Research map / Graph learning / Graph algorithms and clustering
Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings
Sudhanshu Chanpuriya, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Zhao Song, Cameron N Musco
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use two nonnegative embeddings per node (homophilous B and heterophilous C) instead of BigClam's single nonnegative embedding | Symmetric nonnegative factorization model · Synthetic dating-app graph (1000 nodes, 10 cities) | Frobenius reconstruction error | Improved |
| Use the proposed model instead of SVD at equal embedding length | Symmetric nonnegative factorization model · Synthetic dating-app graph | Frobenius reconstruction error | Improved |
| Use the proposed model instead of SVD, BigClam and SymNMF at ground-truth community count | Symmetric nonnegative factorization model · Real-world networks (Blog, YouTube, POS, PPI, Amazon) | Frobenius error and entrywise cross-entropy | Improved |
| Heterophilous datasets versus homophilous social networks | Symmetric nonnegative factorization model · POS, PPI, Amazon | Reconstruction error relative to baselines | Improved |
| Use the proposed model for overlapping community detection versus SymNMF, BigClam, vGraph | Symmetric nonnegative factorization model · Real-world networks, ground-truth community similarity | F1-Score | No clear effect |
| Use the proposed model for link prediction versus BigClam, SymNMF and a random baseline | Symmetric nonnegative factorization model · Real-world networks, 10% held-out node pairs | F1 Score | Mixed |
Closest papers by meaning
- Community Preserving Network Embedding (AAAI 2017 · similarity 0.90)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.87)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.86)
- Information Loss and Disparate Effects in Network Embeddings (NeurIPS 2026 · similarity 0.86)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.86)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
