The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?

• URL: http://arxiv.org/abs/2509.22580v1
• Date: Fri, 26 Sep 2025 17:00:15 GMT
• Title: The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
• Authors: Guannan Lai, Da-Wei Zhou, Xin Yang, Han-Jia Ye,
• Abstract summary: Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones.<n>We argue that a robust CIL evaluation protocol should accurately characterize and estimate the entire performance distribution.<n>We propose EDGE, an evaluation protocol that adaptively identifies and samples extreme class sequences using inter-task similarity.
• Score: 48.83567710215299
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in which classes arrive is diverse and unpredictable, and model performance can vary substantially across different sequences. Yet mainstream evaluation protocols calculate mean and variance from only a small set of randomly sampled sequences. Our theoretical analysis and empirical results demonstrate that this sampling strategy fails to capture the full performance range, resulting in biased mean estimates and a severe underestimation of the true variance in the performance distribution. We therefore contend that a robust CIL evaluation protocol should accurately characterize and estimate the entire performance distribution. To this end, we introduce the concept of extreme sequences and provide theoretical justification for their crucial role in the reliable evaluation of CIL. Moreover, we observe a consistent positive correlation between inter-task similarity and model performance, a relation that can be leveraged to guide the search for extreme sequences. Building on these insights, we propose EDGE (Extreme case-based Distribution and Generalization Evaluation), an evaluation protocol that adaptively identifies and samples extreme class sequences using inter-task similarity, offering a closer approximation of the ground-truth performance distribution. Extensive experiments demonstrate that EDGE effectively captures performance extremes and yields more accurate estimates of distributional boundaries, providing actionable insights for model selection and robustness checking. Our code is available at https://github.com/AIGNLAI/EDGE.

Related papers

• Toward Reliable Machine Unlearning: Theory, Algorithms, and Evaluation [1.7767466724342065]
  We introduce Adrial Machine UNlearning (AMUN), which surpasses prior state-of-the-art methods for image classification based on SOTA MIA scores.<n>We show that existing methods fail in replicating a retrained model's behavior by introducing a nearest-neighbor membership inference attack (MIA-NN)<n>We then propose a fine-tuning objective that mitigates this leakage by approximating, for forget-class inputs, the distribution over remaining classes that a model retrained from scratch would produce.
  arXiv  Detail & Related papers  (2025-12-07T20:57:25Z)
• Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation [19.145735532822012]
  We show that the canonical randomized split of a test set in conventional evaluation leaves the test set dominated by samples with high similarity to the training set.<n>We propose a framework of similarity aware evaluation in which a novel split methodology is proposed to adapt to any desired distribution.<n>Results demonstrate that the proposed split methodology can significantly better fit desired distributions and guide the development of models.
  arXiv  Detail & Related papers  (2025-04-13T08:30:57Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Boosted Control Functions: Distribution generalization and invariance in confounded models [10.503777692702952]
  We introduce a strong notion of invariance that allows for distribution generalization even in the presence of nonlinear, non-identifiable structural functions.<n>We propose the ControlTwicing algorithm to estimate the Boosted Control Function (BCF) using flexible machine-learning techniques.
  arXiv  Detail & Related papers  (2023-10-09T15:43:46Z)
• Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization [89.73665256847858]
  We show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of-distribution performance on variants of CIFAR-10 & ImageNet. We also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS.
  arXiv  Detail & Related papers  (2021-07-09T19:48:23Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• Modeling Score Distributions and Continuous Covariates: A Bayesian Approach [8.772459063453285]
  We develop a generative model of the match and non-match score distributions over continuous covariates. We use mixture models to capture arbitrary distributions and local basis functions. Three experiments demonstrate the accuracy and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-09-21T02:41:20Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.