English
Related papers

Related papers: Generating Classification Weights with GNN Denoisi…

200 papers

Auto-encoder is a special kind of neural network based on reconstruction. De-noising auto-encoder (DAE) is an improved auto-encoder which is robust to the input by corrupting the original data first and then reconstructing the original…

Machine Learning · Computer Science 2014-04-24 Fu-qiang Chen , Yan Wu , Guo-dong Zhao , Jun-ming Zhang , Ming Zhu , Jing Bai

The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the…

Machine Learning · Computer Science 2021-06-15 Thomas Elsken , Benedikt Staffler , Jan Hendrik Metzen , Frank Hutter

Meta-learning has been widely used for implementing few-shot learning and fast model adaptation. One kind of meta-learning methods attempt to learn how to control the gradient descent process in order to make the gradient-based learning…

Machine Learning · Computer Science 2019-11-20 Jialin Liu , Fei Chao , Longzhi Yang , Chih-Min Lin , Qiang Shen

Graph neural networks (GNNs) face significant challenges with class imbalance, leading to biased inference results. To address this issue in heterogeneous graphs, we propose a novel framework that combines Graph Neural Network (GNN) and…

Machine Learning · Computer Science 2024-11-26 Hung-Chun Hsu , Bo-Jun Wu , Ming-Yi Hong , Che Lin , Chih-Yu Wang

Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet. However, such models require many thousands of gradient-based weight updates and unique…

Neural and Evolutionary Computing · Computer Science 2018-03-01 Scott Reed , Yutian Chen , Thomas Paine , Aäron van den Oord , S. M. Ali Eslami , Danilo Rezende , Oriol Vinyals , Nando de Freitas

We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on…

Machine Learning · Computer Science 2025-12-15 Haiyang Yu , Meng-Chieh Lee , Xiang song , Qi Zhu , Christos Faloutsos

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…

Information Retrieval · Computer Science 2019-11-22 Shumin Deng , Ningyu Zhang , Zhanlin Sun , Jiaoyan Chen , Huajun Chen

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…

Machine Learning · Computer Science 2018-07-27 Tailin Wu , John Peurifoy , Isaac L. Chuang , Max Tegmark

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category,…

Machine Learning · Computer Science 2019-08-28 Duo Wang , Yu Cheng , Mo Yu , Xiaoxiao Guo , Tao Zhang

Prototypical network for Few shot learning tries to learn an embedding function in the encoder that embeds images with similar features close to one another in the embedding space. However, in this process, the support set samples for a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Manas Gogoi , Sambhavi Tiwari , Shekhar Verma

Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest. Though several approaches have been proposed, most existing few-shot learning (FSL) models assume that base and novel…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Yuan-Chia Cheng , Ci-Siang Lin , Fu-En Yang , Yu-Chiang Frank Wang

The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new…

Computation and Language · Computer Science 2020-10-13 Nithin Holla , Pushkar Mishra , Helen Yannakoudakis , Ekaterina Shutova

Existing graph-network-based few-shot learning methods obtain similarity between nodes through a convolution neural network (CNN). However, the CNN is designed for image data with spatial information rather than vector form node feature. In…

Computer Vision and Pattern Recognition · Computer Science 2021-01-28 Peixiao Zheng , Xin Guo , Lin Qi

Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-22 Yuma Koizumi , Shoichiro Saito , Masataka Yamaguchi , Shin Murata , Noboru Harada

This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both…

Machine Learning · Computer Science 2023-12-01 Kai Li , Jingjing Zheng , Xin Yuan , Wei Ni , Ozgur B. Akan , H. Vincent Poor

Few-shot learning can find the latent structure information between the prior knowledge and the queried data by the similarity metric of meta-learning to construct the discriminative model for recognizing the new categories with the rare…

Computer Vision and Pattern Recognition · Computer Science 2020-06-01 Guangfeng Lin , Ying Yang , Yindi Fan , Xiaobing Kang , Kaiyang Liao , Fan Zhao

Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. The state-of-the-art solutions are built by deep learning, which focuses on designing increasingly complex deep backbones.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-31 Na Chen , Xianming Kuang , Feiyu Liu , Kehao Wang , Qun Chen

The problem of end-to-end learning of a communication system using an autoencoder -- consisting of an encoder, channel, and decoder modeled using neural networks -- has recently been shown to be an effective approach. A challenge faced in…

Machine Learning · Computer Science 2023-03-07 Jayaram Raghuram , Yijing Zeng , Dolores García Martí , Rafael Ruiz Ortiz , Somesh Jha , Joerg Widmer , Suman Banerjee

A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training…

Machine Learning · Computer Science 2019-04-12 Minseop Park , Jungtaek Kim , Saehoon Kim , Yanbin Liu , Seungjin Choi

In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples. Recent approaches broadly solve this problem by…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Wei-Hong Li , Xialei Liu , Hakan Bilen