These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining

• URL: http://arxiv.org/abs/2506.18221v2
• Date: Thu, 26 Jun 2025 13:50:38 GMT
• Title: These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining
• Authors: Xingyu Alice Yang, Jianyu Zhang, Léon Bottou,
• Abstract summary: Transfer learning is a cornerstone of modern machine learning, promising a way to adapt models pretrained on a broad mix of data to new tasks with minimal new data.<n>We evaluate model transfer from a pretraining mixture to each of its component tasks, assessing whether pretrained features can match the performance of task-specific direct training.<n>We identify a fundamental limitation in deep learning models, where networks fail to learn new features once they encode similar competing features during training.
• Score: 10.749875317643031
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Transfer learning is a cornerstone of modern machine learning, promising a way to adapt models pretrained on a broad mix of data to new tasks with minimal new data. However, a significant challenge remains in ensuring that transferred features are sufficient to handle unseen datasets, amplified by the difficulty of quantifying whether two tasks are "related". To address these challenges, we evaluate model transfer from a pretraining mixture to each of its component tasks, assessing whether pretrained features can match the performance of task-specific direct training. We identify a fundamental limitation in deep learning models -- an "information saturation bottleneck" -- where networks fail to learn new features once they encode similar competing features during training. When restricted to learning only a subset of key features during pretraining, models will permanently lose critical features for transfer and perform inconsistently on data distributions, even components of the training mixture. Empirical evidence from published studies suggests that this phenomenon is pervasive in deep learning architectures -- factors such as data distribution or ordering affect the features that current representation learning methods can learn over time. This study suggests that relying solely on large-scale networks may not be as effective as focusing on task-specific training, when available. We propose richer feature representations as a potential solution to better generalize across new datasets and, specifically, present existing methods alongside a novel approach, the initial steps towards addressing this challenge.

Related papers

• Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification [34.37262622415682]
  We propose a new adaptation framework called Data Adaptive Traceback. Specifically, we utilize a zero-shot-based method to extract the most downstream task-related subset of the pre-training data. We adopt a pseudo-label-based semi-supervised technique to reuse the pre-training images and a vision-language contrastive learning method to address the confirmation bias issue in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-07-11T18:01:58Z)
• Negotiated Representations to Prevent Forgetting in Machine Learning Applications [0.0]
  Catastrophic forgetting is a significant challenge in the field of machine learning. We propose a novel method for preventing catastrophic forgetting in machine learning applications.
  arXiv  Detail & Related papers  (2023-11-30T22:43:50Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning [40.13416912075668]
  We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
  arXiv  Detail & Related papers  (2023-06-21T01:43:25Z)
• Optimal transfer protocol by incremental layer defrosting [66.76153955485584]
  Transfer learning is a powerful tool enabling model training with limited amounts of data. The simplest transfer learning protocol is based on freezing" the feature-extractor layers of a network pre-trained on a data-rich source task. We show that this protocol is often sub-optimal and the largest performance gain may be achieved when smaller portions of the pre-trained network are kept frozen.
  arXiv  Detail & Related papers  (2023-03-02T17:32:11Z)
• Frugal Reinforcement-based Active Learning [12.18340575383456]
  We propose a novel active learning approach for label-efficient training. The proposed method is iterative and aims at minimizing a constrained objective function that mixes diversity, representativity and uncertainty criteria. We also introduce a novel weighting mechanism based on reinforcement learning, which adaptively balances these criteria at each training iteration.
  arXiv  Detail & Related papers  (2022-12-09T14:17:45Z)
• Discrete Key-Value Bottleneck [95.61236311369821]
  Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. One powerful approach that has addressed this challenge involves pre-training of large encoders on volumes of readily available data, followed by task-specific tuning. Given a new task, however, updating the weights of these encoders is challenging as a large number of weights needs to be fine-tuned, and as a result, they forget information about the previous tasks. We propose a model architecture to address this issue, building upon a discrete bottleneck containing pairs of separate and learnable key-value codes.
  arXiv  Detail & Related papers  (2022-07-22T17:52:30Z)
• Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification [53.735029033681435]
  Transfer learning is a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. In this work, we demonstrate that adversarially-trained models transfer better than non-adversarially-trained models.
  arXiv  Detail & Related papers  (2020-07-11T22:48:42Z)
• Uniform Priors for Data-Efficient Transfer [65.086680950871]
  We show that features that are most transferable have high uniformity in the embedding space. We evaluate the regularization on its ability to facilitate adaptation to unseen tasks and data.
  arXiv  Detail & Related papers  (2020-06-30T04:39:36Z)
• Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks [27.44348371795822]
  We develop a statistical minimax framework to characterize the limits of transfer learning. We derive a lower-bound for the target generalization error achievable by any algorithm as a function of the number of labeled source and target data.
  arXiv  Detail & Related papers  (2020-06-16T22:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.