paper-with-me

홈 › Papers

Ising on the Graph: Task-specific Graph Subsampling via the Ising Model

2024-02-15 · Maria Bånkestad, Jennifer R. Andersson, Sebastian Mair, Jens Sjölund

Reducing a graph while preserving its overall structure is an important problem with many applications. Typically, reduction approaches either remove edges (sparsification) or merge nodes (coarsening) in an unsupervised way with no specific downstream task in mind. In this paper, we present an approach for subsampling graph structures using an Ising model defined on either the nodes or edges and learning the external magnetic field of the Ising model using a graph neural network. Our approach is task-specific as it can learn how to reduce a graph for a specific downstream task in an end-to-end fashion. For this, the task's loss function does not have to be differentiable. We showcase the versatility of our approach on four distinct applications: image segmentation, explainability for graph classification, 3D shape sparsification, and sparse approximate matrix inverse determination.

📄 PDF Abstract BibTeX arXiv:2402.10206

Code (0)

등록된 구현이 없습니다.

Tasks

Graph ClassificationGraph Neural NetworkImage SegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems

2023-05-25 · Xiaohui Chen, Jiankai Sun, Taiqing Wang, Ruocheng Guo 외

Data subsampling is widely used to speed up the training of large-scale recommendation systems. Most subsampling methods are model-based and often require a pre-trained pilot model to measure data importance via e.g. sam…

Recommendation Systems

Model-based Subsampling for Knowledge Graph Completion

2023-09-17 · Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets. However, current subsampling approaches consider only frequencies of queries t…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph Embeddingmodel

Subsampling for Knowledge Graph Embedding Explained

2022-09-13 · Hidetaka Kamigaito, Katsuhiko Hayashi

In this article, we explain the recent advance of subsampling methods in knowledge graph embedding (KGE) starting from the original one used in word2vec.

Graph EmbeddingKnowledge Graph Embedding

Subsampling Graphs with GNN Performance Guarantees

2025-02-23 · Mika Sarkin Jain, Stefanie Jegelka, Ishani Karmarkar, Luana Ruiz 외

How can we subsample graph data so that a graph neural network (GNN) trained on the subsample achieves performance comparable to training on the full dataset? This question is of fundamental interest, as smaller datasets…

Graph Neural NetworkModel Selection

Subsampling of Correlated Graph Signals

2024-09-06 · Rishabh Ravi, Kaushani Majumder, Kalp Vyas, Satish Mulleti

Graph signals are functions of the underlying graph. When the edge-weight between a pair of nodes is high, the corresponding signals generally have a higher correlation. As a result, the signals can be represented in ter…