基于功能性LoRA的深度生成式持续学习：FunLoRA
Deep Generative Continual Learning using Functional LoRA: FunLoRA
AI总结：
针对深度生成模型增量训练的灾难性遗忘问题，提出仅用秩1矩阵、通过函数提升功能秩的FunLoRA条件机制，仅用当前任务数据训练即可避免遗忘，性能超越扩散模型SOTA且成本更低。
摘要：
深度生成模型在文本和视觉类应用中的应用正快速拓展，其持续适配能力具备巨大潜力且至关重要。然而，增量训练仍因灾难性遗忘现象极具挑战性，该现象导致神经网络难以有效整合新知识。一种常见策略是用生成模型自身的合成数据重新训练模型，以缓解遗忘问题。但这类方法存在两大主要局限：（i）持续增长的训练时间最终会变得难以处理；（ii）依赖合成数据不可避免会导致长期性能下降，因为合成样本缺乏真实训练数据的丰富性。本文中，我们为生成模型设计了一种基于低秩适配（LoRA）的新型、表达能力更强的条件机制，以缓解上述问题：该机制仅使用秩1矩阵，通过精心选择的函数从功能上提升其重参数化后的矩阵秩，被称为功能性LoRA：FunLoRA。借助这种动态条件机制，生成模型可确保避免灾难性遗忘，且仅需在当前任务的数据上进行训练。我们使用从头训练的基于流匹配的模型开展了大量实验，结果表明，我们提出的参数高效微调（PEFT）方法超越了此前基于扩散模型的最优结果，取得了更高的分类准确率，同时仅需占用一小部分内存成本和采样时间。
英文摘要：
Continual adaptation of deep generative models holds tremendous potential and critical importance, given their rapid and expanding usage in text and vision based applications. Incremental training, however, remains highly challenging due to catastrophic forgetting phenomenon, which makes it difficult for neural networks to effectively incorporate new knowledge. A common strategy consists in retraining the generative model on its own synthetic data in order to mitigate forgetting. Yet, such an approach faces two major limitations: (i) the continually increasing training time eventually becomes intractable, and (ii) reliance on synthetic data inevitably leads to long-term performance degradation, since synthetic samples lack the richness of real training data. In this paper, we attenuate these issues by designing a novel and more expressive conditioning mechanism for generative models based on low rank adaptation (LoRA), that exclusively employs rank 1 matrices, whose reparametrized matrix rank is functionally increased using carefully selected functions -- and dubbed functional LoRA: FunLoRA. Using this dynamic conditioning, the generative model is guaranteed to avoid catastrophic forgetting and needs only to be trained on data from the current task. Extensive experiments using flow-matching based models trained from scratch, showcase that our proposed parameter-efficient fine-tuning (PEFT) method surpasses prior state-of-the-art results based on diffusion models, reaching higher classification accuracy scores, while only requiring a fraction of the memory cost and sampling time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
