Representative Graph Neural Network
Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://git.io/RepGraph.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural Networkobject-detectionObject DetectionSemantic SegmentationSimilar Papers 제목 키워드 기반
Image Categorization and Search via a GAT Autoencoder and Representative Models
We propose a method for image categorization and retrieval that leverages graphs and a graph attention network (GAT)-based autoencoder. Our approach is representative-centric, that is, we execute the categorization and r…
Metropolis Algorithms for Representative Subgraph Sampling
While data mining in chemoinformatics studied graph data with dozens of nodes, systems biology and the Internet are now generating graph data with thousands and millions of nodes. Hence data mining faces the algorithmic …
Tackling Provably Hard Representative Selection via Graph Neural Networks
Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset. In this paper, we study RS for attributed graphs, and focus on finding representat…
Active LearningData CompressionRepresentation LearningLearning Large-scale Network Embedding from Representative Subgraph
We study the problem of large-scale network embedding, which aims to learn low-dimensional latent representations for network mining applications. Recent research in the field of network embedding has led to significant …
Graph SamplingNetwork EmbeddingSubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We o…
RAGRetrievalRetrieval-augmented Generation