133 citations · 147 across the 11 of their papers we have counts for
11 papers
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
Zhihao Shi, Jie Wang, Fanghua Lu +5
Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important d…
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
Jie Wang, Zhihao Shi, Xize Liang +5
Subgraph-wise sampling -- a promising class of mini-batch training techniques for graph neural networks (GNNs -- is critical for real-world applications. During the message passing…
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
Jie Wang, Rui Yang, Zijie Geng +7
Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely u…
LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
Zhihao Shi, Xize Liang, Jie Wang
The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the we…
Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Jie Wang, Zhanqiu Zhang, Zhihao Shi +3
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing s…
Video Frame Interpolation Transformer
Zhihao Shi, Xiangyu Xu, Xiaohong Liu +2
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights…
Towards a Unified Approach to Single Image Deraining and Dehazing
Xiaohong Liu, Yongrui Ma, Zhihao Shi +2
We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuo…
GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing
Xiaohong Liu, Zhihao Shi, Zijun Wu +1
We propose an enhanced multi-scale network, dubbed GridDehazeNet+, for single image dehazing. The proposed dehazing method does not rely on the Atmosphere Scattering Model (ASM), a…
Learning for Unconstrained Space-Time Video Super-Resolution
Zhihao Shi, Xiaohong Liu, Chengqi Li +4
Recent years have seen considerable research activities devoted to video enhancement that simultaneously increases temporal frame rate and spatial resolution. However, the existing…
Video Frame Interpolation via Generalized Deformable Convolution
Zhihao Shi, Xiaohong Liu, Kangdi Shi +2
Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies. The existing deep-learning-based…
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
Xiaohong Liu, Yongrui Ma, Zhihao Shi +1
We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing,…