Inductive Knowledge Graph Completion Benchmark Results (HITS@10)

5.5 KB of benchmark results for inductive knowledge graph completion, measuring HITS@10 scores. The data, published by Qingsong Li on figshare, compares multiple methods across four standard inductive split versions (v1-v4). Results were last updated on March 19, 2026.

Use Cases

• Benchmarking new inductive KGC models against published results based on the HITS@10 metric.
• Analyzing the performance of different methods across the four standard inductive split versions (v1-v4).
• Comparing the top-performing methods (best and second-best) as highlighted in the data.

Strengths

• Results are directly comparable, sourced from a single cited reference [7].
• Includes four standard inductive split versions (v1-v4) for evaluation.
• Explicitly marks the best and second-best results for quick comparison.

Limitations

• Dataset is very small at 5.5 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Results of compared methods are taken from a cited reference [7].

Collection Method

Likely compiled from experimental results of various knowledge graph completion methods.

Freshness

Last updated 2026-03-19 17:41:18