graphs-1

Graph Similarity

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-similarity-1

Trend

Dataset

Best Model

Actions

IMDb

Libraries

i

Use these libraries to find graph-similarity-1 models and implementations

Datasets

IMDb Movie Reviews

IMDB-MULTI

Linux

Subtasks

No subtasks available.

Most implemented papers

Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks

S. Ktena, D. Rueckert, Ben Glocker, Enzo Ferrante, M. J. Lee, Sarah Parisot, Martin Rajchl•Mon Mar 06 2017

A novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory to allow these operations on irregular graphs to be exploited.

208

Content

0

Paper Graph

clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

J. Paetzold, Suprosanna Shit, Bjoern H Menze, A. Sekuboyina, I. Ezhov, J. Pluim, Alexander Unger, A. Zhylka, Ulrich Bauer•Sun Mar 15 2020

This work theoretically proves that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation, and pro-poses a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks.

416 0

Paper Graph

SimGNN: A Neural Network Approach to Fast Graph Similarity Computation

Ting Chen, Wei Wang, Yunsheng Bai, Haoyang Ding, Yizhou Sun, Song Bian•Wed Aug 15 2018

This work proposes a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance, and suggests SimGNN provides a new direction for future research on graph similarity computation and graph similarity search.

382 0

Paper Graph

GREED: A Neural Framework for Learning Graph Distance Functions

Rishab Ranjan, Siddharth Grover, Sourav Medya, Venkatesan T. Chakaravarthy, Yogish Sabharwal, Sayan Ranu•Thu Dec 23 2021

A novel siamese graph neural network called GREED is designed, which through a carefully crafted inductive bias, learns GED and SED in a property-preserving manner and is not only more accurate than the state of the art, but also up to 3 orders of magnitude faster.

55 0

Paper Graph

MathLingBudapest: Concept Networks for Semantic Similarity

Gábor Recski, Judit Ács•Sun May 31 2015

The hybrid approach to measuring semantic similarity of sentence pairs used in Semeval 2015 tasks 1 and 2 hybridize the common vector-based models with definition graphs from the 4lang concept dictionary and devise a measure of graph similarity that yields good results on training data.

10 0

Paper Graph

Scalable Spectral Clustering Using Random Binning Features

C. Aggarwal, Pin-Yu Chen, Fangli Xu, Lingfei Wu, I. E. Yen, Yinglong Xia•Thu May 24 2018

This paper presents a novel scalable spectral clustering method using Random Binning features (RB) to simultaneously accelerate both similarity graph construction and the eigendecomposition and introduces a state-of-the-art SVD solver to effectively compute eigenvectors of a large sparse feature matrix generated by RB.

42 0

Paper Graph

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications

Pin-Yu Chen, Lingfei Wu, Sijia Liu, I. Rajapakse•Mon Apr 30 2018

FINGER reduces the cubic complexity of VNGE to linear complexity in the number of nodes and edges, and thus enables online computation based on incremental graph changes, and shows asymptotic equivalence of FINGER to the exact VN GE, and proposes efficient algorithms for computing Jensen-Shannon distance between graphs.

29 0

Paper Graph

Message Passing Graph Kernels

M. Vazirgiannis, Giannis Nikolentzos•Mon Aug 06 2018

This paper derives four instances of the proposed framework for designing graph kernels, and shows through extensive experiments that these instances are competitive with state-of-the-art methods in various tasks.

8 0

Paper Graph

Learning Networks from Random Walk-Based Node Similarities

J. Hoskins, Cameron Musco, Christopher Musco, Charalampos E. Tsourakakis•Mon Jan 22 2018

This work considers a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances or personalized PageRank scores, and shows that with just a small subset of measurements, the attacker can learn a large fraction of edges in asocial network, even when the measurements are noisy.

6 0

Paper Graph

Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching

Yunsheng Bai, Haoyang Ding, Ken Gu, Yizhou Sun•Sun Sep 09 2018

The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings, compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.

124 0

Paper Graph

Adding a benchmark result helps the community track progress.