Forget Less by Learning Together through Concept Consolidation

• URL: http://arxiv.org/abs/2601.01963v1
• Date: Mon, 05 Jan 2026 10:14:16 GMT
• Title: Forget Less by Learning Together through Concept Consolidation
• Authors: Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini Ratha, Venu Govindaraju,
• Abstract summary: Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes.<n>Existing CDMs suffer from catastrophic forgetting when continuously learning new concepts.<n>We propose Forget Less by Learning Together (FL2T) that enables concurrent and order-agnostic concept learning.
• Score: 6.121904567143191
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most prior works attempt to mitigate this issue under the sequential learning setting with a fixed order of concept inflow and neglect inter-concept interactions. In this paper, we propose a novel framework - Forget Less by Learning Together (FL2T) - that enables concurrent and order-agnostic concept learning while addressing catastrophic forgetting. Specifically, we introduce a set-invariant inter-concept learning module where proxies guide feature selection across concepts, facilitating improved knowledge retention and transfer. By leveraging inter-concept guidance, our approach preserves old concepts while efficiently incorporating new ones. Extensive experiments, across three datasets, demonstrates that our method significantly improves concept retention and mitigates catastrophic forgetting, highlighting the effectiveness of inter-concept catalytic behavior in incremental concept learning of ten tasks with at least 2% gain on average CLIP Image Alignment scores.

Related papers

• Forget Less by Learning from Parents Through Hierarchical Relationships [11.149407640112239]
  We present Forget Less by Learning from Parents (FLLP), a novel framework that introduces a parent-child inter-concept learning mechanism.<n>FLLP preserves prior knowledge and supports continual integration of new concepts.<n>We validate FLLP on three public datasets and one synthetic benchmark, showing consistent improvements in both robustness and generalization.
  arXiv  Detail & Related papers  (2026-01-05T08:35:36Z)
• ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement [15.939409734710198]
  We present ConceptSplit, a novel framework to split individual concepts through training and inference.<n>Our framework comprises two key components. First, we introduce Token-wise Value Adaptation (ToVA), a merging-free training method.<n>Second, we propose Latent Optimization for Disentangled Attention (LODA), which alleviates attention entanglement during inference.
  arXiv  Detail & Related papers  (2025-10-06T10:22:46Z)
• CURE: Controlled Unlearning for Robust Embeddings - Mitigating Conceptual Shortcuts in Pre-Trained Language Models [23.898244353656352]
  We introduce CURE, a framework that systematically disentangles and suppresses conceptual shortcuts.<n>CURE achieves an absolute improvement of +10 points in F1 score on IMDB and +2 points on Yelp.
  arXiv  Detail & Related papers  (2025-09-05T16:47:22Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Language Guided Concept Bottleneck Models for Interpretable Continual Learning [62.09201360376577]
  Continual learning aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information.<n>Most existing CL methods focus primarily on preserving learned knowledge to improve model performance.<n>We introduce a novel framework that integrates language-guided Concept Bottleneck Models to address both challenges.
  arXiv  Detail & Related papers  (2025-03-30T02:41:55Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation [3.7816957214446103]
  ConceptGuard is a comprehensive approach that combines shift embedding, concept-binding prompts and memory preservation regularization.<n>We show that our approach outperforms all the baseline methods consistently and significantly in both quantitative and qualitative analyses.
  arXiv  Detail & Related papers  (2025-03-13T13:39:24Z)
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? [91.49559116493414]
  We propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM) It can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Experiments validate that our CIDM surpasses existing custom diffusion models.
  arXiv  Detail & Related papers  (2024-10-23T06:47:29Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Mnemonics Training: Multi-Class Incremental Learning without Forgetting [131.1065577648532]
  Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. This paper proposes a novel and automatic framework we call mnemonics, where we parameterize exemplars and make them optimizable in an end-to-end manner. We conduct extensive experiments on three MCIL benchmarks, CIFAR-100, ImageNet-Subset and ImageNet, and show that using mnemonics exemplars can surpass the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-02-24T12:55:25Z)

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.