Marius Kloft

Distributed Training of All-in-one Multi-class SVMs

2:20 - 2:40 PM

Extended Abstract Talk:

Parabel: Partitioned Label Trees for Extreme Classification with Application to Dynamic Search Advertising [PDF]

Yashoteja Prabhu, Anil Kag, Shrutendra Harsola, Rahul Agrawal and Manik Varma

2:40 - 3:00 PM

Extended Abstract Talk:

Efficient exact batch prediction for label trees [PDF]

Kalina Jasinska

Session 4

Chair: Akshay Soni

3:40 - 4:20 PM

Invited Talk: Moustapha Cisse

Deep Extreme Classification: From head to tail