18 citations · 34 across the 5 of their papers we have counts for
5 papers
ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learning
Zhenwei Dai, Vasileios Ioannidis, Soji Adeshina +3
What target labels are most effective for graph neural network (GNN) training? In some applications where GNNs excel-like drug design or fraud detection, labeling new instances is…
Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks
Zhenwei Dai, Chen Dun, Yuxin Tang +2
Federated learning enables many local devices to train a deep learning model jointly without sharing the local data. Currently, most of federated training schemes learns a global m…
Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix
Zhenwei Dai, Aditya Desai, Reinhard Heckel +1
Estimating and storing the covariance (or correlation) matrix of high-dimensional data is computationally challenging because both memory and computational requirements scale quadr…
Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier
Zhenwei Dai, Anshumali Shrivastava
Recent work suggests improving the performance of Bloom filter by incorporating a machine learning model as a binary classifier. However, such learned Bloom filter does not take fu…
Channel Normalization in Convolutional Neural Network avoids Vanishing Gradients
Zhenwei Dai, Reinhard Heckel
Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent o…