Related papers: SliceFine: The Universal Winning-Slice Hypothesis …

Fine-tuning large language models (LLMs) on downstream tasks requires substantial computational resources. Selective PEFT, a class of parameter-efficient fine-tuning (PEFT) methodologies, aims to mitigate these computational challenges by…

We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task. This method is inspired by interpretability methods designed to automatically find subnetworks…

Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of…

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully…

Network pruning techniques, including weight pruning and filter pruning, reveal that most state-of-the-art neural networks can be accelerated without a significant performance drop. This work focuses on filter pruning which enables…

Recently, the paradigm of pre-training and fine-tuning graph neural networks has been intensively studied and applied in a wide range of graph mining tasks. Its success is generally attributed to the structural consistency between…

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for. In this work, a principled approach to choosing the learning rate is proposed for shallow feedforward neural…

Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sacrificing performance and becoming the de-facto learning…

Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a…

The emergence of foundation models, such as the Segment Anything Model (SAM), has sparked interest in Parameter-Efficient Fine-Tuning (PEFT) methods that tailor these large models to application domains outside their training data. However,…

Parameter-efficient transfer learning (PETL) based on large-scale pre-trained foundation models has achieved great success in various downstream applications. Existing tuning methods, such as prompt, prefix, and adapter, perform…

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,…

Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and under what…

We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a…

As graphs grow larger, full-batch GNN training becomes hard for single GPU memory. Therefore, to enhance the scalability of GNN training, some studies have proposed sampling-based mini-batch training and distributed graph learning. However,…

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy…