Timezone: »
Recently a wide variety of NAS methods have been proposed and achieved considerable success in automatically identifying highly-performing architectures of neural networks for the sake of reducing the reliance on human experts. Existing NAS methods ignore the fact that different input data elements (e.g., image pixels) have different importance (or saliency) in determining the prediction outcome. They treat all data elements as being equally important and therefore lead to suboptimal performance. To address this problem, we propose an end-to-end framework which dynamically detects saliency of input data, reweights data using saliency maps, and searches architectures on saliency-reweighted data. Our framework is based on four-level optimization, which performs four learning stages in a unified way. At the first stage, a model is trained with its architecture tentatively fixed. At the second stage, saliency maps are generated using the trained model. At the third stage, the model is retrained on saliency-reweighted data. At the fourth stage, the model is evaluated on a validation set and the architecture is updated by minimizing the validation loss. Experiments on several datasets demonstrate the effectiveness of our framework.
Author Information
Ramtin Hosseini (UCSD)
Pengtao Xie (UC San Diego)
More from the Same Authors
-
2022 : Betty: An Automatic Differentiation Library for Multilevel Optimization »
Sang Choe · Willie Neiswanger · Pengtao Xie · Eric Xing -
2023 Poster: LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching »
Duy Minh Ho Nguyen · Hoang Nguyen · Nghiem Diep · Tan Ngoc Pham · Tri Cao · Binh Nguyen · Paul Swoboda · Nhat Ho · Shadi Albarqouni · Pengtao Xie · Mathias Niepert · Daniel Sonntag -
2023 Poster: Making Scalable Meta Learning Practical »
Sang Choe · Sanket Vaibhav Mehta · Hwijeen Ahn · Willie Neiswanger · Pengtao Xie · Emma Strubell · Eric Xing -
2023 Workshop: 4th Workshop on Self-Supervised Learning: Theory and Practice »
Tengda Han · Ishan Misra · Pengtao Xie · Mathilde Caron · Hilde Kuehne -
2022 Workshop: Self-Supervised Learning: Theory and Practice »
Ishan Misra · Pengtao Xie · Gul Varol · Yale Song · Yuki Asano · Xiaolong Wang · Pauline Luc -
2021 Workshop: 2nd Workshop on Self-Supervised Learning: Theory and Practice »
Pengtao Xie · Ishan Misra · Pulkit Agrawal · Abdelrahman Mohamed · Shentong Mo · Youwei Liang · Jeannette Bohg · Kristina N Toutanova