2021 2020 2019 2018 2017 2016
2015 2014 2013 2012 2010
2021:
- Mostafa Dehghani* , A. Arnab* , L. Beyer* , A. Vaswani, Y. Tay*, The Efficiency Misnomer, arXiv preprint arXiv:2110.12894.
- Mostafa Dehghani, A. Gritsenko, A. Arnab, M. Minderer, Y. Tay, Scenic: A JAX library for computer vision research and beyond, arXiv preprint arXiv:2110.11403.
- S Abnar, Mostafa Dehghani, B Neyshabur, H Sedghi, Exploring the limits of large scale pre-training, arXiv preprint arXiv:2110.02095.
- C. Mao, L. Jiang, Mostafa Dehghani, C. Vondrick, R. Sukthankar, I. Essa, "Discrete Representations Strengthen Vision Transformer Robustness", arXiv preprint arXiv:2111.10493.
- Y. Tay* , Mostafa Dehghani* , J. Rao, W. Fedus, S. Abnar, H. W. Chung, S. Narang, D. Yogatama† , A. Vaswani, D. Metzler, Scale efficiently: Insights from pre-training and fine-tuning transformers, arXiv preprint arXiv:2109.10686.
- Mostafa Dehghani*, Y. Tay*, A. A. Gritsenko, Z. Zhao, N. Houlsby, F. Diaz, D. Metzler, O. Vinyals, "The Benchmark Lottery", arXiv preprint arXiv:2107.07002.
- S. Abnar, R. van den Berg, G. Ghiasi, Mostafa Dehghani, N. Kalchbrenner, H. Sedghi, "Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent", arXiv preprint arXiv:2106.06080.
- M. S. Ryoo, AJ. Piergiovanni, A. Arnab, Mostafa Dehghani, A. Angelova, "TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?", (published in NeurIPS 2021).
- Y. Tay, Mostafa Dehghani, J. Gupta, V. Aribandi, D. Bahri, Z. Qin, D. Metzler, "Are Pre-trained Convolutions Better than Pre-trained Transformers?", arXiv preprint arXiv:2105.03322, (published in ACL'21.).
- RK Mahabadi, S Ruder, Mostafa Dehghani, J Henderson, "Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks", (published in ACL'21).
- A. Arnab*, Mostafa Dehghani*, G. Heigold, C. Sun, M. Lučić, C. Schmid, "ViViT: A Video Vision Transformer", arXiv preprint arXiv:2103.15691, (2021).
- Y. Tay*, Mostafa Dehghani*, V. Aribandi, J. Gupta, P. Pham, Z. Qin, D. Bahri, D.C. Juan, D. Metzler, "OmniNet: Omnidirectional Representations from Transformers", arXiv preprint arXiv:2103.01075, (published in ICML'21 as Oral.).
2020:
- Y. Tay*, Mostafa Dehghani*, S. Abnar, Y. Shen, D. Bahri, P. Pham, J. Rao, L. Yang, S. Ruder, D. Metzler, "Long Range Arena: A Benchmark for Efficient Transformers", arXiv preprint arXiv:2011.04006, (published in ICLR'21).
- A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, Mostafa Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale" ,arXiv preprint arXiv:2010.11929, (published in ICLR'21).
- Y. Tay, Mostafa Dehghani, D. Bahri, D. Metzler. "Efficient Transformers: A Survey", arXiv preprint arXiv:2009.06732, (2020).
- R. van den Berg, A. A. Gritsenko, Mostafa Dehghani, C. Kaae Sønderby, T. Salimans. "IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression", arXiv preprint arXiv:2006.12459 (2020).
- S. Abnar, Mostafa Dehghani, W. Zuidema. "Transferring Inductive Biases through Knowledge Distillation", arXiv preprint arXiv:2006.00555, (2020).
- C. K. Sønderby, L. Espeholt, J. Heek, Mostafa Dehghani, A. Oliver, T. Salimans, S. Agrawal, J. Hickey, and N. Kalchbrenner. "MetNet: A Neural Weather Model for Precipitation Forecasting", arXiv preprint arXiv:2003.12140, (2020).
- Mostafa Dehghani. Learning with Imperfect Supervision for Language Understanding, Ph.D. thesis, University of Amsterdam, (2020).
- H. Azarbonyad, Mostafa Dehghani, M. Marx, and J. Kamps, "Learning to rank for multi-label text classification: Combining different sources of information", Journal of Natural Language Engineering, (2020).
2019:
- Mostafa Dehghani, S. Gouws, O. Vinyals, J. Uszkoreit, and L. Kaiser. "Universal Transformers". In Proceedings of International Conference on Learning Representations, (ICLR'19).
- Mostafa Dehghani, A. Mehrjou, S. Gouws, J Kamps, B Schölkopf. "Learning from Samples of Variable Quality", ICLR Workshop on Learning from Limited Labeled Data (ICLR-LLD'19).
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, M. de Rijke. "Learning to Transform, Combine, and Reason in Open-Domain Question Answering'', In Proceedings of the Twelfth International Conference on Web Search and Data Mining (WSDM2019).
