相关论文: Robust MAE-Driven NAS: From Mask Reconstruction to…

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation…

Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning. Since the discovery that original DARTS will inevitably converge to poor architectures, recent works alleviate this by either…

Neural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests. Despite various successful approaches proposed to solve…

Raman spectroscopy serves as a powerful and reliable tool for analyzing the chemical information of substances. The integration of Raman spectroscopy with deep learning methods enables rapid qualitative and quantitative analysis of…

Neural Architecture Search (NAS) is a collection of methods to craft the way neural networks are built. We apply this idea to Federated Learning (FL), wherein predefined neural network models are trained on the client/device data. This…

High-dimensional data, particularly in the form of high-order tensors, presents a major challenge in self-supervised learning. While MLP-based autoencoders (AE) are commonly employed, their dependence on flattening operations exacerbates…

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

Recent advancements in Neural Architecture Search(NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation without substantial…

Accurate imputation of missing laboratory values in electronic health records (EHRs) is critical to enable robust clinical predictions and reduce biases in AI systems in healthcare. Existing methods, such as XGBoost, softimpute, GAIN,…

Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the search costs of…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

State-of-the-art speaker verification models are based on deep learning techniques, which heavily depend on the handdesigned neural architectures from experts or engineers. We borrow the idea of neural architecture search(NAS) for the…

Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to adapt the given neural architecture to…

Medical image segmentation based on deep learning is often faced with the problems of insufficient datasets and long time-consuming labeling. In this paper, we introduce the self-supervised method MAE(Masked Autoencoders) into knee joint…

Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the knowledge from a given teacher model. Previous DaNAS methods…

Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of self-supervised pretraining strategies. However, existing…

Designing effective neural networks is fundamentally important in deep multimodal learning. Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to…