4 papers
Macformer: Transformer with Random Maclaurin Feature Attention
Yuhan Guo, Lizhong Ding, Ye Yuan +1
Random feature attention (RFA) adopts random fourier feature (RFF) methods to approximate the softmax function, resulting in a linear time and space attention mechanism that enable…
Learning to Generate Parameters of ConvNets for Unseen Image Data
Shiye Wang, Kaituo Feng, Changsheng Li +2
Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn networ…
Influence Maximization in Hypergraphs by Stratified Sampling for Efficient Generation of Reverse Reachable Sets
Lingling Zhang, Hong Jiang, Ye Yuan +1
Given a hypergraph, influence maximization (IM) is to discover a seed set containing vertices that have the maximal influence. Although the existing vertex-based IM algorithms…
Robust Knowledge Adaptation for Dynamic Graph Neural Networks
Hanjie Li, Changsheng Li, Kaituo Feng +3
Graph structured data often possess dynamic characters in nature. Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling graph da…