Cold Start Streaming Learning for Deep Networks

• URL: http://arxiv.org/abs/2211.04624v1
• Date: Wed, 9 Nov 2022 00:53:19 GMT
• Title: Cold Start Streaming Learning for Deep Networks
• Abstract summary: Cold Start Streaming Learning (CSSL) is a simple, end-to-end approach for streaming learning with deep networks. In experiments, we find that CSSL outperforms existing baselines for streaming learning.
• Score: 13.452510519858995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to dynamically adapt neural networks to newly-available data without performance deterioration would revolutionize deep learning applications. Streaming learning (i.e., learning from one data example at a time) has the potential to enable such real-time adaptation, but current approaches i) freeze a majority of network parameters during streaming and ii) are dependent upon offline, base initialization procedures over large subsets of data, which damages performance and limits applicability. To mitigate these shortcomings, we propose Cold Start Streaming Learning (CSSL), a simple, end-to-end approach for streaming learning with deep networks that uses a combination of replay and data augmentation to avoid catastrophic forgetting. Because CSSL updates all model parameters during streaming, the algorithm is capable of beginning streaming from a random initialization, making base initialization optional. Going further, the algorithm's simplicity allows theoretical convergence guarantees to be derived using analysis of the Neural Tangent Random Feature (NTRF). In experiments, we find that CSSL outperforms existing baselines for streaming learning in experiments on CIFAR100, ImageNet, and Core50 datasets. Additionally, we propose a novel multi-task streaming learning setting and show that CSSL performs favorably in this domain. Put simply, CSSL performs well and demonstrates that the complicated, multi-step training pipelines adopted by most streaming methodologies can be replaced with a simple, end-to-end learning approach without sacrificing performance.

Related papers

• PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning [17.230781041043823]
  We propose a novel prompt-based method for online continual learning (OCL) that includes 4 main components.<n>Our proposed method achieves significantly higher performance than the current SOTAs in CIFAR100, ImageNet-R, ImageNet-A, and CUB dataset.
  arXiv  Detail & Related papers  (2025-07-16T15:04:46Z)
• Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study [35.60356938705585]
  Real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge.<n>We propose a simple-yet-effective method, Simple Graph Continual Learning (SimGCL), that surpasses the previous state-of-the-art GNN-based baseline by around 20%.
  arXiv  Detail & Related papers  (2025-05-24T13:43:29Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Streaming Deep Reinforcement Learning Finally Works [6.106447284305318]
  Streaming learning is ideal for resource-limited, communication-constrained, and privacy-sensitive applications. In deep RL, learners almost always use batch updates and replay buffers, making them computationally expensive and incompatible with streaming learning. This paper introduces the stream-x algorithms, the first class of deep RL algorithms to overcome stream barrier for both prediction and control and match sample efficiency of batch RL.
  arXiv  Detail & Related papers  (2024-10-18T17:00:29Z)
• A Unified Framework for Neural Computation and Learning Over Time [56.44910327178975]
  Hamiltonian Learning is a novel unified framework for learning with neural networks "over time" It is based on differential equations that: (i) can be integrated without the need of external software solvers; (ii) generalize the well-established notion of gradient-based learning in feed-forward and recurrent networks; (iii) open to novel perspectives.
  arXiv  Detail & Related papers  (2024-09-18T14:57:13Z)
• Simplifying Deep Temporal Difference Learning [3.458933902627673]
  We investigate whether it is possible to accelerate and simplify TD training while maintaining its stability. Our key theoretical result demonstrates for the first time that regularisation techniques such as LayerNorm can yield provably convergent TD algorithms. Motivated by these findings, we propose PQN, our simplified deep online Q-Learning algorithm.
  arXiv  Detail & Related papers  (2024-07-05T18:49:07Z)
• Streaming Active Learning with Deep Neural Networks [44.50018541065145]
  We propose VeSSAL, a new algorithm for batch active learning with deep neural networks in streaming settings. VeSSAL samples groups of points to query for labels at the moment they are encountered. We expand the applicability of deep neural networks to realistic active learning scenarios.
  arXiv  Detail & Related papers  (2023-03-05T00:57:28Z)
• Slimmable Networks for Contrastive Self-supervised Learning [69.9454691873866]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Boosting Federated Learning in Resource-Constrained Networks [1.7010199949406575]
  Federated learning (FL) enables a set of client devices to collaboratively train a model without sharing raw data. We propose GeL, the guess and learn algorithm. We show that GeL can boost empirical convergence by up to 40% in resource-constrained networks.
  arXiv  Detail & Related papers  (2021-10-21T21:23:04Z)
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment [55.91291559442884]
  This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. We propose to build the notion of continual learning into the modeling process of learning wireless systems. Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2020-11-16T08:24:34Z)
• Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks [84.2155885234293]
  We first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC. To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC.
  arXiv  Detail & Related papers  (2020-02-22T14:38:11Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

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.