graphssl 0.1.0__tar.gz

graphssl-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Simone Copetti
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

graphssl-0.1.0/PKG-INFO

@@ -0,0 +1,273 @@
+Metadata-Version: 2.4
+Name: graphssl
+Version: 0.1.0
+Summary: A modular Python library for Self-Supervised Learning on graphs, built on PyTorch and PyTorch Geometric.
+Author-email: Simone Copetti <copetti.simone7@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/Simocop7/graphssl
+Project-URL: Repository, https://github.com/Simocop7/graphssl
+Project-URL: Bug Tracker, https://github.com/Simocop7/graphssl/issues
+Project-URL: Documentation, https://github.com/Simocop7/graphssl#readme
+Keywords: graph-learning,self-supervised-learning,gnn,pytorch-geometric,contrastive-learning,graph-neural-networks
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: torch_geometric>=2.3.0
+Provides-Extra: viz
+Requires-Dist: umap-learn; extra == "viz"
+Requires-Dist: matplotlib; extra == "viz"
+Requires-Dist: seaborn; extra == "viz"
+Provides-Extra: full
+Requires-Dist: faiss-cpu; extra == "full"
+Requires-Dist: umap-learn; extra == "full"
+Requires-Dist: matplotlib; extra == "full"
+Requires-Dist: seaborn; extra == "full"
+Requires-Dist: ogb; extra == "full"
+Requires-Dist: pyyaml; extra == "full"
+Provides-Extra: benchmark
+Requires-Dist: ogb; extra == "benchmark"
+Requires-Dist: pyyaml; extra == "benchmark"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Requires-Dist: pyyaml; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Dynamic: license-file
+
+# GraphSSL
+
+[![Tests](https://github.com/Simocop7/graphssl/actions/workflows/tests.yml/badge.svg)](https://github.com/Simocop7/graphssl/actions/workflows/tests.yml)
+[![codecov](https://codecov.io/gh/Simocop7/graphssl/branch/main/graph/badge.svg)](https://codecov.io/gh/Simocop7/graphssl)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)](pyproject.toml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+
+A modular Python library for **Self-Supervised Learning on graphs**, built on PyTorch and PyTorch Geometric. No Lightning, no Hydra — clean, readable training loops you can step through with a debugger.
+
+> **Status:** Alpha — all models train end-to-end and pass tests; citation-network benchmarks validated (see below), large-scale (OGB) benchmarks in progress.
+
+---
+
+## Supported Methods
+
+| Method | Family | Paper |
+|---|---|---|
+| **DGI** | Mutual Information | Veličković et al., ICLR 2019 |
+| **GraphCL** | Contrastive (NT-Xent) | You et al., NeurIPS 2020 |
+| **BGRL** | Teacher-Student + EMA | Thakoor et al., ICLR 2022 |
+| **AFGRL** | Augmentation-Free Mining | Lee et al., AAAI 2022 |
+| **VICReg** | Variance-Invariance-Covariance | Bardes et al., ICLR 2022 |
+| **Barlow Twins** | Cross-Correlation | Zbontar et al., ICML 2021 |
+| **GraphDINO** | Self-Distillation | Adapted from Caron et al., ICCV 2021 |
+
+Plus a **Supervised** baseline for comparison.
+
+Encoder backbones: **GCN**, **GIN**, **Graph Transformer** — all swappable via one config line.
+
+---
+
+## Installation
+
+```bash
+pip install graphssl
+
+# optional extras
+pip install "graphssl[viz]"        # UMAP + matplotlib
+pip install "graphssl[benchmark]"  # ogb + pyyaml (for ZINC / ogbn-arxiv)
+pip install "graphssl[full]"       # faiss-cpu + viz + benchmark
+```
+
+**Development:**
+```bash
+git clone https://github.com/Simocop7/graphssl.git
+cd graphssl
+pip install -e ".[dev]"
+pre-commit install   # ruff on every commit
+pytest tests/ -v
+```
+
+All 107 unit tests should pass. AFGRL tests are auto-skipped if `faiss-cpu` is not installed.
