CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

• URL: http://arxiv.org/abs/2503.04655v1
• Date: Thu, 06 Mar 2025 17:49:13 GMT
• Title: CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models
• Authors: Shengzhuang Chen, Yikai Liao, Xiaoxiao Sun, Kede Ma, Ying Wei,
• Abstract summary: We describe CL on dynamic benchmarks (CLDyB), a general computational framework for evaluating CL methods reliably.<n>We first conduct a joint evaluation of multiple state-of-the-art CL methods, leading to a set of commonly challenging and generalizable task sequences.<n>We then conduct separate evaluations of individual CL methods using CLDyB, discovering their respective strengths and weaknesses.
• Score: 22.032582616029707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advent of the foundation model era has sparked significant research interest in leveraging pre-trained representations for continual learning (CL), yielding a series of top-performing CL methods on standard evaluation benchmarks. Nonetheless, there are growing concerns regarding potential data contamination during the pre-training stage. Furthermore, standard evaluation benchmarks, which are typically static, fail to capture the complexities of real-world CL scenarios, resulting in saturated performance. To address these issues, we describe CL on dynamic benchmarks (CLDyB), a general computational framework based on Markov decision processes for evaluating CL methods reliably. CLDyB dynamically identifies inherently difficult and algorithm-dependent tasks for the given CL methods, and determines challenging task orders using Monte Carlo tree search. Leveraging CLDyB, we first conduct a joint evaluation of multiple state-of-the-art CL methods, leading to a set of commonly challenging and generalizable task sequences where existing CL methods tend to perform poorly. We then conduct separate evaluations of individual CL methods using CLDyB, discovering their respective strengths and weaknesses. The source code and generated task sequences are publicly accessible at https://github.com/szc12153/CLDyB.

Related papers

• Continual Learning Should Move Beyond Incremental Classification [51.23416308775444]
  Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. Here, we argue that maintaining such a focus limits both theoretical development and practical applicability of CL methods. We identify three fundamental challenges: (C1) the nature of continuity in learning problems, (C2) the choice of appropriate spaces and metrics for measuring similarity, and (C3) the role of learning objectives beyond classification.
  arXiv  Detail & Related papers  (2025-02-17T15:40:13Z)
• Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning [42.4526628515253]
  Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. We study the robustness and similarity of the most common scoring functions for sample difficulty estimation. We find that the robustness of scoring functions across random seeds positively correlates with CL performance.
  arXiv  Detail & Related papers  (2024-11-01T18:55:31Z)
• CLoG: Benchmarking Continual Learning of Image Generation Models [29.337710309698515]
  This paper advocates for shifting the research focus from classification-based CL to CLoG. We adapt three types of existing CL methodologies, replay-based, regularization-based, and parameter-isolation-based methods to generative tasks. Our benchmarks and results yield intriguing insights that can be valuable for developing future CLoG methods.
  arXiv  Detail & Related papers  (2024-06-07T02:12:29Z)
• Hyperparameters in Continual Learning: A Reality Check [53.30082523545212]
  Continual learning (CL) aims to train a model on a sequence of tasks while balancing the trade-off between plasticity (learning new tasks) and stability (retaining prior knowledge) The dominantly adopted conventional evaluation protocol for CL algorithms selects the best hyper parameters in a given scenario and then evaluates the algorithms in the same scenario. This protocol has significant shortcomings: it overestimates the CL capacity of algorithms and relies on unrealistic hyper parameter tuning. We argue that the evaluation of CL algorithms should focus on assessing the generalizability of their CL capacity to unseen scenarios.
  arXiv  Detail & Related papers  (2024-03-14T03:13:01Z)
• Density Distribution-based Learning Framework for Addressing Online Continual Learning Challenges [4.715630709185073]
  We introduce a density distribution-based learning framework for online Continual Learning. Our framework achieves superior average accuracy and time-space efficiency. Our method outperforms popular CL approaches by a significant margin.
  arXiv  Detail & Related papers  (2023-11-22T09:21:28Z)
• From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning [9.104068727716294]
  Continual learning (CL) is one of the most promising trends in machine learning research. We introduce two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity.
  arXiv  Detail & Related papers  (2023-03-16T18:11:19Z)
• Real-Time Evaluation in Online Continual Learning: A New Hope [104.53052316526546]
  We evaluate current Continual Learning (CL) methods with respect to their computational costs. A simple baseline outperforms state-of-the-art CL methods under this evaluation. This surprisingly suggests that the majority of existing CL literature is tailored to a specific class of streams that is not practical.
  arXiv  Detail & Related papers  (2023-02-02T12:21:10Z)
• Do Pre-trained Models Benefit Equally in Continual Learning? [25.959813589169176]
  Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmarks, these algorithms show dramatic performance drops in real-world scenarios. This paper advocates the systematic introduction of pre-training to CL.
  arXiv  Detail & Related papers  (2022-10-27T18:03:37Z)
• A Study of Continual Learning Methods for Q-Learning [78.6363825307044]
  We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario. Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay"
  arXiv  Detail & Related papers  (2022-06-08T14:51:52Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• The CLEAR Benchmark: Continual LEArning on Real-World Imagery [77.98377088698984]
  Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. We introduce CLEAR, the first continual image classification benchmark dataset with a natural temporal evolution of visual concepts. We find that a simple unsupervised pre-training step can already boost state-of-the-art CL algorithms.
  arXiv  Detail & Related papers  (2022-01-17T09:09:09Z)

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.