AGENT SKILL

heterogeneous-graphs

Build and debug PyTorch Geometric heterogeneous graph data, loaders, HeteroConv models, to_hetero conversions, and hetero link-prediction workflows.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
heterogeneous-graphs
license
MIT
metadata
{ "disco-role": "operating" }
description
Build and debug PyTorch Geometric heterogeneous graph data, loaders, HeteroConv models, to_hetero conversions, and hetero link-prediction workflows.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Heterogeneous Graphs

Use this sub-skill when the task involves PyG HeteroData, typed metadata, heterogeneous mini-batches, HeteroConv, to_hetero, bipartite message passing, or heterogeneous link prediction.

Quick Routing

  • Read references/hetero-api.md when you need exact object shapes, metadata conventions, loader signatures, or model API choices for hetero graphs.
  • Read references/hetero-workflows.md when implementing a complete workflow: constructing HeteroData, converting a homogeneous SAGE-style model with to_hetero, hand-writing HeteroConv, using hetero loaders, or preparing link prediction splits.
  • Read references/troubleshooting.md when errors mention missing stores, invalid edge triplets, absent reverse edges, to_hetero metadata mismatch, or bipartite size inference.
  • Run scripts/hetero_metadata_check.py --help to inspect a safe synthetic validator for tiny HeteroData metadata and reverse-edge expectations.

Common Starting Points

  • Build a typed graph with data = HeteroData(), then assign node stores such as data['paper'].x and edge stores such as data['author', 'writes', 'paper'].edge_index.
  • Use node_types, edge_types = data.metadata() as the canonical metadata tuple for to_hetero, HeteroConv planning, and hetero loader dictionaries.
  • For mini-batch node tasks, pass hetero neighbor budgets as num_neighbors={edge_type: [fanout1, fanout2]} and set input_nodes=('paper', paper_indices).
  • For link prediction, keep forward and reverse relation names explicit, and pass matching edge_types and rev_edge_types to RandomLinkSplit when reverse edges exist.
  • For model conversion, prefer SAGEConv((-1, -1), hidden_channels) or other bipartite-capable layers in the homogeneous model before calling to_hetero(model, data.metadata(), aggr='sum').

Boundaries

  • For homogeneous Data, dataset classes, transforms, and basic graph validation, use the sibling data-and-datasets skill.
  • For generic training-loop design, metrics, pooling, and homogeneous GNN architecture choices, use the sibling gnn-modeling skill.
  • For distributed graph stores, remote backends, multi-GPU, or service-based sampling, use the sibling scalable-distributed skill.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351