GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

• URL: http://arxiv.org/abs/2405.06849v1
• Date: Fri, 10 May 2024 23:21:16 GMT
• Title: GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs
• Authors: Mustafa Munir, William Avery, Md Mostafijur Rahman, Radu Marculescu,
• Abstract summary: Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. We propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN. We also propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC.
• Score: 5.895049552752008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNN-GNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models.

Related papers

• BG-HGNN: Toward Scalable and Efficient Heterogeneous Graph Neural Network [6.598758004828656]
  Heterogeneous graph neural networks (HGNNs) stand out as a promising neural model class designed for heterogeneous graphs. Existing HGNNs employ different parameter spaces to model the varied relationships. This paper introduces Blend&Grind-HGNN, which integrates different relations into a unified feature space manageable by a single set of parameters.
  arXiv  Detail & Related papers  (2024-03-13T03:03:40Z)
• PVG: Progressive Vision Graph for Vision Recognition [25.752613030302534]
  We propose a Progressive Vision Graph (PVG) architecture for vision recognition task. PVG contains three main components: 1) Progressively Separated Graph Construction (PSGC), 2) Neighbor nodes information aggregation and update module, and 3) Graph error Linear Unit (GraphLU)
  arXiv  Detail & Related papers  (2023-08-01T14:35:29Z)
• MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications [7.2210216531805695]
  Vision graph neural networks (ViGs) provide a new avenue for exploration. ViGs are computationally expensive due to the overhead of representing images as graph structures. We propose a new graph-based sparse attention mechanism, Sparse Vision Graph Attention (SVGA), that is designed for ViGs running on mobile devices.
  arXiv  Detail & Related papers  (2023-07-01T17:49:12Z)
• LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation [51.552170474958736]
  We propose to capture long-distance dependency in graphs by shallower models instead of deeper models, which leads to a much more efficient model, LazyGNN, for graph representation learning. LazyGNN is compatible with existing scalable approaches (such as sampling methods) for further accelerations through the development of mini-batch LazyGNN. Comprehensive experiments demonstrate its superior prediction performance and scalability on large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-02-03T02:33:07Z)
• Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph [58.99478502486377]
  We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
  arXiv  Detail & Related papers  (2022-09-23T05:24:18Z)
• Revisiting Embeddings for Graph Neural Networks [0.0]
  We explore different embedding extraction techniques for both images and texts. We find that the choice of embedding biases the performance of different GNN architectures. We propose Graph-connected Network (GraNet) layers which use GNN message passing within large models to allow neighborhood aggregation.
  arXiv  Detail & Related papers  (2022-09-19T20:37:55Z)
• Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [58.76759997223951]
  We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs. We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
  arXiv  Detail & Related papers  (2022-03-19T14:26:43Z)
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks [82.31087406264437]
  We present a unified GNN sparsification (UGS) framework that simultaneously prunes the graph adjacency matrix and the model weights. We further generalize the popular lottery ticket hypothesis to GNNs for the first time, by defining a graph lottery ticket (GLT) as a pair of core sub-dataset and sparse sub-network.
  arXiv  Detail & Related papers  (2021-02-12T21:52:43Z)
• Identity-aware Graph Neural Networks [63.6952975763946]
  We develop a class of message passing Graph Neural Networks (ID-GNNs) with greater expressive power than the 1-WL test. ID-GNN extends existing GNN architectures by inductively considering nodes' identities during message passing. We show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks.
  arXiv  Detail & Related papers  (2021-01-25T18:59:01Z)
• GPT-GNN: Generative Pre-Training of Graph Neural Networks [93.35945182085948]
  Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. We present the GPT-GNN framework to initialize GNNs by generative pre-training. We show that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.
  arXiv  Detail & Related papers  (2020-06-27T20:12:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.