(F20-CS 598) Learning to Learn: Schedule
Schedule (Tentative)
We will typically cover three papers in each class.
| Date |
Presenter |
Topic |
Papers |
Slides |
| Aug 26 |
Yuxiong Wang |
Introduction |
|
|
| Aug 28 |
Yuxiong Wang |
Overview |
Y.-X. Wang and M. Hebert. Learning to learn: Model regression networks for easy small sample learning. ECCV, 2016.
Y.-X. Wang, D. Ramanan, and M. Hebert,. Learning to model the tail. NeurIPS, 2017.
Y.-X. Wang, R. Girshick, M. Hebert, and B. Hariharan. Low-shot learning from imaginary data. CVPR, 2018.
L.-Y. Gui, Y.-X. Wang, D. Ramanan, and J. M. F. Moura. Few-shot human motion prediction via meta-learning. ECCV, 2018. |
|
| Part I: Different Types of Meta-Level Knowledge |
| Sep 2 |
Raj Kataria |
Metric Learning |
J. Snell, K. Swersky, and R. S. Zemel. Prototypical networks for few shot learning. NeurIPS, 2017.
O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra. Matching networks for one shot learning. NeurIPS, 2016.
K. Lee, S. Maji, A. Ravichandran, and S. Soatto. Meta-learning with differentiable convex optimization. CVPR, 2019. |
|
| Sep 4 |
|
Learning to Initialize |
C. Finn, P. Abbeel, and S. Levine. Model-agnostic meta-learning for fast adaptation of deep networks. ICML, 2017.
C. Finn, K. Xu, and S. Levine. Probabilistic model-agnostic meta-learning. NeurIPS, 2018.
A. A. Rusu, D. Rao, J. Sygnowski, O. Vinyals, R. Pascanu, S. Osindero, and R. Hadsell. Meta-learning with latent embedding optimization. ICLR, 2019. |
|
| Sep 9 |
|
Learning to Optimize & Hyperparameter Optimization |
M. Andrychowicz, M. Denil, S. G. Colmenarejo, M. W. Hoffman, D. Pfau, T. Schaul, and N. de Freitas. Learning to learn by gradient descent by gradient descent. NeurIPS, 2016.
S. Ravi and H. Larochelle. Optimization as a model for few-shot learning. ICLR, 2016.
D. Maclaurin, D. Duvenaud, and R. Adams. Gradient-based hyperparameter optimization through reversible learning. ICML 2015. |
|
| Sep 11 |
|
Learning to Predict Parameters |
D. Ha, A. Dai, and Q. V. Le. HyperNetworks. ICLR, 2017.
S. Gidaris and N. Komodakis. Dynamic few-shot visual learning without forgetting. CVPR, 2018.
I. Misra, A. Gupta, and M. Hebert. From red wine to red tomato: Composition with context. CVPR, 2017. |
|
| Sep 16 |
|
Modular Meta-Learning |
F. Alet, T. Lozano-Perez, and L. P. Kaelbling. Modular meta-learning. CoRL, 2018.
S.-A. Rebuffi, H. Bilen, and A. Vedaldi. Learning multiple visual domains with residual adapters. NeurIPS, 2017.
L. Liu, W. Hamilton, G. Long, J. Jiang, and H. Larochelle. A universal representation transformer layer for few-shot image classification. arXiv:2006.11702, 2020. |
|
| Sep 18 |
|
Architecture Search |
B. Zoph and L. Quoc. Neural architecture search with reinforcement learning. ICLR, 2017.
H. Liu, K. Simonyan, and Y. Yang. DARTS: Differentiable architecture search. ICLR, 2019.
A. Brock, T. Lim, J. Ritchie, and N. Weston. Smash: one-shot model architecture search through hypernetworks. ICLR, 2018. |
|
| Sep 23 |
|
Data Selection & Reweighting |
L. Jiang, Z. Zhou, T. Leung, L.-J. Li, and L. Fei-Fei. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. ICML, 2018.
M. Ren, W. Zeng, B. Yang, and R. Urtasun. Learning to reweight examples for robust deep learning. ICML, 2018.
J. Shu, Q. Xie, L. Yi, Q. Zhao, S. Zhou, Z. Xu, and D. Meng. Meta-weight-net: Learning an explicit mapping for sample weighting. NeurIPS, 2019. |
|
| Sep 25 |
|
Data Augmentation |
E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le. AutoAugment: learning augmentation policies from data. CVPR, 2019.
