Reducing Model Churn: Stable Re-training of Conversational Agents

Christopher Hidey, Fei Liu, Rahul Goel


Abstract
Retraining modern deep learning systems can lead to variations in model performance even when trained using the same data and hyper-parameters by simply using different random seeds. This phenomenon is known as model churn or model jitter. This issue is often exacerbated in real world settings, where noise may be introduced in the data collection process. In this work we tackle the problem of stable retraining with a novel focus on structured prediction for conversational semantic parsing. We first quantify the model churn by introducing metrics for agreement between predictions across multiple retrainings. Next, we devise realistic scenarios for noise injection and demonstrate the effectiveness of various churn reduction techniques such as ensembling and distillation. Lastly, we discuss practical trade-offs between such techniques and show that co-distillation provides a sweet spot in terms of churn reduction with only a modest increase in resource usage.
Anthology ID:
2022.sigdial-1.2
Volume:
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2022
Address:
Edinburgh, UK
Editors:
Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–25
Language:
URL:
https://aclanthology.org/2022.sigdial-1.2
DOI:
10.18653/v1/2022.sigdial-1.2
Bibkey:
Cite (ACL):
Christopher Hidey, Fei Liu, and Rahul Goel. 2022. Reducing Model Churn: Stable Re-training of Conversational Agents. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 14–25, Edinburgh, UK. Association for Computational Linguistics.
Cite (Informal):
Reducing Model Churn: Stable Re-training of Conversational Agents (Hidey et al., SIGDIAL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigdial-1.2.pdf
Video:
 https://youtu.be/okIrVZD-zDE
Code
 google/stable-retraining-conversational-agents
Data
MTOPTOPv2