paper-with-me

홈 › Papers

Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions

2021-05-24 · Zhenyue Qin, Saeed Anwar, Dongwoo Kim, Yang Liu, Pan Ji, Tom Gedeon

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the awareness of node positions, some nodes are set as anchors. Then, using the distances from a node to the anchors, GNNs can infer relative positions between nodes. However, P-GNNs arbitrarily select anchors, leading to compromising position-awareness and feature extraction. To eliminate this compromise, we demonstrate that selecting evenly distributed and asymmetric anchors is essential. On the other hand, we show that choosing anchors that can aggregate embeddings of all the nodes within a graph is NP-hard. Therefore, devising efficient optimal algorithms in a deterministic approach is practically not feasible. To ensure position-awareness and bypass NP-completeness, we propose Position-Sensing Graph Neural Networks (PSGNNs), learning how to choose anchors in a back-propagatable fashion. Experiments verify the effectiveness of PSGNNs against state-of-the-art GNNs, substantially improving performance on various synthetic and real-world graph datasets while enjoying stable scalability. Specifically, PSGNNs on average boost AUC more than 14% for pairwise node classification and 18% for link prediction over the existing state-of-the-art position-aware methods. Our source code is publicly available at: https://github.com/ZhenyueQin/PSGNN

📄 PDF Abstract BibTeX arXiv:2105.11346

Code (1)

ZhenyueQin/PSGNN 공식 구현

Tasks

Link PredictionNode ClassificationPosition

Similar Papers 제목 키워드 기반

mmSnap: Bayesian One-Shot Fusion in a Self-Calibrated mmWave Radar Network

2025-05-01 · Anirban Banik, Lalitha Giridhar, Aaditya Prakash Kattekola, Anurag Pallaprolu 외

We present mmSnap, a collaborative RF sensing framework using multiple radar nodes, and demonstrate its feasibility and efficacy using commercially available mmWave MIMO radars. Collaborative fusion requires network cali…

Leveraging commonsense for object localisation in partial scenes

2022-11-01 · Francesco Giuliari, Geri Skenderi, Marco Cristani, Alessio Del Bue 외

We propose an end-to-end solution to address the problem of object localisation in partial scenes, where we aim to estimate the position of an object in an unknown area given only a partial 3D scan of the scene. We propo…

Graph Neural NetworkObjectPosition

PA-GM: Position-Aware Learning of Embedding Networks for Deep Graph Matching

2023-01-05 · Dongdong Chen, Yuxing Dai, Lichi Zhang, Zhihong Zhang

Graph matching can be formalized as a combinatorial optimization problem, where there are corresponding relationships between pairs of nodes that can be represented as edges. This problem becomes challenging when there a…

Combinatorial OptimizationGraph MatchingPosition

GRPE: Relative Positional Encoding for Graph Transformer

2022-01-30 · Wonpyo Park, WoongGi Chang, Donggeon Lee, Juntae Kim 외

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with a…

Graph ClassificationGraph RegressionGraph Representation LearningMolecular Property Prediction+2

GraphReach: Position-Aware Graph Neural Network using Reachability Estimations

2020-08-19 · Sunil Nishad, Shubhangi Agarwal, Arnab Bhattacharya, Sayan Ranu

Majority of the existing graph neural networks (GNN) learn node embeddings that encode their local neighborhoods but not their positions. Consequently, two nodes that are vastly distant but located in similar local neigh…

Graph Neural NetworkLink PredictionNode ClassificationPosition