Cover Image

Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Vejendla, Harshil
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
by: Goswami, Dipam, et al.
Published: (2025)

VIBE: Vector Index Benchmark for Embeddings
by: Jääsaari, Elias, et al.
Published: (2025)

SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
by: Vejendla, Harshil
Published: (2025)

LoRACode: LoRA Adapters for Code Embeddings
by: Chaturvedi, Saumya, et al.
Published: (2025)

Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering
by: Ebrat, Danial, et al.
Published: (2025)

RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling
by: Vejendla, Harshil
Published: (2026)

Challenges and Considerations in Annotating Legal Data: A Comprehensive Overview
by: Darji, Harshil, et al.
Published: (2024)

H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
by: Vejendla, Harshil
Published: (2025)

LATTA: Langevin-Anchored Test-Time Adaptation for Enhanced Robustness and Stability
by: Vejendla, Harshil
Published: (2025)

Learning to Predict Chaos: Curriculum-Driven Training for Robust Forecasting of Chaotic Dynamics
by: Vejendla, Harshil
Published: (2025)

A Super Fast K-means for Indexing Vector Embeddings
by: Kuffo, Leonardo, et al.
Published: (2026)

Towards Lifelong Learning Embeddings: An Algorithmic Approach to Dynamically Extend Embeddings
by: Gomes, Miguel Alves, et al.
Published: (2024)

Teaching by Failure: Counter-Example-Driven Curricula for Transformer Self-Improvement
by: Vejendla, Harshil
Published: (2025)

Wave-PDE Nets: Trainable Wave-Equation Layers as an Alternative to Attention
by: Vejendla, Harshil
Published: (2025)

Multimodal Data Curation Through Ranked Retrieval
by: Muthukumar, Pratyush, et al.
Published: (2026)

Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
by: Yoo, Hyunsik, et al.
Published: (2025)

Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
by: Long, Mabiao, et al.
Published: (2025)

Segmentation and Processing of German Court Decisions from Open Legal Data
by: Darji, Harshil, et al.
Published: (2026)

From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation
by: Shin, Jeeho, et al.
Published: (2025)

Semantic Outlier Removal with Embedding Models and LLMs
by: Akbiyik, Eren, et al.
Published: (2025)

EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention
by: Tian, Zhen, et al.
Published: (2024)

Alignment Adapter to Improve the Performance of Compressed Deep Learning Models
by: Rai, Rohit Raj, et al.
Published: (2026)

LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
by: Li, Hang, et al.
Published: (2025)

On the Embedding Collapse when Scaling up Recommendation Models
by: Guo, Xingzhuo, et al.
Published: (2023)

Long-Sequence Recommendation Models Need Decoupled Embeddings
by: Feng, Ningya, et al.
Published: (2024)

PSQE: A Theoretical-Practical Approach to Pseudo Seed Quality Enhancement for Unsupervised Multimodal Entity Alignment
by: Hong, Yunpeng, et al.
Published: (2026)

AdaS&S: a One-Shot Supernet Approach for Automatic Embedding Size Search in Deep Recommender System
by: Wei, He, et al.
Published: (2024)

Accelerating Recommender Model Training by Dynamically Skipping Stale Embeddings
by: Maboud, Yassaman Ebrahimzadeh, et al.
Published: (2024)

LEMUR: Learned Multi-Vector Retrieval
by: Jääsaari, Elias, et al.
Published: (2026)

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation
by: Zhou, Sashuai, et al.
Published: (2025)

Locally-Adaptive Quantization for Streaming Vector Search
by: Aguerrebere, Cecilia, et al.
Published: (2024)

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
by: Ju, Yeong-Joon, et al.
Published: (2025)

Curator: Efficient Indexing for Multi-Tenant Vector Databases
by: Jin, Yicheng, et al.
Published: (2024)

Efficient Vector Search in the Wild: One Model for Multi-K Queries
by: Peng, Yifan, et al.
Published: (2026)

Generalized Embedding Machines for Recommender Systems
by: Yang, Enneng, et al.
Published: (2020)

A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems
by: Tran, Hung Vinh, et al.
Published: (2024)

Methods for Generating Drift in Text Streams
by: Garcia, Cristiano Mesquita, et al.
Published: (2024)

Topological Metric for Unsupervised Embedding Quality Evaluation
by: Shestov, Aleksei, et al.
Published: (2025)

Scaling Laws for Embedding Dimension in Information Retrieval
by: Killingback, Julian, et al.
Published: (2026)

Applying Embedding-Based Retrieval to Airbnb Search
by: Abdool, Mustafa, et al.
Published: (2026)