MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
MambaSimilar Papers 제목 키워드 기반
VectorMapNet: End-to-end Vectorized HD Map Learning
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 learningNavigateGeometry-Aware Learning of Maps for Camera Localization
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 LocalizationAerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion
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 UnderstandingOut-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations
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 LearningPriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors
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