paper-with-me

홈 › Papers

MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregation

2025-02-23 · Xuqi Mao, Zhenying He, X. Sean Wang

Graph neural networks (GNNs) have become the state of the art for various graph-related tasks and are particularly prominent in heterogeneous graphs (HetGs). However, several issues plague this paradigm: first, the difficulty in fully utilizing long-range information, known as over-squashing; second, the tendency for excessive message-passing layers to produce indistinguishable representations, referred to as over-smoothing; and finally, the inadequacy of conventional MPNNs to train effectively on large sparse graphs. To address these challenges in deep neural networks for large-scale heterogeneous graphs, this paper introduces the Mamba-based Asynchronous Propagation Network (MAPN), which enhances the representation of heterogeneous sparse graphs. MAPN consists of two primary components: node sequence generation and semantic information aggregation. Node sequences are initially generated based on meta-paths through random walks, which serve as the foundation for a spatial state model that extracts essential information from nodes at various distances. It then asynchronously aggregates semantic information across multiple hops and layers, effectively preserving unique node characteristics and mitigating issues related to deep network degradation. Extensive experiments across diverse datasets demonstrate the effectiveness of MAPN in graph embeddings for various downstream tasks underscoring its substantial benefits for graph representation in large sparse heterogeneous graphs.

📄 PDF Abstract BibTeX arXiv:2502.16454

Code (0)

등록된 구현이 없습니다.

Tasks

Mamba

Similar Papers 제목 키워드 기반

VectorMapNet: End-to-end Vectorized HD Map Learning

2022-06-17 · Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang 외

Autonomous driving systems require High-Definition (HD) semantic maps to navigate around urban roads. Existing solutions approach the semantic mapping problem by offline manual annotation, which suffers from serious scal…

3D Lane DetectionAutonomous DrivingHD semantic map learningNavigate

Geometry-Aware Learning of Maps for Camera Localization

2017-12-09 · CVPR 2018 6 · Samarth Brahmbhatt, Jinwei Gu, Kihwan Kim, James Hays 외

Maps are a key component in image-based camera localization and visual SLAM systems: they are used to establish geometric constraints between images, correct drift in relative pose estimation, and relocalize cameras afte…

Camera LocalizationVisual Localization

AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion

2026-06-23 · Daniel Lengerer, Mathias Pechinger, Klaus Bogenberger, Carsten Markgraf arxiv

High-resolution aerial imagery has recently emerged as a complementary modality for automated driving perception and has shown potential to improve birds-eye-view (BEV) scene understanding when fused with onboard sensors…

Scene Understanding

Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations

2021-03-01 · Nature Machine Intelligence 2021 3 · Wan Xiang Shen, Xian Zeng, Feng Zhu, Ya li Wang 외

Successful deep learning critically depends on the representation of the learned objects. Recent state-of-the-art pharmaceutical deep learning models successfully exploit graph-based de novo learning of molecular represe…

Deep Learning

PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors

2024-08-16 · Rongxuan Wang, Xin Lu, Xiaoyang Liu, Xiaoyi Zou 외

Online vectorized High-Definition (HD) map construction is crucial for subsequent prediction and planning tasks in autonomous driving. Following MapTR paradigm, recent works have made noteworthy achievements. However, re…

Autonomous DrivingDecoderOnline Vectorized HD Map Construction