Training Lightweight Graph Convolutional Networks with Phase-field Models
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs). PFMs exhibit a bi-phase behavior using a particular ultra-local term that allows training both the topology and the weight parameters of GCNs as a part of a single "end-to-end" optimization problem. Our proposed solution also relies on a reparametrization that pushes the mask of the topology towards binary values leading to effective topology selection and high generalization while implementing any targeted pruning rate. Both masks and weights share the same set of latent variables and this further enhances the generalization power of the resulting lightweight GCNs. Extensive experiments conducted on the challenging task of skeleton-based recognition show the outperformance of PFMs against other staple regularizers as well as related lightweight design methods.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
Holography encodes the three dimensional (3D) information of a sample in the form of an intensity-only recording. However, to decode the original sample image from its hologram(s), auto-focusing and phase-recovery are ne…
Image Reconstruction1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems
This paper presents a 1-D convolutional graph neural network for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spat…
Event DetectionFault DetectionGraph Neural NetworkTransfer LearningHolographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
Digital holography is one of the most widely used label-free microscopy techniques in biomedical imaging. Recovery of the missing phase information of a hologram is an important step in holographic image reconstruction. …
Image ReconstructionExtrapolating Phase-Field Simulations in Space and Time with Purely Convolutional Architectures
Phase-field models of liquid metal dealloying (LMD) can resolve rich microstructural dynamics but become intractable for large domains or long time horizons. We present a conditionally parameterized, fully convolutional …
Skeleton-Based Action Recognition With Shift Graph Convolutional Network
Action recognition with skeleton data is attracting more attention in computer vision. Recently, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have obtained remarkabl…
Action RecognitionSkeleton Based Action Recognition