+See [CONTRIBUTING.md](CONTRIBUTING.md) for the full dev workflow (lint, type checking, adding a model).
+
+---
+
+## Quick Start
+
+Every model uses the same constructor API:
+
+```python
+from graphssl.models import BGRL
+from graphssl.training import DINOTrainer
+from torch.optim import AdamW
+
+config = {
+    "encoder": {
+        "name": "gin",
+        "hidden_dim": 256,
+        "num_layers": 3,
+        "norm_type": "batch",  # 'batch', 'layer', or 'none'
+        "pool": False,         # False = node-level task
+    },
+    "augment": [
+        {"name": "edge_drop", "p": 0.5},
+        {"name": "feat_mask", "p": 0.1},
+    ],
+    "pred_hidden": 512,
+    "ema_tau": 0.99,
+    "ema_tau_end": 1.0,
+    "total_steps": 0,
+}
+
+model = BGRL(config, in_channels=dataset.num_features)
+optimizer = AdamW(model.student_parameters(), lr=1e-3)
+trainer = DINOTrainer(device="cuda")
+losses = trainer.train(model, loader, optimizer, num_epochs=1000)
+```
+
+Or load config from YAML:
+
+```python
+from graphssl.config.load import load_config, build_model
+
+cfg   = load_config("configs/ogbn_arxiv_bgrl.yaml")
+model = build_model(cfg, in_channels=128)
+```
+
+See `configs/` for reference YAML files and `examples/` for full benchmark scripts:
+
+| Script | Dataset | Task | Notes |
+|---|---|---|---|
+| `examples/cora_bgrl.py` | Cora | Node classification (7 classes) | Full-batch, CPU-friendly — fastest smoke test |
+| `examples/benchmark_planetoid.py` | Cora / CiteSeer / PubMed | Node classification, multi-seed | Reproduces the results below (`--seeds`, `--epochs`) |
+| `examples/ogbn_arxiv_bgrl.py` | ogbn-arxiv | Node classification (40 classes) | `NeighborLoader` mini-batch training |
+| `examples/zinc_bgrl.py` | ZINC-12k | Molecular property regression | Categorical node/edge embeddings |
+
+### Benchmark results (citation networks)
+
+BGRL, GIN-2L encoder (`hidden_dim=256`), full-batch training for 300 steps, public Planetoid split, mean ± std over 10 seeds (`python examples/benchmark_planetoid.py --dataset <name> --seeds 10`):
+
+| Dataset | Linear probe (test) | KNN k=5 (test) |
+|---|---|---|
+| Cora | 62.39 ± 3.71 | 58.61 ± 3.76 |
+| CiteSeer | 50.08 ± 1.58 | 43.07 ± 3.61 |
+| PubMed | 69.18 ± 2.32 | 66.59 ± 2.88 |
+
+This is a deliberately lightweight, untuned configuration (no per-dataset hyperparameter search) meant to validate that the training/evaluation pipeline is correct end-to-end — not a state-of-the-art claim. See `paper.tex` for a methodological comparison against the original BGRL paper's own numbers on these datasets. ogbn-arxiv and OGB graph-level benchmarks (ogbg-molhiv, ogbg-molpcba) require larger compute and are planned on dedicated infrastructure.
+
+---
+
+## Datasets with Categorical Features (ZINC)
+
+ZINC has integer node and edge features. Use `node_emb_num_classes` and `edge_emb_num_classes`
+to replace linear projections with `nn.Embedding`:
+
+```python
+config = {
+    "encoder": {
+        "name": "gin",
+        "hidden_dim": 64,
+        "num_layers": 4,
+        "norm_type": "layer",
+        "pool": True,
+        "node_emb_num_classes": 28,  # 28 atom types
+        "edge_dim": 64,
+        "edge_emb_num_classes": 4,   # 4 bond types
+    },
+    ...
