Incremental Learning with Differentiable Architecture and Forgetting Search

被引:1
|
作者
Smith, James Seale [1 ]
Seymour, Zachary [2 ]
Chiu, Han-Pang [2 ]
机构
[1] Georgia Inst Technol, Atlanta, GA 30332 USA
[2] SRI Int, Princeton, NJ USA
关键词
continual learning; incremental learning; neural architecture search;
D O I
10.1109/IJCNN55064.2022.9892400
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental learning is automatic architecture design via Neural Architecture Search (NAS). In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks. Specifically, we contribute the following: first, we create a strong baseline approach for incremental learning based on Differentiable Architecture Search (DARTS) and state-of-the-art incremental learning strategies, outperforming many existing strategies trained with similar-sized popular architectures; second, we extend the idea of architecture search to regularize architecture forgetting, boosting performance past our proposed baseline. We evaluate our method on both RF signal and image classification tasks, and demonstrate we can achieve up to a 10% performance increase over state-of-the-art methods. Most importantly, our contribution enables learning from continuous distributions on real-world application data for which the complexity of the data distribution is unknown, or the modality less explored (such as RF signal classification).
引用
收藏
页数:8
相关论文
共 50 条
  • [21] Incremental Learning in Nonstationary Environments with Controlled Forgetting
    Elwell, Ryan
    Polikar, Robi
    IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6, 2009, : 1388 - 1395
  • [22] AUTOKWS: KEYWORD SPOTTING WITH DIFFERENTIABLE ARCHITECTURE SEARCH
    Zhang, Bo
    Li, Wenfeng
    Li, Qingyuan
    Zhuang, Weiji
    Chu, Xiangxiang
    Wang, Yujun
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2830 - 2834
  • [23] Image Understanding by Captioning with Differentiable Architecture Search
    Hosseini, Ramtin
    Xie, Pengtao
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 4665 - 4673
  • [24] Defying Imbalanced Forgetting in Class Incremental Learning
    Xu, Shixiong
    Meng, Gaofeng
    Nie, Xing
    Ni, Bolin
    Fan, Bin
    Xiang, Shiming
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 14, 2024, : 16211 - 16219
  • [25] Decoupled differentiable graph neural architecture search
    Chen, Jiamin
    Gao, Jianliang
    Wu, Zhenpeng
    Al-Sabri, Raeed
    Oloulade, Babatounde Moctard
    INFORMATION SCIENCES, 2024, 673
  • [26] Differentiable Architecture Search Based on Coordinate Descent
    Ahn, Pyunghwan
    Hong, Hyeong Gwon
    Kim, Junmo
    IEEE ACCESS, 2021, 9 (09): : 48544 - 48554
  • [27] Layered feature representation for differentiable architecture search
    Hao, Jie
    Zhu, William
    SOFT COMPUTING, 2022, 26 (10) : 4741 - 4753
  • [28] Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification
    Kim, Youngkee
    Jung, Soyi
    Choi, Minseok
    Kim, Joongheon
    2022 THIRTEENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN), 2022, : 363 - 365
  • [29] Dependency-Aware Differentiable Neural Architecture Search
    Zhang, Buang
    Wu, Xinle
    Miao, Hao
    Guo, Chenjuan
    Yang, Bin
    COMPUTER VISION - ECCV 2024, PT LV, 2025, 15113 : 219 - 236
  • [30] Enhanced Differentiable Architecture Search Based on Asymptotic Regularization
    Jin, Cong
    Huang, Jinjie
    Chen, Yuanjian
    Gong, Yuqing
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 78 (02): : 1547 - 1568