相关论文: Class-Proportional Coreset Selection for Difficult…

In the era of data-centric AI, the ability to curate high-quality training data is as crucial as model design. Coresets offer a principled approach to data reduction, enabling efficient learning on large datasets through importance…

Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…

Image clustering is one of the crucial techniques in multimedia analytics and knowledge discovery. Recently, the Deep clustering method (DC), characterized by its ability to perform feature learning and cluster assignment jointly, surpasses…

A wide range of optimization problems arising in machine learning can be solved by gradient descent algorithms, and a central question in this area is how to efficiently compress a large-scale dataset so as to reduce the computational…

Similarity-based clustering methods separate data into clusters according to the pairwise similarity between the data, and the pairwise similarity is crucial for their performance. In this paper, we propose {\em Clustering by Discriminative…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Tabular anomaly detection under the one-class classification setting poses a significant challenge, as it involves accurately conceptualizing "normal" derived exclusively from a single category to discern anomalies from normal data…

Dataset pruning has been widely studied for 2D images to remove redundancy and accelerate training, while particular pruning methods for 3D data remain largely unexplored. In this work, we study dataset pruning for 3D data, where its…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

Instruction tuning has achieved unprecedented success in NLP, turning large language models into versatile chatbots. However, the increasing variety and volume of instruction datasets demand significant computational resources. To address…

Few-shot learning aims to learn to generalize a classifier to novel classes with limited labeled data. Transductive inference that utilizes unlabeled test set to deal with low-data problem has been employed for few-shot learning in recent…

Deep learning models require an enormous amount of data for training. However, recently there is a shift in machine learning from model-centric to data-centric approaches. In data-centric approaches, the focus is to refine and improve the…

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

We give relative error coresets for training linear classifiers with a broad class of loss functions, including the logistic loss and hinge loss. Our construction achieves $(1\pm \epsilon)$ relative error with $\tilde O(d \cdot…

Recent advances in deep learning have resulted in great successes in various applications. Although semi-supervised or unsupervised learning methods have been widely investigated, the performance of deep neural networks highly depends on…

Channel pruning has received ever-increasing focus on network compression. In particular, class-discrimination based channel pruning has made major headway, as it fits seamlessly with the classification objective of CNNs and provides good…

We propose Cluster Pruning (CUP) for compressing and accelerating deep neural networks. Our approach prunes similar filters by clustering them based on features derived from both the incoming and outgoing weight connections. With CUP, we…

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…