+}
+model = BGRL(config, in_channels=1)  # in_channels ignored when node_emb_num_classes is set
+```
+
+---
+
+## Composable Losses
+
+Mix and weight multiple objectives without touching model code:
+
+```python
+from graphssl.losses import CombinedLoss
+
+loss_fn = CombinedLoss.from_config([
+    {"name": "nt_xent",  "weight": 0.7, "tau": 0.5},
+    {"name": "vicreg",   "weight": 0.3, "invariance": 25.0, "variance": 25.0, "covariance": 1.0},
+])
+loss = loss_fn(z1, z2)
+```
+
+---
+
+## Extending the Library
+
+All major components are registered by name and can be replaced via config:
+
+```python
+from graphssl.registry import ENCODERS, LOSSES, AUGMENTS
+
+@ENCODERS.register("my_gat")
+class GATEncoder(nn.Module):
+    ...
+
+# Then use it in any model config:
+config = {"encoder": {"name": "my_gat", "hidden_dim": 128, ...}, ...}
+```
+
+Models expose `compute_loss(batch)`, `post_backward()`, and `post_step()` hooks,
+so you can write your own training loop if needed:
+
+```python
+for batch in loader:
+    loss = model.compute_loss(batch)
+    loss.backward()
+    model.post_backward()
+    optimizer.step()
+    model.post_step()
+```
+
+---
+
+## Project Structure
+
+```
+src/graphssl/
+├── core/          # BaseSSLModel, Callback, Registry, Protocol interfaces
+├── config/        # Dataclass schemas + YAML loading (load_config, build_model)
+├── registry/      # ENCODERS, HEADS, AUGMENTS, LOSSES, LOADERS, OBJECTIVES, DATASETS
+├── encoders/      # GCN, GIN, Transformer (auto-registered)
+├── models/        # All SSL models + Supervised baseline
+├── losses/        # NT-Xent, DINO, VICReg, Barlow Twins, CosineRegression, CombinedLoss
+├── augmentation/  # 7 transforms, compose(), MultiView
+├── nn/            # MLP, Projector, Predictor, DINOHead, pooling
+├── evaluation/    # LogRegEvaluator, KNNEvaluator, extract_embeddings
+├── training/      # DINOTrainer + callbacks
+├── data/          # DataModule (full-batch and NeighborLoader)
+└── utils/         # update_ema_params, CosineDecayScheduler, CosineEMAScheduler, PositiveMiner
+```
+
+---
+
+## Key Design Choices
+
+- **Uniform API.** Every model is `ModelClass(config: Dict, in_channels: int)`. The config dict is validated by a dedicated dataclass in `schema.py`.
+- **Hook-driven training.** The trainer calls `post_backward()` and `post_step()` at fixed points. Models implement these to freeze prototype gradients (GraphDINO) or update the EMA teacher (BGRL, AFGRL) — without subclassing the trainer.
+- **Protected-node augmentations.** When using `NeighborLoader` for mini-batch training, seed nodes are shielded from `node_drop` so the loss remains valid.
+- **Registry pattern.** All components are registered by name (`@ENCODERS.register("gin")`), so swapping architectures is a one-line config change.
+- **Composable losses.** `CombinedLoss` enables weighted mixtures of any registered losses, configurable from YAML or programmatically.
+
+---
+
+## Acknowledgments
+
+Developed at [NECSTLab](https://necst.it), Politecnico di Milano.

graphssl-0.1.0/README.md

@@ -0,0 +1,224 @@
+# GraphSSL
+
+[![Tests](https://github.com/Simocop7/graphssl/actions/workflows/tests.yml/badge.svg)](https://github.com/Simocop7/graphssl/actions/workflows/tests.yml)
+[![codecov](https://codecov.io/gh/Simocop7/graphssl/branch/main/graph/badge.svg)](https://codecov.io/gh/Simocop7/graphssl)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)](pyproject.toml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+
+A modular Python library for **Self-Supervised Learning on graphs**, built on PyTorch and PyTorch Geometric. No Lightning, no Hydra — clean, readable training loops you can step through with a debugger.
+
+> **Status:** Alpha — all models train end-to-end and pass tests; citation-network benchmarks validated (see below), large-scale (OGB) benchmarks in progress.
