Neural Chess Tablebase Compression

Neural Tablebase Compression — V8-Pro

License: MIT Python 3.8+ PyTorch

Compressing chess endgame tablebases and universal evaluation with Relational Graph Neural Networks (RGNN), attention mechanisms, and triple-head outputs.

Neural Tablebases explores whether chess knowledge (both endgame technicality and middle-game intuition) can be represented with extreme efficiency using neural models.

• Architecture: Transitioned to V8 Relational GNN (RGNN) with Vectorized Message Passing and Global Attention Pooling.
• Milestone: Reached 99.83% Accuracy on complex 4-piece endgames using the V8 architecture.
• Universal Evaluation: Implementation of the Triple-Head V8-Pro, predicting WDL, DTZ, and Stockfish-Eval (Centipawns) simultaneously.
• Industry Pipeline: High-speed sharding of the Lichess Evaluation Dataset (100M+ positions) using a Rust-backed tactical engine.

The repo still contains historical V1-V4 artifacts and reports. The current direction is V5-style relative encoding plus canonical datasets and search-based correction.

Generate topological shards from Lichess ZST backups using the high-performance Rust engine:

# Process 100M+ positions with 12 workers
python src/generate_gnn_lichess.py --input data/lichess_db_eval.jsonl.zst --output_dir data/v8_shards --workers 12

Train the flagship GNN model leveraging DirectML/AMD acceleration:

# Automated loading and logging included
python src/train_v8.py --data_dir data/v8_shards --model_name v8_pro_triple_head --batch_size 1024

• v1 to v5: Historical geometric/relative encodings for flat MLPs.
• V8 (Topological): Represents the board as a directed graph where:
  • Nodes: 64 squares with 128D learned embeddings.
  • Edges: 16 relational types (Attacks, Defenses, X-Rays, Pins, Checks) generated on-the-fly by the Rust movegen.
  • Pooling: Global Attention mechanism for dynamic feature aggregation.

• Project status
• Live project snapshot
• Scripts guide

• 3-piece summary
• Canonical forms results
• Encoding analysis
• Search correction analysis

• Paper draft
• TalkChess post draft

python >= 3.8
torch >= 2.0
numpy >= 1.20
python-chess >= 1.9

MIT License. See LICENSE.

Last updated: March 28, 2026 Current focus: V8-Pro GNN training on Syzygy tablebases, GNN-Search integration, ONNX export

Sibling repo: neural-chess-eval — Universal evaluation function trained on Lichess/Stockfish data (100M+ positions).