2018:
- H. Zamani, Mostafa Dehghani, W. B. Croft, E. Learned-Miller, and J. Kamps. "From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing", In Proceedings of the 27th ACM International on Conference on Information and Knowledge Management, 2018 (CIKM ’18).
- H. Azarbonyad, Mostafa Dehghani, T. Kenter, M. Marx, J. Kamps, and M. De Rijke, "HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents" in IEEE Transactions on Knowledge and Data Engineering (TKDE).
- H. Zamani, Mostafa Dehghani, F. Diaz, H. Li, and N. Craswell, "SIGIR Workshop on Learning from Limited or Noisy Data for Information Retrieval (LND4IR)". In Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018 (SIGIR ’18).
- Mostafa Dehghani, A. Mehrjou, S. Gouws, J Kamps, B Schölkopf. "Fidelity-Weighted Learning", In Proceedings of International Conference on Learning Representations, (ICLR'18).
- Mostafa Dehghani, and J. Kamps. "Learning to Rank from Samples of Variable Quality", SIGIR Workshop on Learning from Limited or Noisy Data for Information Retrieval (LND4IR'18).
- T. Kenter, A. Borisov, C. Van Gysel, Mostafa Dehghani, M. de Rijke, and B. Mitra. "Neural Networks for Information Retrieval'', Tutorial at International ACM International Conference on Web Search and Data Mining (WSDM'18).
- T. Kenter, A. Borisov, C. Van Gysel, Mostafa Dehghani, M. de Rijke, and B. Mitra. "Neural Networks for Information Retrieval'', Tutorial at European Conference on Information Retrieval (ECIR'18).
2017:
- Mostafa Dehghani, A. Severyn, S. Rothe, and J. Kamps. "Learning to Learn from Weak Supervision by Full Supervision", the NIPS2017 workshop on Meta-Learning (MetaLearn 2017).
- Mostafa Dehghani."Toward Document Understanding for Information Retrieval", article published on SIGIR Forum December 2017, Volume 51 Number 3, 2017.
- Mostafa Dehghani, A. Severyn, S. Rothe, and J. Kamps. "Avoiding Your Teacher’s Mistake: Training Neural Networks with Controlled Weak Supervision", arXiv preprint arXiv:1711.00313 (2017).
- Mostafa Dehghani, S. Rothe, E. Alfonseca and P. Fleury. "Learning to Attend, Copy, and Generate for Session-Based Query Suggestion'', In Proceedings of International Conference on Information and Knowledge Management (CIKM'17).
- H.Azarbonyad, Mostafa Dehghani, J. Kamps, and M. Marx. "Words are Malleable: Computing Semantic Shifts in Political and Media Discourse", In Proceedings of International Conference on Information and Knowledge Management (CIKM'17).
- N. Torkzadeh Mahani, Mostafa Dehghani, M. S. Mirian, A. Shakery, and K. Taheri, "Expert Finding by the Dempster-Shafer Theory for Evidence Combination", Journal of Expert Systems.
- Mostafa Dehghani, G. Jagfeld, A. Olieman, H. Azarbonyad J. Kamps, and M. Marx. "On Search Powered Navigation'', In Proceedings of the ACM International Conference on the Theory of Information Retrieval (ICTIR'17). [Poster]
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, M. de Rijke. "Share your Model instead of your Data: Privacy-Preserving Mimic Learning for Ranking'', In Neu-IR: SIGIR Workshop on Neural Information Retrieval [Poster].
- Mostafa Dehghani, H. Zamani, Al. Severyn, J. Kamps, and W. B. Croft. "Neural Ranking Models with Weak Supervision", In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'17), 2017, pp 65-74. [Slides]
- T Kenter, A Borisov, C Van Gysel, Mostafa Dehghani, M. de Rijke, and B Mitra. "Neural Networks for Information Retrieval'', Tutorial at the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'17). [website]
- Mostafa Dehghani, G. Jagfeld, H. Azarbonyad, A. Olieman, J. Kamps and M. Marx. "Telling how to narrow it down: Effect of Browsing Path Recommendation on Exploratory Search", In Proceedings of ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR'17), 2017, pp. 369-372. [Poster]
- H. Azarbonyad, Mostafa Dehghani, T. Kenter, M. Marx, J. Kamps and M. de Rijke. "Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity", In Proceedings of the European Conference on Information Retrieval (ECIR'17), 2017, pp 68-81. [Poster]
2016:
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, and M. Marx, "Significant Words Language Models for Contextual Suggestion", In Proceedings of Text REtrieval Conference (TREC), 2016. [Slides]
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, D. Hiemstra, and M. Marx. "Inoculating Relevance Feedback Against Poison Pills", In proceedings of Dutch-Belgian Information Retrieval Workshop (DIR'16), 2016. [Slides]
-
-
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, and M. Marx, "On Horizontal and Vertical Separation in Hierarchical Text Classification", In Proceedings of ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR'16), 2016, pp. 185-194 . [Slides] (Best Paper Award)
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, and M. Marx, "Two-Way Parsimonious Classification Models for Evolving Hierarchies", In Proceedings of Conference and Labs of the Evaluation Forum (CLEF'16), 2016, pp. 69-82. [Slides] (Best Paper Honorable Mention)
- L. Quiroz, L. Mennes, Mostafa Dehghani, E.Kanoulas, "Distributional Semantics for Medical Information Extraction", In Notebook for CLEFeHealth at Conference and Labs of the Evaluation Forum (CLEF'16), 2016. [Poster]
- Mostafa Dehghani, "Significant Words Representations of Entities", In proceedings the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-Doctoral Consortium'16), 2016, pp. 1183-1183. [Slides] (SIGIR Doctoral Consortium Award)
- R. Rahimi, A. Shakery, J. Dadashkarimi, M. Ariannezhad, Mostafa Dehghani, and H. N. Esfahani. "Building a Multi-Domain Comparable Corpus Using a Learning to Rank Method". Journal of Natural Language Engineering, Cambridge University Press, Volume 22, Special Issue 04, 2016, pp. 627-653.
