Cover Image

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Monath, Nicholas, Grathwohl, Will, Boratko, Michael, Fergus, Rob, McCallum, Andrew, Zaheer, Manzil
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
by: Yadav, Nishant, et al.
Published: (2024)

A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
by: Dasgupta, Shib, et al.
Published: (2025)

Incremental Extractive Opinion Summarization Using Cover Trees
by: Chowdhury, Somnath Basu Roy, et al.
Published: (2024)

Analysis of Plan-based Retrieval for Grounded Text Generation
by: Godbole, Ameya, et al.
Published: (2024)

Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration
by: Khaled, Ahmed, et al.
Published: (2025)

A Statistical Framework for Data-dependent Retrieval-Augmented Models
by: Basu, Soumya, et al.
Published: (2024)

On the Theoretical Limitations of Embedding-Based Retrieval
by: Weller, Orion, et al.
Published: (2025)

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching
by: Angell, Rico, et al.
Published: (2023)

Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders
by: Rozonoyer, Benjamin, et al.
Published: (2026)

Efficient Distributed Optimization under Heavy-Tailed Noise
by: Lee, Su Hyeong, et al.
Published: (2025)

Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
by: Piterbarg, Ulyana, et al.
Published: (2024)

Efficient, Accurate and Stable Gradients for Neural ODEs
by: McCallum, Sam, et al.
Published: (2024)

Differentially Private Model Merging
by: Yin, Qichuan, et al.
Published: (2026)

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
by: Huang, Yukun, et al.
Published: (2025)

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

Federation over Text: Insight Sharing for Multi-Agent Reasoning
by: Yao, Dixi, et al.
Published: (2026)

Reversible Deep Equilibrium Models
by: McCallum, Sam, et al.
Published: (2025)

Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval
by: Song, Jonghyun, et al.
Published: (2024)

Asynchronous Heavy-Tailed Optimization
by: Sun, Junfei, et al.
Published: (2026)

Efficient Adaptive Federated Optimization
by: Lee, Su Hyeong, et al.
Published: (2024)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
by: Huang, Kezhao, et al.
Published: (2023)

Functional Interpolation for Relative Positions Improves Long Context Transformers
by: Li, Shanda, et al.
Published: (2023)

VISAGNN: Versatile Staleness-Aware Efficient Training on Large-Scale Graphs
by: Xue, Rui
Published: (2025)

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
by: Shi, Kensen, et al.
Published: (2023)

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
by: Skreta, Marta, et al.
Published: (2025)

Kernel Corrector LSTM
by: Tuna, Rodrigo, et al.
Published: (2024)

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
by: Du, Yilun, et al.
Published: (2023)

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
by: Park, Seongwan, et al.
Published: (2025)

Insertion Based Sequence Generation with Learnable Order Dynamics
by: Patel, Dhruvesh, et al.
Published: (2026)

Deep Tabular Representation Corrector
by: Ye, Hangting, et al.
Published: (2026)

Discrete Feynman-Kac Correctors
by: Hasan, Mohsin, et al.
Published: (2026)

Can Public Large Language Models Help Private Cross-device Federated Learning?
by: Wang, Boxin, et al.
Published: (2023)

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
by: Phan, Peter, et al.
Published: (2025)

MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline
by: Sheng, Guangming, et al.
Published: (2024)

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
by: GX-Chen, Anthony, et al.
Published: (2024)

diff History for Neural Language Agents
by: Piterbarg, Ulyana, et al.
Published: (2023)

On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations
by: McCallum, Matthew C., et al.
Published: (2024)

Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions
by: Patel, Dhruvesh, et al.
Published: (2025)

Corrector Sampling in Language Models
by: Gat, Itai, et al.
Published: (2025)

Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems
by: Kolodner, Matthew, et al.
Published: (2024)