paper-with-me

Papers

Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning

2023-05-30 · Hichem Sahbi

Graph convolutional networks (GCNs) are nowadays becoming mainstream in solving many image processing tasks including skeleton-based recognition. Their general recipe consists in learning convolutional and attention layers that maximize classification performances. With multi-head attention, GCNs are highly accurate but oversized, and their deployment on edge devices requires their pruning. Among existing methods, magnitude pruning (MP) is relatively effective but its design is clearly suboptimal as network topology selection and weight retraining are achieved independently. In this paper, we devise a novel lightweight GCN design dubbed as Probabilistic Magnitude Pruning (PMP) that jointly trains network topology and weights. Our method is variational and proceeds by aligning the weight distribution of the learned networks with an a priori distribution. This allows implementing any fixed pruning rate, and also enhancing the generalization performances of the designed lightweight GCNs. Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.

📄 PDF Abstract BibTeX arXiv:2305.19343

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Budget-aware Few-shot Learning via Graph Convolutional Network

2022-01-07 · Shipeng Yan, Songyang Zhang, Xuming He

This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random sampling strategy in acquiring data lab…

Few-Shot LearningInformativenessMeta-Learning

Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints

2026-06-01 · Reda Snaiki, Abdelatif Merabtine arxiv

Reconstructing spatially continuous daily temperature fields from sparse observations is important for urban climate monitoring and heat-risk analysis, but practical deployments are limited by sensor budgets and spacing …

Graph Neural Network

Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfaction

2022-10-03 · Seokjun Ahn, Jungtaek Kim, Minsu Cho, Jaesik Park

We tackle the problem of sequential brick assembly with LEGO bricks to create combinatorial 3D structures. This problem is challenging since this brick assembly task encompasses the characteristics of combinatorial optim…

Bayesian OptimizationCombinatorial OptimizationPosition

Graph-Based Interaction-Aware Multimodal 2D Vehicle Trajectory Prediction using Diffusion Graph Convolutional Networks

2023-09-05 · Keshu Wu, Yang Zhou, Haotian Shi, Xiaopeng Li 외

Predicting vehicle trajectories is crucial for ensuring automated vehicle operation efficiency and safety, particularly on congested multi-lane highways. In such dynamic environments, a vehicle's motion is determined by …

Graph EmbeddingIntent DetectionTrajectory Prediction

Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data

2019-10-18 · Sergio Casas, Cole Gulino, Renjie Liao, Raquel Urtasun

In this paper, we tackle the problem of relational behavior forecasting from sensor data. Towards this goal, we propose a novel spatially-aware graph neural network (SpAGNN) that models the interactions between agents in…

Graph Neural NetworkMotion PlanningTrajectory Forecasting