+
+---
+
+## Supported Methods
+
+| Method | Family | Paper |
+|---|---|---|
+| **DGI** | Mutual Information | Veličković et al., ICLR 2019 |
+| **GraphCL** | Contrastive (NT-Xent) | You et al., NeurIPS 2020 |
+| **BGRL** | Teacher-Student + EMA | Thakoor et al., ICLR 2022 |
+| **AFGRL** | Augmentation-Free Mining | Lee et al., AAAI 2022 |
+| **VICReg** | Variance-Invariance-Covariance | Bardes et al., ICLR 2022 |
+| **Barlow Twins** | Cross-Correlation | Zbontar et al., ICML 2021 |
+| **GraphDINO** | Self-Distillation | Adapted from Caron et al., ICCV 2021 |
+
+Plus a **Supervised** baseline for comparison.
+
+Encoder backbones: **GCN**, **GIN**, **Graph Transformer** — all swappable via one config line.
+
+---
+
+## Installation
+
+```bash
+pip install graphssl
+
+# optional extras
+pip install "graphssl[viz]"        # UMAP + matplotlib
+pip install "graphssl[benchmark]"  # ogb + pyyaml (for ZINC / ogbn-arxiv)
+pip install "graphssl[full]"       # faiss-cpu + viz + benchmark
+```
+
+**Development:**
+```bash
+git clone https://github.com/Simocop7/graphssl.git
+cd graphssl
+pip install -e ".[dev]"
+pre-commit install   # ruff on every commit
+pytest tests/ -v
+```
+
+All 107 unit tests should pass. AFGRL tests are auto-skipped if `faiss-cpu` is not installed.
+See [CONTRIBUTING.md](CONTRIBUTING.md) for the full dev workflow (lint, type checking, adding a model).
+
+---
+
+## Quick Start
+
+Every model uses the same constructor API:
+
+```python
+from graphssl.models import BGRL
+from graphssl.training import DINOTrainer
+from torch.optim import AdamW
+
+config = {
+    "encoder": {
+        "name": "gin",
+        "hidden_dim": 256,
+        "num_layers": 3,
+        "norm_type": "batch",  # 'batch', 'layer', or 'none'
+        "pool": False,         # False = node-level task
+    },
+    "augment": [
+        {"name": "edge_drop", "p": 0.5},
+        {"name": "feat_mask", "p": 0.1},
+    ],
+    "pred_hidden": 512,
+    "ema_tau": 0.99,
+    "ema_tau_end": 1.0,
+    "total_steps": 0,
+}
+
+model = BGRL(config, in_channels=dataset.num_features)
+optimizer = AdamW(model.student_parameters(), lr=1e-3)
+trainer = DINOTrainer(device="cuda")
+losses = trainer.train(model, loader, optimizer, num_epochs=1000)
+```
+
+Or load config from YAML:
+
+```python
+from graphssl.config.load import load_config, build_model
+
+cfg   = load_config("configs/ogbn_arxiv_bgrl.yaml")
+model = build_model(cfg, in_channels=128)
+```
+
+See `configs/` for reference YAML files and `examples/` for full benchmark scripts:
+
+| Script | Dataset | Task | Notes |
+|---|---|---|---|
+| `examples/cora_bgrl.py` | Cora | Node classification (7 classes) | Full-batch, CPU-friendly — fastest smoke test |
+| `examples/benchmark_planetoid.py` | Cora / CiteSeer / PubMed | Node classification, multi-seed | Reproduces the results below (`--seeds`, `--epochs`) |
+| `examples/ogbn_arxiv_bgrl.py` | ogbn-arxiv | Node classification (40 classes) | `NeighborLoader` mini-batch training |
+| `examples/zinc_bgrl.py` | ZINC-12k | Molecular property regression | Categorical node/edge embeddings |
+
+### Benchmark results (citation networks)
+
+BGRL, GIN-2L encoder (`hidden_dim=256`), full-batch training for 300 steps, public Planetoid split, mean ± std over 10 seeds (`python examples/benchmark_planetoid.py --dataset <name> --seeds 10`):
+
+| Dataset | Linear probe (test) | KNN k=5 (test) |
+|---|---|---|
+| Cora | 62.39 ± 3.71 | 58.61 ± 3.76 |
+| CiteSeer | 50.08 ± 1.58 | 43.07 ± 3.61 |
+| PubMed | 69.18 ± 2.32 | 66.59 ± 2.88 |
+
+This is a deliberately lightweight, untuned configuration (no per-dataset hyperparameter search) meant to validate that the training/evaluation pipeline is correct end-to-end — not a state-of-the-art claim. See `paper.tex` for a methodological comparison against the original BGRL paper's own numbers on these datasets. ogbn-arxiv and OGB graph-level benchmarks (ogbg-molhiv, ogbg-molpcba) require larger compute and are planned on dedicated infrastructure.