Y. Li, G. Hu, Y. Wang, T. Hospedales, N. M. Robertson, and Y. Yang. DADA: Differentiable automatic data augmentation. ECCV, 2020.
A. Antoniou, A. Storkey, and H. Edwards. Data augmentation generative adversarial networks. arXiv:1711.04340, 2017. |
|
| Sep 30 |
|
Data synthesis |
T. Wang, J.-Y. Zhu, A. Torralba, and A. Efros. Dataset distillation. arXiv:1811.10959, 2018.
Z. Chen, Y. Fu, Y.-X. Wang, L. Ma, W. Liu, and M. Hebert. Image deformation meta-networks for one-shot learning. CVPR, 2019.
N. Ruiz, S. Schulter, and M. Chandraker. Learning to simulate. ICLR, 2019. |
|
| Oct 2 |
|
Other Meta-Objectives |
D. Li, J. Zhang, Y. Yang, C. Liu, Y.-Z. Song, and T. Hospedales. Episodic training for domain generalization. ICCV, 2019.
J. Li, Y. Wong, Q. Zhao, and M. Kankanhalli. Learning to learn from noisy labeled data. CVPR, 2019.
D. Zügner and S. Günnemann. Adversarial attacks on graph neural networks via meta learning. ICLR, 2019. |
|
| Oct 7 |
|
Meta-Reinforcement Learning |
J. Wang, Z. Kurth-Nelson, D. Tirumala, H. Soyer, J. Leibo, R. Munos, C. Blundell, D. Kumaran, and M. Botvinick. Learning to reinforcement learn. CogSci, 2017.
Y. Duan, J. Schulman, X. Chen, P. Bartlett, I. Sutskever, and P. Abbeel. RL^ 2: Fast reinforcement learning via slow reinforcement learning. ICLR, 2017.
A. Gupta, R. Mendonca, Y. Liu, P. Abbeel, and S. Levine. Meta-reinforcement learning of structured exploration strategies. NeurIPS, 2018. |
|
| Part II: Different Settings |
| Oct 9 |
|
Semi-supervised Learning & Active Learning & Domain Shift |
M. Ren, E. Triantafillou, S. Ravi, J. Snell, K. Swersky, J. Tenenbaum, H. Larochelle, and R. Zemel. Meta-learning for semi-supervised few-shot classification. ICLR, 2018.
P. Bachman, A. Sordoni, and A. Trischler. Learning algorithms for active learning. ICML, 2017.
H.-Y. Tseng, H.-Y. Lee, J.-B. Huang, and M.-H. Yang. Cross-domain few-shot classification via learned feature-wise transformation. ICLR, 2020. |
|
| Oct 14 |
|
Unsupervised Learning |
Y.-X. Wang and M. Hebert. Learning from small sample sets by combining unsupervised meta-training with CNNs. NeurIPS, 2016.
K. Hsu, S. Levine, and C. Finn. Unsupervised learning via meta-learning. ICLR, 2019.
L. Metz, N. Maheswaranathan, B. Cheung, and J. Sohl-Dickstein. Meta-learning update rules for unsupervised representation learning. ICLR, 2019. |
|
| Oct 16 |
|
Benchmarks |
E. Triantafillou, T. Zhu, V. Dumoulin, P. Lamblin, U. Evci, K. Xu, R. Goroshin, C. Gelada, K. Swersky, P. Manzagol, and H. Larochelle. Meta-dataset: A dataset of datasets for learning to learn from few examples. ICLR, 2020.
T. Yu, D. Quillen, Z. He, R. Julian, K. Hausman, C. Finn, S. Levine. Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning. CoRL, 2019.
