Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective

• URL: http://arxiv.org/abs/2206.08101v3
• Date: Tue, 25 Jun 2024 17:49:35 GMT
• Title: Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective
• Authors: Sungmin Cha, Jihwan Kwak, Dongsub Shim, Hyunwoo Kim, Moontae Lee, Honglak Lee, Taesup Moon,
• Abstract summary: Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data. We experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning.
• Score: 67.45111837188685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average test accuracy across all classes learned so far -- however, we argue that solely focusing on maximizing the test accuracy may not necessarily lead to developing a CIL algorithm that also continually learns and updates the representations, which may be transferred to the downstream tasks. To that end, we experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning and propose new analysis methods. Our experiments show that most state-of-the-art algorithms prioritize high stability and do not significantly change the learned representation, and sometimes even learn a representation of lower quality than a naive baseline. However, we observe that these algorithms can still achieve high test accuracy because they enable a model to learn a classifier that closely resembles an estimated linear classifier trained for linear probing. Furthermore, the base model learned in the first task, which involves single-task learning, exhibits varying levels of representation quality across different algorithms, and this variance impacts the final performance of CIL algorithms. Therefore, we suggest that the representation-level evaluation should be considered as an additional recipe for more diverse evaluation for CIL algorithms.

Related papers

• Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms [88.93372675846123]
  We propose a task-agnostic evaluation framework Camilla for evaluating machine learning algorithms. We use cognitive diagnosis assumptions and neural networks to learn the complex interactions among algorithms, samples and the skills of each sample. In our experiments, Camilla outperforms state-of-the-art baselines on the metric reliability, rank consistency and rank stability.
  arXiv  Detail & Related papers  (2023-07-14T03:15:56Z)
• NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage [3.4806267677524896]
  We propose a novel active learning strategy, neural tangent kernel clustering-pseudo-labels (NTKCPL) It estimates empirical risk based on pseudo-labels and the model prediction with NTK approximation. We validate our method on five datasets, empirically demonstrating that it outperforms the baseline methods in most cases.
  arXiv  Detail & Related papers  (2023-06-07T01:43:47Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning [29.80680408934347]
  We propose an alternative framework to incremental learning where we continually fine-tune the model from a pre-trained representation. Our method takes advantage of linearization technique of a pre-trained neural network for simple and effective continual learning. We show that our method can be applied to general continual learning settings, we evaluate our method in data-incremental, task-incremental, and class-incremental learning problems.
  arXiv  Detail & Related papers  (2022-08-17T06:58:14Z)
• Meta-free representation learning for few-shot learning via stochastic weight averaging [13.6555672824229]
  Recent studies on few-shot classification using transfer learning pose challenges to the effectiveness and efficiency of episodic meta-learning algorithms. We propose a new transfer learning method to obtain accurate and reliable models for few-shot regression and classification.
  arXiv  Detail & Related papers  (2022-04-26T17:36:34Z)
• Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
  arXiv  Detail & Related papers  (2021-04-07T10:54:51Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View [82.80085730891126]
  We provide the first modernally precise analysis of linear multiclass classification. Our analysis reveals that the classification accuracy is highly distribution-dependent. The insights gained may pave the way for a precise understanding of other classification algorithms.
  arXiv  Detail & Related papers  (2020-11-16T05:17:29Z)
• Uncovering Coresets for Classification With Multi-Objective Evolutionary Algorithms [0.8057006406834467]
  A coreset is a subset of the training set, using which a machine learning algorithm obtains performances similar to what it would deliver if trained over the whole original data. A novel approach is presented: candidate corsets are iteratively optimized, adding and removing samples. A multi-objective evolutionary algorithm is used to minimize simultaneously the number of points in the set and the classification error.
  arXiv  Detail & Related papers  (2020-02-20T09:59:56Z)

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.