Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
暂无分享,去创建一个
Aaron C. Courville | Kartik Ahuja | Aaron Courville | Dinghuai Zhang | Yisen Wang | Yilun Xu | Yisen Wang | Dinghuai Zhang | Kartik Ahuja | Yilun Xu
[1] Jonas Peters,et al. Causal inference by using invariant prediction: identification and confidence intervals , 2015, 1501.01332.
[2] Aleksander Madry,et al. Robustness May Be at Odds with Accuracy , 2018, ICLR.
[3] Vladimir Vapnik,et al. An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.
[4] Yoshua Bengio,et al. An Analysis of the Adaptation Speed of Causal Models , 2020, AISTATS.
[5] Bernhard Schölkopf,et al. Recurrent Independent Mechanisms , 2021, ICLR.
[6] Joseph D. Janizek,et al. AI for radiographic COVID-19 detection selects shortcuts over signal , 2020, Nature Machine Intelligence.
[7] Roger B. Grosse,et al. Picking Winning Tickets Before Training by Preserving Gradient Flow , 2020, ICLR.
[8] Aaron C. Courville,et al. What Do Compressed Deep Neural Networks Forget , 2019, 1911.05248.
[9] Pietro Perona,et al. Microsoft COCO: Common Objects in Context , 2014, ECCV.
[10] Bernhard Schölkopf,et al. Domain Generalization via Invariant Feature Representation , 2013, ICML.
[11] Masanori Koyama,et al. Out-of-Distribution Generalization with Maximal Invariant Predictor , 2020, ArXiv.
[12] Nathan Srebro,et al. The Implicit Bias of Gradient Descent on Separable Data , 2017, J. Mach. Learn. Res..
[13] M. Bethge,et al. Shortcut learning in deep neural networks , 2020, Nature Machine Intelligence.
[14] Suyog Gupta,et al. To prune, or not to prune: exploring the efficacy of pruning for model compression , 2017, ICLR.
[15] Nitish Srivastava,et al. Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..
[16] Yingwei Li,et al. Shape-Texture Debiased Neural Network Training , 2020, ICLR.
[17] Xin Wang,et al. Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization , 2019, ICML.
[18] Andreas Geiger,et al. Counterfactual Generative Networks , 2021, ICLR.
[19] Philip H. S. Torr,et al. SNIP: Single-shot Network Pruning based on Connection Sensitivity , 2018, ICLR.
[20] Max Welling,et al. Learning Sparse Neural Networks through L0 Regularization , 2017, ICLR.
[21] Christopher Joseph Pal,et al. A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms , 2019, ICLR.
[22] Timo Aila,et al. Pruning Convolutional Neural Networks for Resource Efficient Inference , 2016, ICLR.
[23] Song Han,et al. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.
[24] Percy Liang,et al. Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately , 2020, FAccT.
[25] Pradeep Ravikumar,et al. The Risks of Invariant Risk Minimization , 2020, ICLR.
[26] Simon Haykin,et al. GradientBased Learning Applied to Document Recognition , 2001 .
[27] Raquel Urtasun,et al. MLPrune: Multi-Layer Pruning for Automated Neural Network Compression , 2018 .
[28] Yann LeCun,et al. Optimal Brain Damage , 1989, NIPS.
[29] Svetlana Lazebnik,et al. PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
[30] David Lopez-Paz,et al. In Search of Lost Domain Generalization , 2020, ICLR.
[31] Pietro Perona,et al. Recognition in Terra Incognita , 2018, ECCV.
[32] Percy Liang,et al. Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization , 2019, ArXiv.
[33] Bernhard Schölkopf,et al. Invariant Models for Causal Transfer Learning , 2015, J. Mach. Learn. Res..
[34] Luigi Gresele,et al. Learning explanations that are hard to vary , 2020, ArXiv.
[35] Dan Klein,et al. Neural Module Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[36] Thomas L. Griffiths,et al. Automatically Composing Representation Transformations as a Means for Generalization , 2018, ICLR.
[37] Regina Barzilay,et al. Domain Extrapolation via Regret Minimization , 2020, ArXiv.
[38] Yadong Mu,et al. Informative Dropout for Robust Representation Learning: A Shape-bias Perspective , 2020, ICML.
[39] Gintare Karolina Dziugaite,et al. Pruning Neural Networks at Initialization: Why are We Missing the Mark? , 2020, ArXiv.
