Research map / Graph learning / Graph algorithms and clustering

Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation

ICLR 2025 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an unsupervised multiple kernel learning method for graphs that selects and combines graph kernels by preserving ordinality of similarities, aimed at clustering tasks.

Problem

Choosing the most appropriate graph kernel for evaluating graph similarities in unsupervised settings (e.g., clustering) without labeled data is difficult.

Approach

Unsupervised multiple kernel learning for graphs that combines multiple graph kernels guided by an ordinality-preservation objective, rather than relying on labels to select the kernel.

Closest papers by meaning

• Graph Filtration Kernels (AAAI 2022 · similarity 0.89)
• Rethinking Kernel Methods for Node Representation Learning on Graphs (NeurIPS 2019 · similarity 0.88)
• RetGK: Graph Kernels based on Return Probabilities of Random Walks (NeurIPS 2018 · similarity 0.88)
• Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning (NeurIPS 2024 · similarity 0.87)
• Multiplex Graph Representation Learning with Homophily and Consistency (AAAI 2025 · similarity 0.86)
• Scalable Multiple Kernel Clustering: Learning Clustering Structure from Expectation (ICML 2024 · similarity 0.86)