+
+---
+
+## Datasets with Categorical Features (ZINC)
+
+ZINC has integer node and edge features. Use `node_emb_num_classes` and `edge_emb_num_classes`
+to replace linear projections with `nn.Embedding`:
+
+```python
+config = {
+    "encoder": {
+        "name": "gin",
+        "hidden_dim": 64,
+        "num_layers": 4,
+        "norm_type": "layer",
+        "pool": True,
+        "node_emb_num_classes": 28,  # 28 atom types
+        "edge_dim": 64,
+        "edge_emb_num_classes": 4,   # 4 bond types
+    },
+    ...
+}
+model = BGRL(config, in_channels=1)  # in_channels ignored when node_emb_num_classes is set
+```
+
+---
+
+## Composable Losses
+
+Mix and weight multiple objectives without touching model code:
+
+```python
+from graphssl.losses import CombinedLoss
+
+loss_fn = CombinedLoss.from_config([
+    {"name": "nt_xent",  "weight": 0.7, "tau": 0.5},
+    {"name": "vicreg",   "weight": 0.3, "invariance": 25.0, "variance": 25.0, "covariance": 1.0},
+])
+loss = loss_fn(z1, z2)
+```
+
+---
+
+## Extending the Library
+
+All major components are registered by name and can be replaced via config:
+
+```python
+from graphssl.registry import ENCODERS, LOSSES, AUGMENTS
+
+@ENCODERS.register("my_gat")
+class GATEncoder(nn.Module):
+    ...
+
+# Then use it in any model config:
+config = {"encoder": {"name": "my_gat", "hidden_dim": 128, ...}, ...}
+```
+
+Models expose `compute_loss(batch)`, `post_backward()`, and `post_step()` hooks,
+so you can write your own training loop if needed:
+
+```python
+for batch in loader:
+    loss = model.compute_loss(batch)
+    loss.backward()
+    model.post_backward()
+    optimizer.step()
+    model.post_step()
+```
+
+---
+
+## Project Structure
+
+```
+src/graphssl/
+├── core/          # BaseSSLModel, Callback, Registry, Protocol interfaces
+├── config/        # Dataclass schemas + YAML loading (load_config, build_model)
+├── registry/      # ENCODERS, HEADS, AUGMENTS, LOSSES, LOADERS, OBJECTIVES, DATASETS
+├── encoders/      # GCN, GIN, Transformer (auto-registered)
+├── models/        # All SSL models + Supervised baseline
+├── losses/        # NT-Xent, DINO, VICReg, Barlow Twins, CosineRegression, CombinedLoss
+├── augmentation/  # 7 transforms, compose(), MultiView
+├── nn/            # MLP, Projector, Predictor, DINOHead, pooling
+├── evaluation/    # LogRegEvaluator, KNNEvaluator, extract_embeddings
+├── training/      # DINOTrainer + callbacks
+├── data/          # DataModule (full-batch and NeighborLoader)
+└── utils/         # update_ema_params, CosineDecayScheduler, CosineEMAScheduler, PositiveMiner
+```
+
+---
+
+## Key Design Choices
+
+- **Uniform API.** Every model is `ModelClass(config: Dict, in_channels: int)`. The config dict is validated by a dedicated dataclass in `schema.py`.
+- **Hook-driven training.** The trainer calls `post_backward()` and `post_step()` at fixed points. Models implement these to freeze prototype gradients (GraphDINO) or update the EMA teacher (BGRL, AFGRL) — without subclassing the trainer.