M. Wallingford, A. Kusupati, K. Alizadeh-Vahid, A. Walsman, A. Kembhavi, and A. Farhadi. In the wild: From ML models to pragmatic ML systems. arXiv:2007.02519, 2020. |
|
| Part III: Historical & Recent Perspectives & Positioning/Connections with Knowledge Transfer in General |
| Oct 21 |
|
Retrospection: Concept of Learning to Learn |
J. Schmidhuber. Evolutionary principles in self-referential learning. On learning how to learn: The meta-meta-... hook, 1987.
G. E. Hinton and D. C. Plaut. Using fast weights to deblur old memories. Conference Of The Cognitive Science Society, 1987.
S. Bengio, Y. Bengio, J. Cloutier, and J. Gecsei. On the optimization of a synaptic learning rule. Conf. Optimality in Artificial and Biological Neural Networks, 1992.
J. Schmidhuber. Learning to control fast-weight memories: An alternative to dynamic recurrent networks. Neural Computation, 1992.
S. Thrun. Is learning the n-th thing any easier than learning the first? NeurIPS, 1996.
S. Thrun and L. Pratt. Learning to learn: Introduction and overview. Learning To Learn, 1998.
S. Hochreiter, A. Younger, and P. Conwell. Learning to learn using gradient descent. International Conference on Artificial Neural Networks, 2001.
A. S. Younger, S. Hochreiter, and P. R. Conwell. Meta-learning with backpropagation. IJCNN, 2001.
R. Vilalta and Y. Drissi. A perspective view and survey of meta-learning. Artificial intelligence review, 2002.
N. Schweighofer and K. Doya. Meta-learning in reinforcement learning. Neural Networks, 2003. |
|
| Oct 23 |
|
Transfer Learning |
Y.-X. Wang, D. Ramanan, and M. Hebert. Growing a brain: Fine-tuning by increasing model capacity. CVPR, 2017.
A. Mallya, D. Davis, and S. Lazebnik. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. ECCV, 2018.
B. Zoph, G. Ghiasi, T.-Y. Lin, Y. Cui, H. Liu, E. Cubuk, and Q. Le. Rethinking pre-training and self-training. arXiv:2006.06882, 2020. |
|
| Oct 28 |
|
Multi-task Learning |
A. Achille, M. Lam, R. Tewari, A. Ravichandran, S. Maji, C. Fowlkes, S. Soatto, and P. Perona. Task2vec: Task embedding for meta-learning. ICCV, 2019.
A. Zamir, A. Sax, W. Shen, L. Guibas, J. Malik, and S. Savarese. Taskonomy: Disentangling task transfer learning. CVPR, 2018.
Z. Li and D. Hoiem. Learning without forgetting. ECCV, 2016. |
|
| Oct 30 |
|
Self-supervised Learning |
T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. A simple framework for contrastive learning of visual representations. ICML, 2020.
K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick. Momentum contrast for unsupervised visual representation learning. CVPR, 2020.
J.-C. Su, S. Maji, and B. Hariharan. When does self-supervision improve few-shot learning? ECCV, 2020. |
|
| Nov 4 |
|
Online Learning & Continual Learning & Lifelong Learning |
C. Finn, A. Rajeswaran, S. Kakade, and S. Levine. Online meta-learning. ICML, 2019.
K. Javed and M. White. Meta-learning representations for continual learning. NeurIPS, 2019.
M. Al-Shedivat, T. Bansal, Y. Burda, I. Sutskever, I. Mordatch, and P. Abbeel. Continuous adaptation via meta-learning in nonstationary and competitive environments. ICLR, 2018. |
|
| Nov 6 |
|
Teacher-Student Models |
G. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. NeurIPS Workshops, 2014.
Y. Fan, F. Tian, T. Qin, X.-Y. Li, and T.-Y. Liu. Learning to teach. ICLR, 2018.
E. Parisotto, J. Ba, and R. Salakhutdinov. Actor-mimic: Deep multitask and transfer reinforcement learning. ICLR, 2016. |
|
| Nov 11 |
|
Controversy on Meta-Learning: Meta-Learning vs. Standard Non-Meta-Learning |
W.-Y. Chen, Y.-C. Liu, Z. Kira, Y.-C. Wang, and J.-B. Huang. A closer look at few-shot classification. ICLR, 2019.
