Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements

• URL: http://arxiv.org/abs/2405.02581v1
• Date: Sat, 4 May 2024 06:31:38 GMT
• Title: Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements
• Authors: Niccolò Biondi, Federico Pernici, Simone Ricci, Alberto Del Bimbo,
• Abstract summary: Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery images with the updated model. We show that the stationary representations learned by the $d$-Simplex fixed classifier optimally approximate compatibility representation according to the two inequality constraints of its formal definition.
• Score: 20.96380700548786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery images with the updated model. While recent research has shown promising empirical evidence, there is still a lack of comprehensive theoretical understanding about learning compatible representations. In this paper, we demonstrate that the stationary representations learned by the $d$-Simplex fixed classifier optimally approximate compatibility representation according to the two inequality constraints of its formal definition. This not only establishes a solid foundation for future works in this line of research but also presents implications that can be exploited in practical learning scenarios. An exemplary application is the now-standard practice of downloading and fine-tuning new pre-trained models. Specifically, we show the strengths and critical issues of stationary representations in the case in which a model undergoing sequential fine-tuning is asynchronously replaced by downloading a better-performing model pre-trained elsewhere. Such a representation enables seamless delivery of retrieval service (i.e., no reprocessing of gallery images) and offers improved performance without operational disruptions during model replacement. Code available at: https://github.com/miccunifi/iamcl2r.

Related papers

• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning [63.850451635362425]
  Continual learning requires a model to adapt to ongoing changes in the data distribution. We show that the combination of a large language model and an image generation model can similarly provide useful premonitions. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem.
  arXiv  Detail & Related papers  (2024-03-12T06:29:54Z)
• Meaning Representations from Trajectories in Autoregressive Models [106.63181745054571]
  We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle.
  arXiv  Detail & Related papers  (2023-10-23T04:35:58Z)
• FastFill: Efficient Compatible Model Update [40.27741553705222]
  FastFill is a compatible model update process using feature alignment and policy based partial backfilling. We show that previous backfilling strategies suffer from decreased performance and demonstrate the importance of both the training objective and the ordering in online partial backfilling.
  arXiv  Detail & Related papers  (2023-03-08T18:03:51Z)
• Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers [66.36045164286854]
  We analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases. By choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.
  arXiv  Detail & Related papers  (2022-10-28T17:52:10Z)
• Towards Universal Backward-Compatible Representation Learning [29.77801805854168]
  backward-compatible representation learning is introduced to support backfill-free model upgrades. We first introduce a new problem of universal backward-compatible representation learning, covering all possible data split in model upgrades. We propose a simple yet effective method, dubbed Universal Backward- Training (UniBCT) with a novel structural prototype refinement algorithm.
  arXiv  Detail & Related papers  (2022-03-03T09:23:51Z)
• Forward Compatible Training for Representation Learning [53.300192863727226]
  backward compatible training (BCT) modifies training of the new model to make its representations compatible with those of the old model. BCT can significantly hinder the performance of the new model. In this work, we propose a new learning paradigm for representation learning: forward compatible training (FCT)
  arXiv  Detail & Related papers  (2021-12-06T06:18:54Z)
• CoReS: Compatible Representations via Stationarity [20.607894099896214]
  In visual search systems, compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. We propose CoReS, a new training procedure to learn representations that are textitcompatible with those previously learned. We demonstrate that our training procedure largely outperforms the current state of the art and is particularly effective in the case of multiple upgrades of the training-set.
  arXiv  Detail & Related papers  (2021-11-15T09:35:54Z)
• Learning Compatible Embeddings [4.926613940939671]
  backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. We propose a general framework called Learning Compatible Embeddings (LCE) which is applicable for both cross model compatibility and compatible training in direct/forward/backward manners.
  arXiv  Detail & Related papers  (2021-08-04T10:48:41Z)
• Towards Backward-Compatible Representation Learning [86.39292571306395]
  We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning.
  arXiv  Detail & Related papers  (2020-03-26T14:34:09Z)

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.