相关论文: Gradient Projection For Continual Parameter-Effici…

Domain generalization (DG) aims to avoid the performance degradation of the model when the distribution shift between the limited training data and unseen test data occurs. Recently, foundation models with enormous parameters have been…

Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the optimization space for new tasks to…

Fine-tuning large foundation models is essential for building expert models tailored to specialized tasks and domains, but fully updating billions of parameters is computationally prohibitive. Reducing the number of trainable parameters…

Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and…

Building upon the success of low-rank adapter (LoRA), low-rank gradient projection (LoRP) has emerged as a promising solution for memory-efficient fine-tuning. However, existing LoRP methods typically treat each row of the gradient matrix…

A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

Recent studies on transfer learning have shown that selectively fine-tuning a subset of layers or customizing different learning rates for each layer can greatly improve robustness to out-of-distribution (OOD) data and retain generalization…

Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field of Continual Learning. Specifically, these approaches propose…

Training deep neural networks is challenging. To accelerate training and enhance performance, we propose PadamP, a novel optimization algorithm. PadamP is derived by applying the adaptive estimation of the p-th power of the second-order…

Task-free online continual learning aims to alleviate catastrophic forgetting of the learner on a non-iid data stream. Experience Replay (ER) is a SOTA continual learning method, which is broadly used as the backbone algorithm for other…

Continual learning necessitates the continual adaptation of models to newly emerging tasks while minimizing the catastrophic forgetting of old ones. This is extremely challenging for large language models (LLMs) with vanilla full-parameter…

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is randomly initialized and data-agnostic, discarding potentially…

Catastrophic forgetting is one of the major challenges in continual learning. To address this issue, some existing methods put restrictive constraints on the optimization space of the new task for minimizing the interference to old tasks.…

Fine-tuning large language models (LLMs) for specialized domains often necessitates a trade-off between acquiring domain expertise and retaining general reasoning capabilities, a phenomenon known as catastrophic forgetting. Existing…

Parameter-Efficient Fine-Tuning (PEFT) and Retrieval-Augmented Generation (RAG) have become popular methods for adapting large language models while minimizing compute requirements. In this paper, we apply PEFT methods (P-tuning, Adapters,…

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks,…

We present a novel Parameter-Efficient Fine-Tuning (PEFT) method, dubbed as Adaptive Freezing of Low Rank Adaptation (AFLoRA). Specifically, for each pre-trained frozen weight tensor, we add a parallel path of trainable low-rank matrices,…