GREED: A Neural Framework for Learning Graph Distance Functions

被引:0
|
作者
Ranjan, Rishabh [1 ]
Grover, Siddharth [1 ]
Medya, Sourav [2 ]
Chakravarthy, Venkat [3 ]
Sabharwal, Yogish [3 ]
Ranu, Sayan [1 ,4 ]
机构
[1] IIT Delhi, Dept Comp Sci & Engn, Delhi, India
[2] Univ Illinois, Dept Comp Sci, Chicago, IL USA
[3] IBM Res, Delhi, India
[4] IIT Delhi, Yardi Sch Jointly, Delhi, India
关键词
EDIT DISTANCE; INDEX;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Among various distance functions for graphs, graph and subgraph edit distances (GED and SED respectively) are two of the most popular and expressive measures. Unfortunately, exact computations for both are NP-hard. To overcome this computational bottleneck, neural approaches to learn and predict edit distance in polynomial time have received much interest. While considerable progress has been made, there exist limitations that need to be addressed. First, the efficacy of an approximate distance function lies not only in its approximation accuracy, but also in the preservation of its properties. To elaborate, although GED is a metric, its neural approximations do not provide such a guarantee. This prohibits their usage in higher order tasks that rely on metric distance functions, such as clustering or indexing. Second, several existing frameworks for GED do not extend to SED due to SED being asymmetric. In this work, we design a novel siamese graph neural network called GREED, which through a carefully crafted inductive bias, learns GED and SED in a property-preserving manner. Through extensive experiments across 10 real graph datasets containing up to 7 million edges, we establish that GREED is not only more accurate than the state of the art, but also up to 3 orders of magnitude faster. Even more significantly, due to preserving the triangle inequality, the generated embeddings are indexable and consequently, even in a CPU-only environment, GREED is up to 50 times faster than GPU-powered baselines for graph / subgraph retrieval.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Learning graph edit distance by graph neural networks
    Riba, Pau
    Fischer, Andreas
    Llados, Josep
    Fornes, Alicia
    PATTERN RECOGNITION, 2021, 120
  • [2] Automatic learning of cost functions for graph edit distance
    Neuhaus, Michel
    Bunke, Horst
    INFORMATION SCIENCES, 2007, 177 (01) : 239 - 247
  • [3] Neighborhood Graph and Learning Discriminative Distance Functions for Clinical Decision Support
    Tsymbal, Alexey
    Zhou, Shaohua Kevin
    Huber, Martin
    2009 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-20, 2009, : 5617 - +
  • [4] Additive Angular Margin Loss in Deep Graph Neural Network Classifier for Learning Graph Edit Distance
    Kajla, Nadeem Iqbal
    Missen, Malik Muhammad Saad
    Luqman, Muhammad Muzzamil
    Coustaty, Mickael
    Mehmood, Arif
    Choi, Gyu Sang
    IEEE ACCESS, 2020, 8 : 201752 - 201761
  • [5] A Graph Reinforcement Learning Framework for Neural Adaptive Large Neighbourhood Search
    Johnn, Syu-Ning
    Darvariu, Victor-Alexandru
    Handl, Julia
    Kalcsics, Jorg
    COMPUTERS & OPERATIONS RESEARCH, 2024, 172
  • [6] MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
    Hu, Jun
    Hooi, Bryan
    Qian, Shengsheng
    Fang, Quan
    Xu, Changsheng
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (07) : 3281 - 3296
  • [7] GCRL: a graph neural network framework for network connectivity robustness learning
    Zhang, Yu
    Chen, Haowei
    Chen, Qiyu
    Ding, Jie
    Li, Xiang
    NEW JOURNAL OF PHYSICS, 2024, 26 (09):
  • [8] Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction
    Zhang, Juzheng
    Wei, Lanning
    Xu, Zhen
    Yao, Quanming
    PROCEEDINGS OF THE 30TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2024, 2024, : 4223 - 4231
  • [9] Automated Graph Neural Network Search Under Federated Learning Framework
    Wang, Chunnan
    Chen, Bozhou
    Li, Geng
    Wang, Hongzhi
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (10) : 9959 - 9972
  • [10] Nonlinear distance function learning using neural network: an iterative framework
    Junying Chen
    Haoyu Zeng
    Na Fan
    Multimedia Tools and Applications, 2015, 74 : 671 - 688