PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks

• URL: http://arxiv.org/abs/2403.11743v2
• Date: Thu, 18 Jul 2024 08:32:51 GMT
• Title: PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks
• Authors: Philip Matthias Winter, Maria Wimmer, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Gaia Romana De Paolis, Johannes Novotny, Sophia Ulonska, Katja Bühler,
• Abstract summary: This work addresses flexibility in deep learning by means of transductive reasoning. We propose PARMESAN, a scalable method which leverages a memory module for solving dense prediction tasks. Our method is compatible with commonly used architectures and canonically transfers to 1D, 2D, and 3D grid-based data.
• Score: 5.5127111704068374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training from scratch, rendering such approaches unflexible in practice. We argue that the notion of separating computation from memory by the means of transduction can act as a stepping stone for solving these issues. We therefore propose PARMESAN (parameter-free memory search and transduction), a scalable method which leverages a memory module for solving dense prediction tasks. At inference, hidden representations in memory are being searched to find corresponding patterns. In contrast to other methods that rely on continuous training of learnable parameters, PARMESAN learns via memory consolidation simply by modifying stored contents. Our method is compatible with commonly used architectures and canonically transfers to 1D, 2D, and 3D grid-based data. The capabilities of our approach are demonstrated at the complex task of continual learning. PARMESAN learns by 3-4 orders of magnitude faster than established baselines while being on par in terms of predictive performance, hardware-efficiency, and knowledge retention.

Related papers

• Mitigating Memorization In Language Models [37.899013074095336]
  Language models (LMs) can "memorize" information, encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. We introduce TinyMem, a suite of small, computationally-efficient LMs for the rapid development and evaluation of memorization-mitigation methods. We show, in particular, that our proposed unlearning method BalancedSubnet outperforms other mitigation methods at removing memorized information while preserving performance on target tasks.
  arXiv  Detail & Related papers  (2024-10-03T02:53:51Z)
• 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)
• Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
  We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
  arXiv  Detail & Related papers  (2024-07-09T15:45:04Z)
• Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory [66.88278207591294]
  We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer manipulation techniques to mimic human and computer symbol processing abilities.
  arXiv  Detail & Related papers  (2024-04-18T03:03:46Z)
• Think Before You Act: Decision Transformers with Working Memory [44.18926449252084]
  Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. We propose a working memory module to store, blend, and retrieve information for different downstream tasks.
  arXiv  Detail & Related papers  (2023-05-24T01:20:22Z)
• RET-LLM: Towards a General Read-Write Memory for Large Language Models [53.288356721954514]
  RET-LLM is a novel framework that equips large language models with a general write-read memory unit. Inspired by Davidsonian semantics theory, we extract and save knowledge in the form of triplets. Our framework exhibits robust performance in handling temporal-based question answering tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:53:38Z)
• Saliency-Augmented Memory Completion for Continual Learning [8.243137410556495]
  How to forget is a problem continual learning must address. Our paper proposes a new saliency-augmented memory completion framework for continual learning.
  arXiv  Detail & Related papers  (2022-12-26T18:06:39Z)
• 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)
• Learning to Prompt for Continual Learning [34.609384246149325]
  This work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions. The objective is to optimize prompts to instruct the model prediction and explicitly manage task-invariant and task-specific knowledge while maintaining model plasticity.
  arXiv  Detail & Related papers  (2021-12-16T06:17:07Z)
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers [38.035925090154024]
  A neural semantic learns tasks sequentially without accessing full training data from previous tasks. We propose TotalRecall, a continual learning method designed for neural semantics from two aspects. We demonstrate that a neural semantic trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch.
  arXiv  Detail & Related papers  (2021-09-11T04:33:28Z)
• Learning to Learn Variational Semantic Memory [132.39737669936125]
  We introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The semantic memory is grown from scratch and gradually consolidated by absorbing information from tasks it experiences. We formulate memory recall as the variational inference of a latent memory variable from addressed contents.
  arXiv  Detail & Related papers  (2020-10-20T15:05:26Z)

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.