A Gradient Accumulation Method for Dense Retriever under Memory Constraint

• URL: http://arxiv.org/abs/2406.12356v3
• Date: Thu, 21 Nov 2024 03:09:23 GMT
• Title: A Gradient Accumulation Method for Dense Retriever under Memory Constraint
• Abstract summary: Contrastive Accumulation (ContAccum) is a stable and efficient memory reduction method for dense retriever trains. Experiments on widely used five information retrieval datasets indicate that ContAccum can surpass not only existing memory reduction methods but also high-resource scenario.
• Score: 7.314901185604559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: InfoNCE loss is commonly used to train dense retriever in information retrieval tasks. It is well known that a large batch is essential to stable and effective training with InfoNCE loss, which requires significant hardware resources. Due to the dependency of large batch, dense retriever has bottleneck of application and research. Recently, memory reduction methods have been broadly adopted to resolve the hardware bottleneck by decomposing forward and backward or using a memory bank. However, current methods still suffer from slow and unstable training. To address these issues, we propose Contrastive Accumulation (ContAccum), a stable and efficient memory reduction method for dense retriever trains that uses a dual memory bank structure to leverage previously generated query and passage representations. Experiments on widely used five information retrieval datasets indicate that ContAccum can surpass not only existing memory reduction methods but also high-resource scenario. Moreover, theoretical analysis and experimental results confirm that ContAccum provides more stable dual-encoder training than current memory bank utilization methods.

Related papers

• Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents [97.19033877543522]
  We present a controlled harness evaluation of memory substrates for memory-augmented agents.<n>We instrument 26 performance and efficiency metrics under a unified harness.<n>These findings motivate substrate routing as a necessary component of adaptive agent memory systems.
  arXiv  Detail & Related papers  (2026-08-15T03:29:48Z)
• MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents [10.248580356955085]
  Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts limit their effectiveness.<n>We propose MGRetrieval, a retrieval strategy that grounds reflective retrieval in the semantic structure of historical memories.<n>Extensive experiments on LoCoMo show that MGRetrieval outperforms the strongest baseline by 8.91% in F1 and 11.11% in BLEU-1.
  arXiv  Detail & Related papers  (2026-05-22T14:41:56Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning [78.46301394559903]
  Large Language Models (LLMs) are increasingly used for long-duration tasks.<n>Current methods face a trade-off between cost and accuracy.<n>MemSifter is a novel framework that offloads the memory retrieval process to a small-scale proxy model.
  arXiv  Detail & Related papers  (2026-03-03T02:57:38Z)
• Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory [6.493102878734374]
  We analyze how performance differences manifest across write strategies, retrieval methods, and memory utilization behavior.<n>On LoCoMo, retrieval method is the dominant factor.<n>Failure analysis shows that performance breakdowns most often manifest at the retrieval stage rather than at utilization.
  arXiv  Detail & Related papers  (2026-03-02T23:47:23Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)
• LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum [73.82125917416067]
  LACONIC is a family of learned sparse retrievers based on the Llama-3 architecture.<n>The 8B variant achieves a state-of-the-art 60.2 nDCG on the MTEB Retrieval benchmark, ranking 15th on the leaderboard.
  arXiv  Detail & Related papers  (2026-01-04T22:42:20Z)
• Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents [33.617262543252494]
  We present ReMemR1, a memory-augmented agent with callback-enhanced memory that allows selective retrieval from the entire memory history.<n>We also propose Reinforcement Learning with Multi-Level Rewards (RLMLR), which combines final-answer rewards with dense, step-level signals that guide effective memory use.
  arXiv  Detail & Related papers  (2025-09-27T01:36:46Z)
• Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation [80.69067017594709]
  Large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks.<n>We propose a novel framework, log-augmented generation (LAG) that directly reuses prior computation and reasoning from past logs at test time.<n>Our method significantly outperforms standard agentic systems that do not utilize logs.
  arXiv  Detail & Related papers  (2025-05-20T14:14:38Z)
• Cost-Efficient Continual Learning with Sufficient Exemplar Memory [55.77835198580209]
  Continual learning (CL) research typically assumes highly constrained exemplar memory resources. In this work, we investigate CL in a novel setting where exemplar memory is ample. Our method achieves state-of-the-art performance while reducing the computational cost to a quarter or third of existing methods.
  arXiv  Detail & Related papers  (2025-02-11T05:40:52Z)
• Information-Theoretic Dual Memory System for Continual Learning [8.803516528821161]
  We propose an innovative dual memory system called the Information-Theoretic Dual Memory System (ITDMS) This system comprises a fast memory buffer designed to retain temporary and novel samples, alongside a slow memory buffer dedicated to preserving critical and informative samples. Our methodology is rigorously assessed through a series of continual learning experiments, with empirical results underscoring the effectiveness of the proposed system.
  arXiv  Detail & Related papers  (2025-01-13T15:01:12Z)
• Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks [0.0]
  Reservoir computing greatly simplifies and speeds up reinforcement learning on memory tasks. In particular, these findings offer significant benefit to meta-learning that depends primarily on efficient and highly general memory systems.
  arXiv  Detail & Related papers  (2024-12-17T17:02:06Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• Noise-Robust Dense Retrieval via Contrastive Alignment Post Training [89.29256833403167]
  Contrastive Alignment POst Training (CAPOT) is a highly efficient finetuning method that improves model robustness without requiring index regeneration. CAPOT enables robust retrieval by freezing the document encoder while the query encoder learns to align noisy queries with their unaltered root. We evaluate CAPOT noisy variants of MSMARCO, Natural Questions, and Trivia QA passage retrieval, finding CAPOT has a similar impact as data augmentation with none of its overhead.
  arXiv  Detail & Related papers  (2023-04-06T22:16:53Z)
• Bridging the Training-Inference Gap for Dense Phrase Retrieval [104.4836127502683]
  Building dense retrievers requires a series of standard procedures, including training and validating neural models. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced. We propose an efficient way of validating dense retrievers using a small subset of the entire corpus.
  arXiv  Detail & Related papers  (2022-10-25T00:53:06Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• Improving Task-free Continual Learning by Distributionally Robust Memory Evolution [9.345559196495746]
  Task-free continual learning aims to learn a non-stationary data stream without explicit task definitions and not forget previous knowledge. Existing methods overlook the high uncertainty in the memory data distribution. We propose a principled memory evolution framework to dynamically evolve the memory data distribution.
  arXiv  Detail & Related papers  (2022-07-15T02:16:09Z)
• Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation [14.36005088171571]
  We propose memory-efficient reinforcement learning algorithms based on the deep Q-network algorithm. Our algorithms reduce forgetting and maintain high sample efficiency by consolidating knowledge from the target Q-network to the current Q-network.
  arXiv  Detail & Related papers  (2022-05-22T17:02:51Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning [19.260402028696916]
  Continual Learning (CL) aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. Previous studies exploit episodic memory (EM), which stores a subset of the past observed samples while learning from new non-i.i.d. data. We propose to exploit the abundant storage to preserve past experiences and alleviate the forgetting by allowing CL to efficiently migrate samples between memory and storage.
  arXiv  Detail & Related papers  (2021-10-14T11:27:45Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)
• Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval [15.238322226336232]
  We identify and address two underlying problems of dense retrievers. We use the recently proposed Condenser pre-training architecture, which learns to condense information into the dense vector through LM pre-training. We propose coCondenser, which adds an unsupervised corpus-level contrastive loss to warm up the passage embedding space.
  arXiv  Detail & Related papers  (2021-08-12T05:20:27Z)

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.