[40] Koby Crammer,et al. A theory of learning from different domains , 2010, Machine Learning.
[41] Koby Crammer,et al. Learning from Multiple Sources , 2006, NIPS.
[42] Richard Zemel,et al. Exchanging Lessons Between Algorithmic Fairness and Domain Generalization , 2020, ArXiv.
[43] Babak Hassibi,et al. Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.
[44] Nathan Srebro,et al. Does Invariant Risk Minimization Capture Invariance? , 2021, ArXiv.
[45] Dana H. Ballard,et al. Modular Learning in Neural Networks , 1987, AAAI.
[46] Matthias Bethge,et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness , 2018, ICLR.
[47] Mingjie Sun,et al. Rethinking the Value of Network Pruning , 2018, ICLR.
[48] Tengyu Ma,et al. In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness , 2020, ICLR.
[49] Bolei Zhou,et al. Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[50] Hod Lipson,et al. The evolutionary origins of modularity , 2012, Proceedings of the Royal Society B: Biological Sciences.
[51] Peter Stone,et al. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science , 2017, Nature Communications.
[52] Prateek Jain,et al. The Pitfalls of Simplicity Bias in Neural Networks , 2020, NeurIPS.
[53] Stuart Russell,et al. Neural Networks are Surprisingly Modular , 2020, ArXiv.
[54] Eric P. Xing,et al. Learning Robust Representations by Projecting Superficial Statistics Out , 2018, ICLR.
[55] Aaron C. Courville,et al. Systematic generalisation with group invariant predictions , 2021, ICLR.
[56] M E J Newman,et al. Modularity and community structure in networks. , 2006, Proceedings of the National Academy of Sciences of the United States of America.
[57] Aaron C. Courville,et al. Out-of-Distribution Generalization via Risk Extrapolation , 2020 .
[58] Zenon W. Pylyshyn,et al. Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.
[59] Amit Dhurandhar,et al. Empirical or Invariant Risk Minimization? A Sample Complexity Perspective , 2020, ArXiv.
[60] Bernhard Schölkopf,et al. On causal and anticausal learning , 2012, ICML.
[61] Behnam Neyshabur,et al. Understanding the Failure Modes of Out-of-Distribution Generalization , 2021, ICLR.
[62] G. Marcus. Rethinking Eliminative Connectionism , 1998, Cognitive Psychology.
[63] Seong Joon Oh,et al. Learning De-biased Representations with Biased Representations , 2019, ICML.
[64] Fei Chen,et al. Risk Variance Penalization: From Distributional Robustness to Causality , 2020, ArXiv.
[65] Samuel Ritter,et al. Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study , 2017, ICML.
[66] Emily Denton,et al. Characterising Bias in Compressed Models , 2020, ArXiv.
[67] Matthias Bethge,et al. Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet , 2019, ICLR.
[68] Donald A. Adjeroh,et al. Unified Deep Supervised Domain Adaptation and Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).
[69] Sjoerd van Steenkiste,et al. Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks , 2020, ICLR.
[70] Percy Liang,et al. An Investigation of Why Overparameterization Exacerbates Spurious Correlations , 2020, ICML.
[71] Aaron C. Courville,et al. Out-of-Distribution Generalization via Risk Extrapolation (REx) , 2020, ICML.
[72] Kunio Kashino,et al. Understanding Community Structure in Layered Neural Networks , 2018, Neurocomputing.
[73] Amit Dhurandhar,et al. Invariant Risk Minimization Games , 2020, ICML.
[74] Tommi S. Jaakkola,et al. Invariant Rationalization , 2020, ICML.
[75] Jason Yosinski,et al. Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask , 2019, NeurIPS.
[76] Ullrich Köthe,et al. Learning Robust Models Using The Principle of Independent Causal Mechanisms , 2020, ArXiv.
[77] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.
[78] Aaron C. Courville,et al. Gradient Starvation: A Learning Proclivity in Neural Networks , 2020, NeurIPS.
[79] Michael C. Mozer,et al. Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment , 1988, NIPS.
[80] Michael Carbin,et al. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.
[81] Jinwoo Shin,et al. Learning from Failure: Training Debiased Classifier from Biased Classifier , 2020, ArXiv.
[82] Xin Dong,et al. Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon , 2017, NIPS.
[83] Ben Poole,et al. Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.