Link Prediction Benchmark Results Across Multiple Datasets

Mean Average Precision (MAP) scores for link prediction tasks across multiple graph datasets. Results are reported as mean ± standard deviation over five independent runs, with statistical significance noted. The 5.5 KB Excel file was authored by Yucai Jiang and last updated on June 1, 2026.

Use Cases

• Benchmarking new link prediction algorithms against reported MAP scores.
• Analyzing the statistical significance of performance improvements across different datasets.
• Comparing the variance of model performance over multiple independent runs.

Strengths

• Results include standard deviation from five independent runs, indicating performance stability.
• Statistical significance of improvements is explicitly marked (paired t-test, p < 0.05).
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset's 5.5 KB size suggests it contains only aggregated results, not the underlying graph data.

Provenance

Source

Yucai Jiang via figshare

Collection Method

Likely compiled from experimental runs of link prediction models.

Freshness

Last updated 2026-06-01 17:40:55; freshness should be verified.