What is Next when Sequential Prediction Meets Implicitly Hard Interaction?
Paper
Paper/Presentation Title | What is Next when Sequential Prediction Meets Implicitly Hard Interaction? |
---|---|
Presentation Type | Paper |
Authors | Hu, Kaixi (Author), Li, Lin (Author), Xie, Qing (Author), Liu, Jianquan (Author) and Tao, Xiaohui (Author) |
Journal or Proceedings Title | Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) |
ERA Conference ID | 42291 |
Number of Pages | 10 |
Year | 2021 |
Place of Publication | New York, United States |
ISBN | 9781450384469 |
Digital Object Identifier (DOI) | https://doi.org/10.1145/3459637.3482492 |
Web Address (URL) of Paper | https://dl.acm.org/doi/abs/10.1145/3459637.3482492 |
Conference/Event | 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) |
ACM International Conference on Information and Knowledge Management | |
Event Details | ACM International Conference on Information and Knowledge Management CIKM Rank A A A A A A A A A A A A A A A A A A A A |
Event Details | 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) Event Date 01 to end of 05 Nov 2021 Event Location Queensland, Australia |
Abstract | Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions caused by wrong responses. However, a model might conduct correct responses by capturing a subset of learnable patterns, which results in implicitly hard interactions with some unlearned patterns. As such, its generalization performance is weakened. The problem gets more serious in sequential prediction due to the interference of substantial similar candidate targets. To this end, we propose a Hardness Aware Interaction Learning framework (HAIL) that mainly consists of two base sequential learning networks and mutual exclusivity distillation (MED). The base networks are initialized differently to learn distinctive view patterns, thus gaining different training experiences. The experiences in the form of the unlikelihood of correct responses are drawn from each other by MED, which provides mutual exclusivity knowledge to figure out implicitly hard interactions. Moreover, we deduce that the unlikelihood essentially introduces additional gradients to push the pattern learning of correct responses. Our framework can be easily extended to more peer base networks. Evaluation is conducted on four datasets covering cyber and physical spaces. The experimental results demonstrate that our framework outperforms several state-of-the-art methods in terms of top-k based metrics. |
Keywords | sequential prediction, hard interaction, unlikelihood, knowledge distillation |
ANZSRC Field of Research 2020 | 460501. Data engineering and data science |
460308. Pattern recognition | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Wuhan University of Technology, China |
NEC Corporation, Japan | |
School of Sciences | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6z57/what-is-next-when-sequential-prediction-meets-implicitly-hard-interaction
Download files
89
total views203
total downloads2
views this month10
downloads this month