Fastfill: Efficient Compatible Model Update

Abstract

In many retrieval systems the original high dimensional data (e.g., images) is mapped to a lower dimensional feature through a learned embedding model. The task of retrieving the most similar data from a gallery set to a given query data is performed through a similarity comparison on features. When the embedding model is updated, it might produce features that are not comparable/compatible with features already in the gallery computed with the old model. Subsequently, all features in the gallery need to be re-computed using the new embedding model -- a computationally expensive process called backfilling. Recently, compatible representation learning methods have been proposed to avoid backfilling. Despite their relative success, there is an inherent trade-off between the new model performance and its compatibility with the old model. In this work, we introduce FastFill: a compatible model update process using feature alignment and policy based partial backfilling to promptly elevate r

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjaeckle2023fastfill

Related papers

• Metric Compatible Training For Online Backfilling In Large-scale Retrieval (2023)2.26
• Forward Compatible Training For Large-scale Embedding Retrieval Systems (2021)8.09
• Backward-compatible Aligned Representations Via An Orthogonal Transformation Layer (2024)0.00
• Privacy-preserving Model Upgrades With Bidirectional Compatible Training In Image Retrieval (2022)0.00
• Towards Backward-compatible Representation Learning (2020)12.93
• Darwinian Model Upgrades: Model Evolving With Selective Compatibility (2022)2.26
• Learning Compatible Embeddings (2021)13.80
• Hot-refresh Model Upgrades With Regression-alleviating Compatible Training In Image Retrieval (2022)2.83