| Presentation | 2022-06-27 AI knowledge forgetting based on the importance of model parameters Tomoya Yamashita, Masanori Yamada, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The accuracy of Deep Learning has been greatly improved by the progress of research in computer technology and Deep Learning techniques, and it has produced results in many fields. However, as Deep Learning becomes more widely used, problems related to privacy violation and data leakage are expected to arise. In this paper, we aim to solve these problems by making Deep Learning models forget their knowledge. We propose a method of forgetting knowledge about a desired task by adding noise to Deep Learning model parameters. Experimental results confirm that the proposed method achieves knowledge oblivion of Deep Learning models. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Learning / Continual Learning / EWC / Catastrophic Forgetting / Privacy Protection |
| Paper # | NC2022-3,IBISML2022-3 |
| Date of Issue | 2022-06-20 (NC, IBISML) |
| Conference Information | |
| Committee | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
|---|---|
| Conference Date | 2022/6/27(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hiroshi Yamakawa(Univ of Tokyo) / Masashi Sugiyama(Univ. of Tokyo) |
| Vice Chair | Hirokazu Tanaka(Tokyo City Univ.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Hirokazu Tanaka(NTT) / Toshihiro Kamishima(NICT) / Koji Tsuda(NTT) / (Hokkaido Univ.) |
| Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Tomoki Kurikawa(KMU) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | AI knowledge forgetting based on the importance of model parameters |
| Sub Title (in English) | |
| Keyword(1) | Deep Learning |
| Keyword(2) | Continual Learning |
| Keyword(3) | EWC |
| Keyword(4) | Catastrophic Forgetting |
| Keyword(5) | Privacy Protection |
| 1st Author's Name | Tomoya Yamashita |
| 1st Author's Affiliation | NTT Social Informatics Laboratories(NTT) |
| 2nd Author's Name | Masanori Yamada |
| 2nd Author's Affiliation | NTT Social Informatics Laboratories(NTT) |
| Date | 2022-06-27 |
| Paper # | NC2022-3,IBISML2022-3 |
| Volume (vol) | vol.122 |
| Number (no) | NC-89,IBISML-90 |
| Page | pp.pp.14-19(NC), pp.14-19(IBISML), |
| #Pages | 6 |
| Date of Issue | 2022-06-20 (NC, IBISML) |