+- **Protected-node augmentations.** When using `NeighborLoader` for mini-batch training, seed nodes are shielded from `node_drop` so the loss remains valid.
+- **Registry pattern.** All components are registered by name (`@ENCODERS.register("gin")`), so swapping architectures is a one-line config change.
+- **Composable losses.** `CombinedLoss` enables weighted mixtures of any registered losses, configurable from YAML or programmatically.
+
+---
+
+## Acknowledgments
+
+Developed at [NECSTLab](https://necst.it), Politecnico di Milano.

graphssl-0.1.0/pyproject.toml

@@ -0,0 +1,118 @@
+[build-system]
+requires = ["setuptools>=77.0.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "graphssl"
+version = "0.1.0"
+description = "A modular Python library for Self-Supervised Learning on graphs, built on PyTorch and PyTorch Geometric."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    {name = "Simone Copetti", email = "copetti.simone7@gmail.com"},
+]
+keywords = [
+    "graph-learning",
+    "self-supervised-learning",
+    "gnn",
+    "pytorch-geometric",
+    "contrastive-learning",
+    "graph-neural-networks",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+# Core deps: only what is always required to import graphssl.
+# torch-scatter / torch-sparse are implicit via torch_geometric extras;
+# users install them separately following the PyG installation guide.
+dependencies = [
+    "torch>=2.0.0",
+    "torch_geometric>=2.3.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/Simocop7/graphssl"
+Repository = "https://github.com/Simocop7/graphssl"
+"Bug Tracker" = "https://github.com/Simocop7/graphssl/issues"
+Documentation = "https://github.com/Simocop7/graphssl#readme"
+
+[project.optional-dependencies]
+# Visualization: UMAP embeddings + matplotlib/seaborn plots
+viz = ["umap-learn", "matplotlib", "seaborn"]
+# Full: everything including AFGRL (faiss), benchmarks (ogb) and YAML configs (pyyaml)
+full = ["faiss-cpu", "umap-learn", "matplotlib", "seaborn", "ogb", "pyyaml"]
+# Minimal extras needed to run the benchmark example scripts
+benchmark = ["ogb", "pyyaml"]
+# Development: testing, building and publishing
+dev = ["pytest", "pytest-cov", "build", "twine", "pyyaml", "ruff", "mypy", "pre-commit"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["graphssl*"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+src = ["src", "tests", "examples"]
+# Don't reformat Python snippets embedded in prose docs (CLAUDE.md, README.md) —
+# ruff format's Markdown support would touch documentation content unrelated
+# to this tooling change.
+extend-exclude = ["*.md"]
+
+[tool.ruff.lint]
+# E/W: pycodestyle, F: pyflakes, I: isort, UP: pyupgrade, B: bugbear, C4: comprehensions
+select = ["E", "F", "W", "I", "UP", "B", "C4"]
+ignore = [
+    "E501",  # line length is handled by the formatter, not worth hard-failing on
+    # Typing modernization (List -> list, Optional[X] -> X | None) touches nearly
+    # every file for a purely cosmetic gain; deferred to a dedicated follow-up
+    # instead of bundling it into an unrelated tooling change. See CONTRIBUTING.md.
+    "UP006", "UP007", "UP035", "UP037", "UP045",
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["graphssl"]
+
+[tool.ruff.lint.per-file-ignores]
+# __init__.py files intentionally re-export names for the public API surface.
+"**/__init__.py" = ["F401"]
+
+[tool.ruff.format]
+quote-style = "double"
+
+[tool.coverage.run]
+source = ["src/graphssl"]
+branch = true
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]
+
+[tool.mypy]
+python_version = "3.10"
+ignore_missing_imports = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+no_implicit_optional = true
+# Incremental adoption: start lenient (no error on untyped defs across the whole
+# codebase yet), tightened module-by-module over time. See CONTRIBUTING.md.
+disallow_untyped_defs = false
+check_untyped_defs = true
+
+[[tool.mypy.overrides]]
+# Third-party deps without bundled type stubs.
+module = ["torch_geometric.*", "faiss.*", "sklearn.*", "umap.*", "ogb.*"]
+ignore_missing_imports = true

graphssl-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+