Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Long Range Arena: A Benchmark for Efficient Transformers

Nov 08, 2020
Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler


  Access Paper or Ask Questions

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Oct 22, 2020
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

* Fine-tuning code and pre-trained models are available at https://github.com/google-research/vision_transformer 

  Access Paper or Ask Questions

Efficient Transformers: A Survey

Sep 16, 2020
Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler


  Access Paper or Ask Questions

IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression

Jun 22, 2020
Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans


  Access Paper or Ask Questions

Transferring Inductive Biases through Knowledge Distillation

Jun 02, 2020
Samira Abnar, Mostafa Dehghani, Willem Zuidema


  Access Paper or Ask Questions

MetNet: A Neural Weather Model for Precipitation Forecasting

Mar 30, 2020
Casper Kaae Sønderby, Lasse Espeholt, Jonathan Heek, Mostafa Dehghani, Avital Oliver, Tim Salimans, Shreya Agrawal, Jason Hickey, Nal Kalchbrenner


  Access Paper or Ask Questions

HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents

Oct 12, 2018
Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke

* IEEE Transactions on Knowledge and Data Engineering 

  Access Paper or Ask Questions

Universal Transformers

Jul 10, 2018
Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Łukasz Kaiser


  Access Paper or Ask Questions

Learning to Rank from Samples of Variable Quality

Jun 21, 2018
Mostafa Dehghani, Jaap Kamps

* Presented at The First International SIGIR2016 Workshop on Learning From Limited Or Noisy Data For Information Retrieval. arXiv admin note: substantial text overlap with arXiv:1711.02799 

  Access Paper or Ask Questions

Fidelity-Weighted Learning

May 23, 2018
Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

* Published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision

Dec 07, 2017
Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps


  Access Paper or Ask Questions

Learning to Learn from Weak Supervision by Full Supervision

Nov 30, 2017
Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps

* Accepted at NIPS Workshop on Meta-Learning (MetaLearn 2017), Long Beach, CA, USA 

  Access Paper or Ask Questions

Words are Malleable: Computing Semantic Shifts in Political and Media Discourse

Nov 15, 2017
Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps

* In Proceedings of the 26th ACM International on Conference on Information and Knowledge Management (CIKM2017) 

  Access Paper or Ask Questions

Learning to Attend, Copy, and Generate for Session-Based Query Suggestion

Nov 13, 2017
Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, Pascal Fleury

* Accepted to be published at The 26th ACM International Conference on Information and Knowledge Management (CIKM2017) 

  Access Paper or Ask Questions

Share your Model instead of your Data: Privacy Preserving Mimic Learning for Ranking

Jul 24, 2017
Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke

* SIGIR 2017 Workshop on Neural Information Retrieval (Neu-IR'17)}{}{August 7--11, 2017, Shinjuku, Tokyo, Japan 

  Access Paper or Ask Questions

Neural Networks for Information Retrieval

Jul 13, 2017
Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra

* Overview of full-day tutorial at SIGIR 2017 

  Access Paper or Ask Questions

Neural Ranking Models with Weak Supervision

May 29, 2017
Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft

* In proceedings of The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2017) 

  Access Paper or Ask Questions

On Horizontal and Vertical Separation in Hierarchical Text Classification

Sep 02, 2016
Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx

* Full paper (10 pages) accepted for publication in proceedings of ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR'16) 

  Access Paper or Ask Questions