Presentation | 2022-06-27 Transformer-Based Fully Trainable Model for Point Process with Past Sequence-Representative Vector Fumiya Nishizawa, Sujun Hong, Hirotaka Hachiya, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, a Transformer-based partially trainable point process has been proposed, where a feature vector is extracted from past event sequence to predict the future event. However, high dependencies of the feature on last event andlimitation of handmade designed hazard function would cause deterioration peformance. To overcome these problems, wepropose a Transformer-based fully trainable point process, where multiple trainable vectors are embedded into the past eventsequence and are transformed through an attention mechanism to realize adaptive and general approximation and prediction. We show the effectiveness of our proposed method through experiments on two datasets. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | point process / Transformer / seismic event / Hawkes process |
Paper # | NC2022-1,IBISML2022-1 |
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 | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Transformer-Based Fully Trainable Model for Point Process with Past Sequence-Representative Vector |
Sub Title (in English) | |
Keyword(1) | point process |
Keyword(2) | Transformer |
Keyword(3) | seismic event |
Keyword(4) | Hawkes process |
1st Author's Name | Fumiya Nishizawa |
1st Author's Affiliation | Graduate School of System Engineering, Wakayama University(Graduate School of System Engineering, Wakayama University) |
2nd Author's Name | Sujun Hong |
2nd Author's Affiliation | Graduate School of System Engineering, Wakayama University(Graduate School of System Engineering, Wakayama University) |
3rd Author's Name | Hirotaka Hachiya |
3rd Author's Affiliation | Graduate School of System Engineering, Wakayama University(Graduate School of System Engineering, Wakayama University) |
Date | 2022-06-27 |
Paper # | NC2022-1,IBISML2022-1 |
Volume (vol) | vol.122 |
Number (no) | NC-89,IBISML-90 |
Page | pp.pp.1-5(NC), pp.1-5(IBISML), |
#Pages | 5 |
Date of Issue | 2022-06-20 (NC, IBISML) |