Pith Number

pith:DGFXGUW5

pith:2025:DGFXGUW5UVN6MP2LMNPQDGKDHB

not attested not anchored not stored refs resolved

Training speedups via batching for geometric learning: an analysis of static and dynamic algorithms

Claudia Draxl, Daniel T. Speckhard, Jonathan Godwin, Sebastian Kehl, Tim Bechtel

Changing the batching algorithm for graph neural networks can speed up training by up to 2.7 times, though the best choice depends on the data, model, batch size, hardware, and training length.

arxiv:2502.00944 v4 · 2025-02-02 · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DGFXGUW5UVN6MP2LMNPQDGKDHB}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Changing the batching algorithm can provide up to a 2.7x speedup, but the fastest algorithm depends on the data, model, batch size, hardware, and number of training steps run. For a select number of combinations of batch size, dataset, and model, significant differences in model learning metrics are observed between static and dynamic batching algorithms.

C2weakest assumption

The reported speedups and metric differences arise specifically from the choice of static versus dynamic batching rather than from unaccounted implementation details, hardware variability, or dataset-specific artifacts in the QM9 and AFLOW experiments.

C3one line summary

Experiments on QM9 and AFLOW datasets show that static and dynamic batching for GNNs can yield up to 2.7x training speedups depending on data, model, batch size, hardware, and training steps, with occasional differences in learning metrics.

References

41 extracted · 41 resolved · 7 Pith anchors

[1] ptgnn: A pytorch gnn library, 2022 2022

[2] T., GODWIN, J.,ANDDRAXL, C 2023

[3] BISHOP, C. M.,ANDNASRABADI, N. M.Pattern recognition and machine learning, vol. 4. Springer, 2006 2006

[4] The tradeoffs of large scale learning.Advances in neural information processing systems 20(2007) 2007

[5] Stochastic gradient learning in neural networks.Proceedings of Neuro- Nımes 91, 8 (1991), 12 1991

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-04T01:08:27.470650Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

198b7352dda55be63f4b635f019943386384d08be6cf71bceadc7a3815a83c9b

Aliases

arxiv: 2502.00944 · arxiv_version: 2502.00944v4 · doi: 10.48550/arxiv.2502.00944 · pith_short_12: DGFXGUW5UVN6 · pith_short_16: DGFXGUW5UVN6MP2L · pith_short_8: DGFXGUW5

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/DGFXGUW5UVN6MP2LMNPQDGKDHB \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 198b7352dda55be63f4b635f019943386384d08be6cf71bceadc7a3815a83c9b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4d4562b8b0a7b8be6ab5ef21d80dbeb047810d7dcc33beb76cb8e221d2901d52",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-02-02T22:34:17Z",
    "title_canon_sha256": "559f5d0046b7d9b1e144e9222a7fcc8f3b2f3a8917dba20dc36c93cf4af71862"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.00944",
    "kind": "arxiv",
    "version": 4
  }
}