Timezone: »
Poster
Bidirectional Learning for Offline Infinite-width Model-based Optimization
Can Chen · Yingxueff Zhang · Jie Fu · Xue (Steve) Liu · Mark Coates
In offline model-based optimization, we strive to maximize a black-box objective function by only leveraging a static dataset of designs and their scores. This problem setting arises in numerous fields including the design of materials, robots, DNAs, proteins, etc. Recent approaches train a deep neural network (DNN) model on the static dataset to act as a proxy function, and then perform gradient ascent on the existing designs to obtain potentially high-scoring designs. This methodology frequently suffers from the out-of-distribution problem where the proxy function often returns adversarial designs. To mitigate this problem, we propose $\textit{\textbf{B}i\textbf{D}irectional learning for offline \textbf{I}nfinite-width model-based optimization}~(\textbf{BDI})$. BDI consists of two mappings: the forward mapping leverages the static dataset to predict the scores of the high-scoring designs, and the backward mapping leverages the high-scoring designs to predict the scores of the static dataset. The backward mapping, neglected in previous work, can distill more information of the static dataset into the high-scoring designs, which effectively mitigates the out-of-distribution problem. Yet, for a finite-width DNN model, the loss function of the backward mapping is intractable and only has an approximate form, which leads to a significant deterioration of the design quality. We thus adopt an infinite-width DNN model and propose to employ the corresponding neural tangent kernel to yield a closed-form loss for more accurate design updates. Experiments on various tasks verify the effectiveness of BDI. The code is available [here](https://github.com/GGchen1997/BDI).
Author Information
Can Chen (McGill University & MILA)
Yingxueff Zhang (Huawei Technology Canada)
Jie Fu (University of Montreal)
Xue (Steve) Liu (McGill University)
Mark Coates (McGill University)
More from the Same Authors
-
2021 : Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods »
Yang Hu · Zhui Zhu · Sirui Song · Xue (Steve) Liu · Yang Yu -
2022 Poster: Versatile Multi-stage Graph Neural Network for Circuit Representation »
shuwen yang · Zhihao Yang · Dong Li · Yingxueff Zhang · Zhanguang Zhang · Guojie Song · Jianye Hao -
2022 : Structural Causal Model for Molecular Dynamics Simulation »
Qi Liu · Yuanqi Du · Fan Feng · Qiwei Ye · Jie Fu -
2022 : Graph neural networks for Ramsey graphs »
Amur Ghose · Amit Levi · Yingxueff Zhang -
2022 : Precise Augmentation and Counting of Helicobacter Pylori in Histology Image »
Yufei CUI · Yixin Chen · Zhifeng Shuai · Fang Peng · Yanbo Lv · Luoning Zheng · Xue (Steve) Liu · Antoni Chan · Tei-Wei Kuo · Chun Jason XUE -
2023 Poster: Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network »
Fuyuan Lyu · Xing Tang · Dugang Liu · Chen Ma · Weihong Luo · xiuqiang He · Xue (Steve) Liu -
2023 Poster: Parallel-mentoring for Offline Model-based Optimization »
Can Chen · Christopher Beckham · Zixuan Liu · Xue (Steve) Liu · Chris Pal -
2023 Poster: Retrieval-Augmented Multiple Instance Learning »
Yufei CUI · Ziquan Liu · Yixin Chen · Yuchen Lu · Xinyue Yu · Xue (Steve) Liu · Tei-Wei Kuo · Miguel Rodrigues · Chun Jason XUE · Antoni Chan -
2023 Poster: When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability »
Sitao Luan · Chenqing Hua · Minkai Xu · Qincheng Lu · Jiaqi Zhu · Xiao-Wen Chang · Jie Fu · Jure Leskovec · Doina Precup -
2023 Poster: GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning »
Haiteng Zhao · Shengchao Liu · Ma Chang · Hannan Xu · Jie Fu · Zhihong Deng · Lingpeng Kong · Qi Liu -
2023 Poster: Importance-aware Co-teaching for Offline Model-based Optimization »
Ye Yuan · Can Chen · Zixuan Liu · Willie Neiswanger · Xue (Steve) Liu -
2023 Poster: Neural Graph Generation from Graph Statistics »
Kiarash Zahirnia · Oliver Schulte · Mark Coates · Yaochen Hu -
2023 Poster: Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias »
Zhongwei Wan · Che Liu · Mi Zhang · Jie Fu · Benyou Wang · Sibo Cheng · Lei Ma · César Quilodrán-Casas · Rossella Arcucci -
2023 Poster: MARBLE: Music Audio Representation Benchmark for Universal Evaluation »
Ruibin Yuan · Yinghao Ma · Yizhi Li · Ge Zhang · Xingran Chen · Hanzhi Yin · zhuo le · Yiqi Liu · Jiawen Huang · Zeyue Tian · Binyue Deng · Ningzhi Wang · Chenghua Lin · Emmanouil Benetos · Anton Ragni · Norbert Gyenge · Roger Dannenberg · wenhu chen · Gus Xia · Wei Xue · Si Liu · Shi Wang · Ruibo Liu · Yike Guo · Jie Fu -
2022 Spotlight: Lightning Talks 3A-2 »
shuwen yang · Xu Zhang · Delvin Ce Zhang · Lan-Zhe Guo · Renzhe Xu · Zhuoer Xu · Yao-Xiang Ding · Weihan Li · Xingxuan Zhang · Xi-Zhu Wu · Zhenyuan Yuan · Hady Lauw · Yu Qi · Yi-Ge Zhang · Zhihao Yang · Guanghui Zhu · Dong Li · Changhua Meng · Kun Zhou · Gang Pan · Zhi-Fan Wu · Bo Li · Minghui Zhu · Zhi-Hua Zhou · Yafeng Zhang · Yingxueff Zhang · shiwen cui · Jie-Jing Shao · Zhanguang Zhang · Zhenzhe Ying · Xiaolong Chen · Yu-Feng Li · Guojie Song · Peng Cui · Weiqiang Wang · Ming GU · Jianye Hao · Yihua Huang -
2022 Spotlight: Versatile Multi-stage Graph Neural Network for Circuit Representation »
shuwen yang · Zhihao Yang · Dong Li · Yingxueff Zhang · Zhanguang Zhang · Guojie Song · Jianye Hao -
2021 Poster: Generalized DataWeighting via Class-Level Gradient Manipulation »
Can Chen · Shuhao Zheng · Xi Chen · Erqun Dong · Xue (Steve) Liu · Hao Liu · Dejing Dou