A. Raghu, M. Raghu, S. Bengio, and O. Vinyals. Rapid learning or feature reuse? towards understanding the effectiveness of MAML. ICLR, 2020.
B. Kang, S. Xie, M. Rohrbach, Z. Yan, A. Gordo, J. Feng, and Y. Kalantidis. Decoupling representation and classifier for long-tailed recognition. ICLR, 2020. |
|
| Nov 13 |
|
Recent Perspectives |
W.-L. Chao, H.-J. Ye, D.-C. Zhan, M. Campbell, and K. Weinberger. Revisiting meta-learning as supervised learning. arXiv:2002.00573, 2020.
B. Lake, R. Salakhutdinov, and J. Tenenbaum. Human-level concept learning through probabilistic program induction. Science, 2015.
T. Cao, M. Law, and S. Fidler. A theoretical analysis of the number of shots in few-shot learning. ICLR, 2020.
L. Franceschi, P. Frasconi, S. Salzo, R. Grazzi, and M. Pontil. Bilevel programming for hyperparameter optimization and meta-learning. ICML, 2018.
T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey. Meta-learning in neural networks: A survey. arXiv:2004.05439, 2020.
Recent meta-learning workshops. e.g., ICML 2019, NeurIPS 2019. |
|
| Part IV: Applications |
| Nov 18 |
|
Computer Vision |
R. Hu, P. Dollár, K. He, T. Darrell, and R. Girshick. Learning to segment every thing. CVPR, 2018.
M. Li, Y.-X. Wang, and D. Ramanan. Towards streaming perception. ECCV, 2020.
M. Wortsman, K. Ehsani, M. Rastegari, A. Farhadi, and R. Mottaghi. Learning to learn how to learn: Self-adaptive visual navigation using meta-learning. CVPR, 2019. |
|
| Nov 20 |
|
Image and Video Generation |
S. Reed, Y. Chen, T. Paine, A. van den Oord, S. Eslami, D. Rezende, O. Vinyals, and N. de Freitas. Few-shot autoregressive density estimation: Towards learning to learn distributions. ICLR, 2018.
E. Zakharov, A. Shysheya, E. Burkov, and V. S. Lempitsky. Few-shot adversarial learning of realistic neural talking head models. ICCV, 2019.
T.-C. Wang, M.-Y. Liu, A. Tao, G. Liu, J. Kautz, and B. Catanzaro. Few-shot video-to-video synthesis. NeurIPS, 2019. |
|
| Nov 25 |
No Class |
Fall Break |
|
|
| Nov 27 |
No Class |
Fall Break |
|
|
| Dec 2 |
|
Language |
A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever. Language models are unsupervised multitask learners. OpenAI Blog, 2019.
J. Gu, Y. Wang, Y. Chen, K. Cho, and V. Li. Meta-learning for low-resource neural machine translation. EMNLP, 2018.
J. Devlin, R. Bunel, R. Singh, M. Hausknecht, and P. Kohli. Neural program meta-induction. NeurIPS, 2017. |
|
| Dec 4 |
|
Robot Imitation Learning |
Y. Duan, M. Andrychowicz, B. Stadie, O. Ho, J. Schneider, I. Sutskever, P. Abbeel, and W. Zaremba. One-shot imitation learning. NeurIPS, 2017.
T. Yu, C. Finn, A. Xie, S. Dasari, T. Zhang, P. Abbeel, and S. Levine. One-shot imitation from observing humans via domain-adaptive meta-learning. RSS, 2018.
D. Pathak, P. Mahmoudieh, G. Luo, P. Agrawal, D. Chen, Y. Shentu, E. Shelhamer, J. Malik, A. Efros, and T. Darrell. Zero-shot visual imitation. ICLR, 2018. |
|
| Dec 9 |
|
Final Project Presentations |
|
|
|