pith. sign in
Pith Number

pith:X5JBXBVX

pith:2026:X5JBXBVXHFBPHJXKHLOLQ5K2PC
not attested not anchored not stored refs pending

Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective

Chuan Wu, Da Zheng, Junwei Su, Mengfan Liu

Full-graph GNN training does not always outperform well-tuned mini-batch training in performance or efficiency.

arxiv:2601.22678 v3 · 2026-01-30 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{X5JBXBVXHFBPHJXKHLOLQ5K2PC}

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

full-graph training does not always yield better model performance or computational efficiency than well-tuned smaller mini-batch settings.

C2weakest assumption

The Wasserstein-distance generalization bound accurately captures the impact of fan-out size across diverse GNN architectures and graph datasets used in the empirical study.

C3one line summary

Full-graph GNN training does not always outperform well-tuned mini-batch training in model performance or computational efficiency when viewed through batch and fan-out sizes.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-20T00:03:03.949674Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

bf521b86b73942f3a6ea3adcb8755a789183598ed1b56fb1005bc8e8445199b8

Aliases

arxiv: 2601.22678 · arxiv_version: 2601.22678v3 · doi: 10.48550/arxiv.2601.22678 · pith_short_12: X5JBXBVXHFBP · pith_short_16: X5JBXBVXHFBPHJXK · pith_short_8: X5JBXBVX
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/X5JBXBVXHFBPHJXKHLOLQ5K2PC \
  | 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: bf521b86b73942f3a6ea3adcb8755a789183598ed1b56fb1005bc8e8445199b8
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "15c7f072f0f0c6da1ab326058759adeabe0eeaba6541382e96c7fa412aa928b7",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-01-30T07:51:38Z",
    "title_canon_sha256": "6b486a829407205bdc19e52fc4190d21d656c28d889c7dfedba4ec25f5f21d66"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.22678",
    "kind": "arxiv",
    "version": 3
  }
}