Filter by Keyword:

30 Results

Poster
Mon 1:00 Semantic Re-tuning with Contrastive Tension
Fredrik Carlsson, Amaru C Gyllensten, Evangelia Gogoulou, Erik Y Hellqvist, Magnus Sahlgren
Poster
Mon 9:00 Revisiting Few-sample BERT Fine-tuning
Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Weinberger, Yoav Artzi
Poster
Mon 9:00 On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow
Poster
Mon 9:00 Predicting Inductive Biases of Pre-Trained Models
Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick
Poster
Mon 9:00 Primal Wasserstein Imitation Learning
Robert Dadashi, Hussenot Hussenot-Desenonges, Matthieu Geist, Olivier Pietquin
Poster
Mon 9:00 Rethinking Embedding Coupling in Pre-trained Language Models
Hyung Won Chung, Thibault Fevry, Henry Tsai, Melvin Johnson, Sebastian Ruder
Oral
Mon 11:30 Growing Efficient Deep Networks by Structured Continuous Sparsification
Xin Yuan, Pedro Savarese, Michael Maire
Poster
Mon 17:00 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Lily Weng, Chuang Gan, Meng Wang
Poster
Mon 17:00 Deberta: Decoding-Enhanced Bert With Disentangled Attention
Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen
Poster
Tue 9:00 FairBatch: Batch Selection for Model Fairness
Yuji Roh, Kangwook Lee, Steven Whang, Changho Suh
Poster
Tue 9:00 Distance-Based Regularisation of Deep Networks for Fine-Tuning
Henry Gouk, Timothy Hospedales, massimiliano pontil
Poster
Tue 9:00 Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning
Beliz Gunel, Jingfei Du, Alexis Conneau, Veselin Stoyanov
Poster
Wed 1:00 Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Poster
Wed 1:00 Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, Yi Wu
Spotlight
Wed 4:40 Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Oral
Wed 5:00 Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
Qiang Zhang, Tete Xiao, Alyosha Efros, Lerrel Pinto, Xiaolong Wang
Poster
Wed 9:00 Pre-training Text-to-Text Transformers for Concept-centric Common Sense
Wangchunshu Zhou, Dong-Ho Lee, Ravi Kiran Selvam, Seyeon Lee, Xiang Ren
Poster
Wed 9:00 Growing Efficient Deep Networks by Structured Continuous Sparsification
Xin Yuan, Pedro Savarese, Michael Maire
Poster
Wed 9:00 HyperGrid Transformers: Towards A Single Model for Multiple Tasks
Yi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, DA-CHENG Juan
Poster
Wed 17:00 Better Fine-Tuning by Reducing Representational Collapse
Armen Aghajanyan, Akshat Shrivastava, Anchit Gupta, Naman Goyal, Luke Zettlemoyer, Sonal Gupta
Poster
Wed 17:00 AdaSpeech: Adaptive Text to Speech for Custom Voice
Mingjian Chen, Xu Tan, Bohan Li, Eric Liu, Tao Qin, sheng zhao, Tie-Yan Liu
Poster
Wed 17:00 Economic Hyperparameter Optimization With Blended Search Strategy
Chi Wang, Qingyun Wu, Silu Huang, Amin Saied
Poster
Thu 1:00 Network Pruning That Matters: A Case Study on Retraining Variants
Duong Le, Binh-Son Hua
Poster
Thu 9:00 Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Jonathan Pilault, Amine EL hattami, Chris J Pal
Poster
Thu 9:00 Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification
Francisco Utrera, Evan Kravitz, N. Benjamin Erichson, Rajiv Khanna, Michael W Mahoney
Poster
Thu 9:00 Variational Information Bottleneck for Effective Low-Resource Fine-Tuning
Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson
Poster
Thu 9:00 Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
Qiang Zhang, Tete Xiao, Alyosha Efros, Lerrel Pinto, Xiaolong Wang
Workshop
Fri 7:00 2nd Workshop on Practical ML for Developing Countries: Learning Under Limited/low Resource Scenarios
Esube Bekele, Waheeda Saib, Timnit Gebru, Meareg Hailemariam, Vukosi Marivate, Judy Gichoya
Workshop
Fri 8:57 Data-driven Weight Initialization with Sylvester Solvers
Buna Das
Workshop
Direct Federated Neural Architecture Search
Anubhav Garg, Amit Saha, Debojyoti Dutta