Apprivoiser la Pré-image (APi, projet ANR)

Search
Skip to content
  • The APi Project
  • The Team
  • Research Results
Conferences

A graph pre-image method based on graph edit distances (accepted in S+SSPR’21)

1 January 2021 dsi-wordpress

By Linlin Jia, Benoit Gaüzère, and Paul Honeine.

In Proceedings of the IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (S+SSPR), Venice, Italy, 21 – 22 January 2021.

Graph edit distanceGraph kernelsGraph representationKernel methodsPre-image problemRepresentation learning

Post navigation

Previous PostInvestigating CoordConv for Fully and Weakly Supervised Medical Image Segmentation (in Proc. IPTA’20)Next PostLearning Output Embeddings in Structured Prediction (submitted to AISTATS’21)

Taming the Beast of the Preimage in Machine Learning for Structured Data: Signal, Image and Graph

Generate a "median" molecule by solving the pre-image problem
Learning Output Embeddings in Structured Prediction
Spectral-designed Depthwise Separable Graph Neural Networks (ICML'20 - GRL+)
When Spectral Domain Meets Spatial Domain in Graph Neural Networks (in ICML’20 – GRL+)
Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses (ICML’20)
Analyzing the expressive power of graph neural networks in a spectral perspective (ICLR'21)
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters (ICML'22)
Vector-Valued Least-Squares Regression under Output Regularity Assumptions (JMLR'22)
Graph Normalizing Flows to Pre-image Free Machine Learning for Regression (IAPR-TC15, 2023)
Bridging Distinct Spaces in Graph-based Machine Learning (ACPR'23)
Interpretable time series kernel analytics by pre-image estimation (Artificial Intelligence, 2020)

Recent News

  • A metric learning approach to graph edit costs for regression (accepted in S+SSPR’21)1 January 2021
  • Learning Output Embeddings in Structured Prediction (submitted to AISTATS’21)1 January 2021
  • A graph pre-image method based on graph edit distances (accepted in S+SSPR’21)1 January 2021
  • Investigating CoordConv for Fully and Weakly Supervised Medical Image Segmentation (in Proc. IPTA’20)9 November 2020
  • BB-UNet: U-Net with Bounding Box Prior (in IEEE Journal of Selected Topics in Signal Processing 2020)1 October 2020

Archives

  • January 2021 (3)
  • November 2020 (1)
  • October 2020 (1)
  • September 2020 (1)
  • July 2020 (3)
  • May 2020 (1)
  • August 2019 (1)

Categories

  • Conferences (9)
  • Journals (2)

Tags

Attention maps Bi-objective optimization Deep learning Dictionary learning Graph edit distance Graph kernels Graph neural networks Graph representation Hyperspectral data analysis Image segmentation Kernel methods Kernel PCA Multi-task regression nonlinear unmixing nonnegative matrix factorization Operator-valued kernels Output Embedding Pre-image problem Prior knowledge Representation learning Robust Shape prior Structured prediction Time series Time series averaging U-Net Vector-valued RKHS Weakly supervised learning

Proudly powered by WordPress