Saved in:
Bibliographic Details
Main Authors: Yang, Xiaoyu, Lu, Jie, Yu, En, Duan, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.07620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917099070291968
author Yang, Xiaoyu
Lu, Jie
Yu, En
Duan, Wei
author_facet Yang, Xiaoyu
Lu, Jie
Yu, En
Duan, Wei
contents The remarkable success of large-scale contrastive pre-training has been largely driven by by vast yet static datasets. However, as the scaling paradigm evolves, this paradigm encounters a fundamental challenge when applied to dynamic data streams characterized by concept drift - unpredictable changes in the underlying data distribution. This paper aims to advance robust pre-training under such non-stationary environments. We begin by revealing that conventional contrastive pre-training methods are highly susceptible to concept drift, resulting in significant substantial bias and instability within the learned feature representations. To systematically analyze these effects, we develop a structural causal model that elucidates how drift acts as a confounder, distorting the learned representations. Based on these causal insights, we propose Resilient Contrastive Pre-training (RCP), a novel method that incorporates causal intervention. RCP formulates a causally-informed objective to mitigate drift-induced biases through targeted interventions. The method is designed for simple and scalable implementation and exhibits notable adaptability, promoting robust and autonomous pre-training on non-stationary data. Comprehensive experiments across various downstream tasks consistently demonstrate that RCP effectively alleviates the detrimental impact of concept drift, yielding more resilient and generalizable representations.
format Preprint
id arxiv_https___arxiv_org_abs_2502_07620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Resilient Contrastive Pre-training under Non-Stationary Drift
Yang, Xiaoyu
Lu, Jie
Yu, En
Duan, Wei
Machine Learning
Computer Vision and Pattern Recognition
The remarkable success of large-scale contrastive pre-training has been largely driven by by vast yet static datasets. However, as the scaling paradigm evolves, this paradigm encounters a fundamental challenge when applied to dynamic data streams characterized by concept drift - unpredictable changes in the underlying data distribution. This paper aims to advance robust pre-training under such non-stationary environments. We begin by revealing that conventional contrastive pre-training methods are highly susceptible to concept drift, resulting in significant substantial bias and instability within the learned feature representations. To systematically analyze these effects, we develop a structural causal model that elucidates how drift acts as a confounder, distorting the learned representations. Based on these causal insights, we propose Resilient Contrastive Pre-training (RCP), a novel method that incorporates causal intervention. RCP formulates a causally-informed objective to mitigate drift-induced biases through targeted interventions. The method is designed for simple and scalable implementation and exhibits notable adaptability, promoting robust and autonomous pre-training on non-stationary data. Comprehensive experiments across various downstream tasks consistently demonstrate that RCP effectively alleviates the detrimental impact of concept drift, yielding more resilient and generalizable representations.
title Resilient Contrastive Pre-training under Non-Stationary Drift
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.07620