MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202411102879 A) filed by Fujitsu Limited on December 24, 2024, for Self-Supervised Graph Condensation.
Inventors include Nandy, Jay; Mondal, Arnab Kumar; and Chandran, Mahesh.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: In an embodiment, operations include determining first condensed graphs and perturbed graphs, based on a received input graph. The operations include determining first embeddings for perturbed graphs and second embeddings for first condensed graphs. Clusters associated with the first embeddings are determined. Latent representations associated with the first condensed graphs are determined, based on the second embeddings. Swapped prediction loss associated with perturbed graphs is determined, based on the first embeddings and the clusters. Latent pseudo-labels associated with the perturbed graphs are determined, based on the swapped prediction loss. A similarity metric between the latent representations and the latent pseudo-labels is determined to update the first condensed graphs. The operations further include rendering of information related to the updated first condensed graph.
Disclaimer: Curated by HT Syndication.
