M
Mehdi Bahri
Researcher at Imperial College London
Publications - 14
Citations - 149
Mehdi Bahri is an academic researcher from Imperial College London. The author has contributed to research in topics: Deep learning & Graph (abstract data type). The author has an hindex of 5, co-authored 11 publications receiving 59 citations.
Papers
More filters
Proceedings ArticleDOI
Binary Graph Neural Networks
TL;DR: In this paper, a dynamic graph neural network (DGNN) was proposed to reduce the model size, memory footprint, and energy consumption by using k-NN search on binary vectors to speed up the construction of the dynamic graph.
Journal ArticleDOI
Robust Kronecker Component Analysis
TL;DR: This paper proposes a novel Kronecker-decomposable component analysis model, coined as Robust Kr onecker Component Analysis (RKCA), that has several appealing properties, including robustness to gross corruption; it can be used for low-rank modeling, and leverages separability to solve significantly smaller problems.
Proceedings ArticleDOI
Geometrically Principled Connections in Graph Neural Networks
TL;DR: It is argued geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning, and affine skip connections are introduced, a novel building block formed by combining a fully connected layer with any graph convolution operator.
Posted Content
Robust Kronecker Component Analysis
TL;DR: In this paper, a robust Kronecker-decomposable component analysis (RKCA) model is proposed for low-rank modeling, which combines ideas from sparse dictionary learning and robust component analysis.
Posted Content
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation.
Mehdi Bahri,Eimear O' Sullivan,Shunwang Gong,Feng Liu,Xiaoming Liu,Michael M. Bronstein,Stefanos Zafeiriou +6 more
TL;DR: Shape-My-Face (SMF), a powerful encoder-decoder architecture based on an improved point cloud encoder, a novel visual attention mechanism, graph convolutional decoders with skip connections, and a specialized mouth model that the authors smoothly integrate with the mesh convolutions are introduced.