3 commits

Author	SHA1	Message	Date
rUv	ded3057831	chore: Publish @ruvector/gnn@0.1.15 to npm ... - Update package.json version to 0.1.15 - Build native binary for linux-x64-gnu - Published base package to npm registry Native binaries for other platforms (darwin, windows, arm64) will be built and published via GitHub Actions CI. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-27 02:56:54 +00:00
rUv	1cc09933eb	feat: Implement GNN forgetting mitigation (#17) ... This commit addresses GitHub issue #17 by implementing comprehensive forgetting mitigation for continual learning in the GNN module. ## New Features ### Optimizer Implementation (training.rs) - Full Adam optimizer with bias-corrected first and second moments - SGD with momentum support - Lazy initialization of state buffers for efficiency ### Replay Buffer (replay.rs) - Experience replay with reservoir sampling for uniform distribution - Distribution shift detection with statistical tracking - Configurable capacity and batch sampling ### Elastic Weight Consolidation (ewc.rs) - Fisher information diagonal computation - Anchor weight consolidation for task boundaries - EWC penalty and gradient computation ### Learning Rate Scheduling (scheduler.rs) - Constant, StepDecay, Exponential schedulers - CosineAnnealing with warm restarts - WarmupLinear for pre-training warmup - ReduceOnPlateau for adaptive learning ## Deployment Infrastructure ### GitHub Actions Release Pipeline (.github/workflows/release.yml) - 8-stage CI/CD pipeline for complete releases - Validates, builds crates, WASM, and native modules - Publishes to crates.io and npmjs.com - Creates GitHub releases with artifacts ### Deployment Script (scripts/deploy.sh) - Comprehensive deployment orchestration - Version synchronization across Cargo.toml and package.json - Dry-run mode for testing - Cross-platform native builds support ## Test Coverage - 177 tests passing in ruvector-gnn - Comprehensive tests for all new modules - Convergence tests for optimizers 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-26 23:17:07 +00:00
Claude	4b2c2c212d	feat: Add ruvector-gnn crate with GNN, compression, WASM and Node.js bindings ... Major additions: - ruvector-gnn: Complete GNN implementation with RuvectorLayer, multi-head attention, GRU cell - Tensor compression: 5-tier adaptive compression (f32→f16→PQ8→PQ4→Binary, 2-32x) - Differentiable search: Soft attention k-NN with gradient flow - Training: InfoNCE contrastive loss, SGD optimizer - Query API: RuvectorQuery, QueryResult, SubGraph types - MmapManager: Memory-mapped embeddings with gradient accumulation - Tensor operations: Full tensor math library Bindings: - ruvector-gnn-wasm: Full WASM bindings for browser - ruvector-gnn-node: napi-rs bindings for Node.js Fixes: - WASM compatibility for ruvector-graph (conditional compilation) - Feature flags for storage/hnsw modules Updated README with GNN architecture overview and tutorials	2025-11-26 04:50:36 +00:00