Log In Sign Up

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks

by   Kun Yuan, et al.

One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data with high diversity. To promote the model capacity, existing approaches usually employ larger convolutional kernels or deeper network structure, which may increase the computational cost. In this paper, we address this issue by raising the Dynamic Graph Network (DG-Net). The network learns the instance-aware connectivity, which creates different forward paths for different instances. Specifically, the network is initialized as a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent the connection paths. We generate edge weights by a learnable module router and select the edges whose weights are larger than a threshold, to adjust the connectivity of the neural network structure. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability. To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix. The matrix is updated to aggregate features in the forward pass, cached in the memory, and used for gradient computing in the backward pass. We verify the effectiveness of our method with several static architectures, including MobileNetV2, ResNet, ResNeXt, and RegNet. Extensive experiments are performed on ImageNet classification and COCO object detection, which shows the effectiveness and generalization ability of our approach.


page 1

page 2

page 3

page 4


Graph Spectral Embedding using the Geodesic Betweeness Centrality

We introduce the Graph Sylvester Embedding (GSE), an unsupervised graph ...

Spectral Embedding of Graph Networks

We introduce an unsupervised graph embedding that trades off local node ...

Network classification with applications to brain connectomics

While statistical analysis of a single network has received a lot of att...

Learning Connectivity of Neural Networks from a Topological Perspective

Seeking effective neural networks is a critical and practical field in d...

Constructing Deep Neural Networks by Bayesian Network Structure Learning

We introduce a principled approach for unsupervised structure learning o...

ISBNet: Instance-aware Selective Branching Network

Recent years have witnessed growing interests in designing efficient neu...

Public Transport Planning: When Transit Network Connectivity Meets Commuting Demand

In this paper, we make a first attempt to incorporate both commuting dem...