- Mostafa Dehghani, H. Azarbonyad, J. Kamps, and M. Marx "Generalized Group Profiling for Content Customization", In Proceedings of ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR'16), 2016, pp. 245-248. [Poster]
- Mostafa Dehghani, A. Shakery, M. S. Mirian. "ALECSA: Attentive Learning for Email Categorization using Structural Aspects". Knowledge-Based Systems Journal, Volume 98, 2016, pp. 44-54.
2015:
- S. H. Hashemi, Mostafa Dehghani, J. Kamps, "Parsimonious User and Group Profiling in Venue Recommendation", In Proceedings of Text REtrieval Conference (TREC), 2015.
- S. H. Hashemi, Mostafa Dehghani, J. Kamps, "University of Amsterdam at TREC 2015: Contextual Suggestion Track", In The Twenty-Fourth Text REtrieval Conference Notebook (TREC). National Institute for Standards and Technology, 2015.
- Mostafa Dehghani, H. Azarbonyad, M. Marx, and J. Kamps. "Learning to Combine Sources of Evidence for Indexing Political Texts", In proceedings of Dutch-Belgian Information Retrieval (DIR'15), 2015, pp. 24-24.
- H. Azarbonyad, Mostafa Dehghani, M. Marx, and J. Kamps. "Time-Aware Authorship Attribution of Short Texts", In Dutch-Belgian Information Retrieval (DIR'15), 2015, pp. 9-9.
- S. A. Tabrizi, J. Dadashkarimi, Mostafa Dehghani, H. Nasr Esfahani, A. Shakery, "Revisiting Optimal Rank Aggregation: A Dynamic Programming Approach", In Proceedings of ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR'15), 2015, pp. 353-356. [Poster]
- S. Abnar, Mostafa Dehghani, A. Shakery, "Meta Text Aligner: Text Alignment Based on Predicted Plagiarism Relation", In Proceedings of Conference and Labs of the Evaluation Forum (CLEF'15), 2015, pp. 193-199. [Poster]
- H. Azarbonyad, F. Saan, Mostafa Dehghani, M. Marx, and J. Kamps, "Are Topically Diverse Documents Also Interesting?", In Proceedings of Conference and Labs of the Evaluation Forum (CLEF'15), 2015, pp. 215-221. [Poster]
- H. Azarbonyad, Mostafa Dehghani, M. Marx, and J. Kamps, "Time-Aware Authorship Attribution for Short Text Streams", In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15), 2015, pp. 727-730. [Poster]
- Mostafa Dehghani, H. Azarbonyad, M. Marx, and J. Kamps, "Sources of evidence for automatic indexing of political texts", in Proceedings of Advances in Information Retrieval: 37th European Conference on Information Retrieval (ECIR'15), 2015, pp. 568-573. [Poster] (Best Poster Award)
2014:
- A. Olieman, H. Azarbonyad, Mostafa Dehghani, J. Kamps, and M. Marx, "Entity linking by focusing DBpedia candidate entities", In Proceedings of the first international workshop on Entity recognition & disambiguation (ERD'14), 2014, pp. 13-24.
- S. Abnar, Mostafa Dehghani, H. Zamani, and A. Shakery, "Expanded N-Grams for Semantic Text Alignment", Notebook for PAN at Conference and Labs of the Evaluation Forum (PAN'14), 2014, pp. 928-938.
- H. Zamani, H. N. Esfahani, P. Babaie, S. Abnar, Mostafa Dehghani, A. Shakery, "Authorship Identification Using Dynamic Selection of Features from Probabilistic Feature Set", In Proceedings of Conference and Labs of the Evaluation Forum (CLEF'14), 2014, pp. 128-140.
2013:
- Mostafa Dehghani, A. Shakery, M. Asadpour, and A. Koushkestani, "A Learning Approach for Email Conversation Thread Reconstruction", Journal of Information Science (JIS), Volume 39 Issue 6, 2013, pp. 846-863. [ACM-DL Link]
- A. Balali, H. Faili, M. Asadpour, and Mostafa Dehghani, "A Supervised Approach for Reconstructing Thread Structure in Comments on Blogs and Online News Agencies", Computación y Sistemas Journal, Volume 17 Number 2, 2013, pp. 207-217.
2012:
2010: