Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning

• URL: http://arxiv.org/abs/2608.30316v1
• Date: Mon, 31 Aug 2026 06:33:20 GMT
• Title: Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning
• Abstract summary: We argue that the core obstacle is the model's ambiguous boundary between known and unknown knowledge.<n>We propose KBK (Knowing Beyond the Known), a reinforced knowledge specification framework that explicitly models what is known or not to unify historical, current, and prospective learning.<n> Experiments on multiple benchmarks validate the effectiveness and robustness of KBK, which surpasses prior best methods by 2.7% in Avg. Acc on MS-COCO B0-C10 setting.
• Score: 37.885906679929796
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising from co-occurring and incomplete labels. We argue that the core obstacle is the model's ambiguous boundary between known and unknown knowledge, which undermines historical knowledge retention, complicates current task learning, and limits adaptability to future concepts. To address this, we propose KBK (Knowing Beyond the Known), a reinforced knowledge specification framework that explicitly models what is known or not to unify historical, current, and prospective learning. Specifically, to clarify known knowledge, we develop a hierarchical feature purification module that disentangles fine-grained class-specific features from global features, where high-level semantic abstraction is reinforced with low-level visual features. Additionally, an uncertainty-aware recall enhancement strategy suppresses unreliable predictions based on distribution priors, improving the quality of historical recall. For probing the unknown, KBK leverages semantic correlations to synthesize informative unknown features under co-occurring, preserving embedding space for future learning. Furthermore, to mitigate heterogeneous forgetting, we design a category-balanced gradient compensation loss that dynamically reweights gradient backpropagation according to forgetting speeds. Experiments on multiple benchmarks validate the effectiveness and robustness of KBK, which surpasses prior best methods by 2.7% in Avg. Acc on MS-COCO B0-C10 setting even without any replay buffers.

Related papers

• Test-Time Unlearning via Sparse Autoencoder [55.4290003355764]
  We propose ARIA, a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state.<n>ARIA improves the forget-retain trade-off over weight-based baselines across both a thinking model and an instruction model.
  arXiv  Detail & Related papers  (2026-09-14T18:58:09Z)
• Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion [27.526437626781597]
  We propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR) for large language models.<n>KUnBR identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy.<n>Experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance.
  arXiv  Detail & Related papers  (2025-11-11T14:12:43Z)
• BLUR: A Bi-Level Optimization Approach for LLM Unlearning [100.90394814817965]
  We argue that it is important to model the hierarchical structure of the unlearning problem.<n>We propose a novel algorithm, termed Bi-Level UnleaRning (textttBLUR), which delivers superior performance.
  arXiv  Detail & Related papers  (2025-06-09T19:23:05Z)
• Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning [51.0864247376786]
  We introduce a Knowledge Graph Enhanced Generative Multi-modal model (KG-GMM) that builds an evolving knowledge graph throughout the learning process.<n>During testing, we propose a Knowledge Graph Augmented Inference method that locates specific categories by analyzing relationships within the generated text.
  arXiv  Detail & Related papers  (2025-03-24T07:20:43Z)
• Specifying What You Know or Not for Multi-Label Class-Incremental Learning [26.607584252708868]
  We argue that the main challenge in multi-label class-incremental learning (MLCIL) lies in the model's inability to clearly distinguish between known and unknown knowledge.<n>This ambiguity hinders the model's ability to retain historical knowledge, master current classes, and prepare for future learning simultaneously.
  arXiv  Detail & Related papers  (2025-03-21T10:26:32Z)
• Towards Robust Incremental Learning under Ambiguous Supervision [22.9111210739047]
  We propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL)<n>IPLL aims to handle sequential fully-supervised learning problems where novel classes emerge from time to time.<n>We develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity.
  arXiv  Detail & Related papers  (2025-01-23T11:52:53Z)
• Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning [73.59672160329296]
  CKPD-FSCIL is a unified framework that unlocks the underutilized capacity of pretrained weights.<n>Our method consistently outperforms state-of-the-art approaches in both adaptability and knowledge retention.
  arXiv  Detail & Related papers  (2025-01-09T07:18:48Z)
• Few-Shot Class-Incremental Learning with Prior Knowledge [94.95569068211195]
  We propose Learning with Prior Knowledge (LwPK) to enhance the generalization ability of the pre-trained model. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-02T08:05:35Z)
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory [23.730424035141155]
  We present IDEC, which consists of a Dense Knowledge Distillation on all Aspects (DADA) and an Asymmetric Region-wise Contrastive Learning (ARCL) module. We demonstrate the effectiveness of our method on multiple CISS tasks by state-of-the-art performance, including Pascal VOC 2012, ADE20K and ISPRS datasets.
  arXiv  Detail & Related papers  (2023-09-27T05:38:31Z)
• Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations [22.289830907729705]
  Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one. Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
  arXiv  Detail & Related papers  (2022-11-10T05:29:43Z)
• Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning [133.39254981496146]
  Class-incremental learning (CIL) suffers from the notorious dilemma between learning newly added classes and preserving previously learned class knowledge. We propose to leverage "free" external unlabeled data querying in continual learning. We show queried unlabeled data can continue to benefit, and seamlessly extend CIL-QUD into its robustified versions.
  arXiv  Detail & Related papers  (2022-06-15T22:53:23Z)

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.