Timezone: »
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental moment matching (IMM), to resolve this problem. IMM incrementally matches the moment of the posterior distribution of the neural network which is trained on the first and the second task, respectively. To make the search space of posterior parameter smooth, the IMM procedure is complemented by various transfer learning techniques including weight transfer, L2-norm of the old and the new parameter, and a variant of dropout with the old parameter. We analyze our approach on a variety of datasets including the MNIST, CIFAR-10, Caltech-UCSD-Birds, and Lifelog datasets. The experimental results show that IMM achieves state-of-the-art performance by balancing the information between an old and a new network.
Author Information
Sang-Woo Lee (Naver Corp.)
Jin-Hwa Kim (SK T-Brain)
Jaehyun Jun (Seoul National University)
Jung-Woo Ha (Clova AI Research, NAVER Corp.)

- Head, AI Innovation, NAVER Cloud - Research Fellow, NAVER AI Lab - Datasets and Benchmarks Co-Chair, NeurIPS 2023 - Socials Co-Chair, ICML 2023 - Socials Co-Chair, NeurIPS 2022 - BS, Seoul National University - PhD, Seoul National University
Byoung-Tak Zhang (Seoul National University & Surromind Robotics)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Spotlight: Overcoming Catastrophic Forgetting by Incremental Moment Matching »
Thu. Dec 7th 01:45 -- 01:50 AM Room Hall A
More from the Same Authors
-
2021 : KLUE: Korean Language Understanding Evaluation »
Sungjoon Park · Jihyung Moon · Sungdong Kim · Won Ik Cho · Ji Yoon Han · Jangwon Park · Chisung Song · Junseong Kim · Youngsook Song · Taehwan Oh · Joohong Lee · Juhyun Oh · Sungwon Lyu · Younghoon Jeong · Inkwon Lee · Sangwoo Seo · Dongjun Lee · Hyunwoo Kim · Myeonghwa Lee · Seongbo Jang · Seungwon Do · Sunkyoung Kim · Kyungtae Lim · Jongwon Lee · Kyumin Park · Jamin Shin · Seonghyun Kim · Lucy Park · Alice Oh · Jung-Woo Ha · Kyunghyun Cho -
2021 : Partition-based Local Independence Discovery »
Inwoo Hwang · Byoung-Tak Zhang · Sanghack Lee -
2021 : C^3: Contrastive Learning for Cross-domain Correspondence in Few-shot Image Generation »
Hyukgi Lee · Gi-Cheon Kang · Chang-Hoon Jeong · Hanwool Sul · Byoung-Tak Zhang -
2022 : Fine-tuning Diffusion Models with Limited Data »
Taehong Moon · Moonseok Choi · Gayoung Lee · Jung-Woo Ha · Juho Lee -
2022 Poster: Robust Imitation via Mirror Descent Inverse Reinforcement Learning »
Dong-Sig Han · Hyunseo Kim · Hyundo Lee · JeHwan Ryu · Byoung-Tak Zhang -
2022 Poster: SelecMix: Debiased Learning by Contradicting-pair Sampling »
Inwoo Hwang · Sangjun Lee · Yunhyeok Kwak · Seong Joon Oh · Damien Teney · Jin-Hwa Kim · Byoung-Tak Zhang -
2022 Poster: On Divergence Measures for Bayesian Pseudocoresets »
Balhae Kim · Jungwon Choi · Seanie Lee · Yoonho Lee · Jung-Woo Ha · Juho Lee -
2021 Poster: Metropolis-Hastings Data Augmentation for Graph Neural Networks »
Hyeonjin Park · Seunghun Lee · Sihyeon Kim · Jinyoung Park · Jisu Jeong · Kyung-Min Kim · Jung-Woo Ha · Hyunwoo Kim -
2021 Poster: Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning »
Kibeom Kim · Min Whoo Lee · Yoonsung Kim · JeHwan Ryu · Minsu Lee · Byoung-Tak Zhang -
2021 Social: ML in Korea »
Jung-Woo Ha -
2020 Workshop: BabyMind: How Babies Learn and How Machines Can Imitate »
Byoung-Tak Zhang · Gary Marcus · Angelo Cangelosi · Pia Knoeferle · Klaus Obermayer · David Vernon · Chen Yu -
2020 : Opening Remarks: BabyMind, Byoung-Tak Zhang and Gary Marcus »
Byoung-Tak Zhang · Gary Marcus -
2020 Poster: Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs »
Dasol Hwang · Jinyoung Park · Sunyoung Kwon · KyungMin Kim · Jung-Woo Ha · Hyunwoo Kim -
2020 Social: NeurIPS 2020 Social ML in Korea »
Jung-Woo Ha -
2018 Poster: Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog »
Sang-Woo Lee · Yu-Jung Heo · Byoung-Tak Zhang -
2018 Spotlight: Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog »
Sang-Woo Lee · Yu-Jung Heo · Byoung-Tak Zhang -
2018 Poster: Bilinear Attention Networks »
Jin-Hwa Kim · Jaehyun Jun · Byoung-Tak Zhang -
2017 : Posters and Coffee »
Jean-Baptiste Tristan · Yunseong Lee · Anna Veronika Dorogush · Shohei Hido · Michael Terry · Mennatullah Siam · Hidemoto Nakada · Cody Coleman · Jung-Woo Ha · Hao Zhang · Adam Stooke · Chen Meng · Christopher Kappler · Lane Schwartz · Christopher Olston · Sebastian Schelter · Minmin Sun · Daniel Kang · Waldemar Hummer · Jichan Chung · Tim Kraska · Kannan Ramchandran · Nick Hynes · Christoph Boden · Donghyun Kwak -
2016 : PororoQA: Cartoon Video Series Dataset for Story Understanding »
KyungMin Kim · Min-Oh Heo · Byoung-Tak Zhang -
2016 Poster: Multimodal Residual Learning for Visual QA »
Jin-Hwa Kim · Sang-Woo Lee · Donghyun Kwak · Min-Oh Heo · Jeonghee Kim · Jung-Woo Ha · Byoung-Tak Zhang -
2010 Poster: Generative Local Metric Learning for Nearest Neighbor Classification »
Yung-Kyun Noh · Byoung-Tak Zhang · Daniel Lee