Pith Number

pith:RLTYJFME

pith:2026:RLTYJFMEGC7H4G3TA5UWNDO75B

not attested not anchored not stored refs resolved

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

Guoren Wang, Haonan Wang, Hongchao Qin, Rong-Hua Li, Shumeng Li, Sirui Zhang, Xunkai Li, Zekai Chen

FedMPO recovers missing modalities in federated multimodal graphs using topology context and reliability-weighted aggregation.

arxiv:2605.12584 v1 · 2026-05-12 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RLTYJFMEGC7H4G3TA5UWNDO75B}

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

Extensive experiments on 3 tasks across 6 datasets demonstrate that FedMPO outperforms baselines, achieving performance gains of up to 4.10% and 5.65% in high-missing and non-IID settings.

C2weakest assumption

That client-side topology-aware generation can reliably recover missing modalities from local graph context alone and that the reliability metric used for server aggregation accurately reflects true update quality without introducing new selection bias.

C3one line summary

FedMPO recovers missing modalities via topology-aware generation, filters noisy recoveries with missing-aware routing, and uses reliability-aware aggregation to achieve up to 5.65% gains over baselines in high-missing and non-IID federated graph settings.

References

39 extracted · 39 resolved · 1 Pith anchors

[1] Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) , series =

[2] Proceedings of Machine Learning and Systems , volume =

[3] Proceedings of the 37th International Conference on Machine Learning (ICML) , series =

[4] Machine Learning and Knowledge Discovery in Databases

[5] and Le Nguyen, Phuong and Huynh, Trung Tin , title = 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:10:01.390773Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8ae784958430be7e1b730769668ddfe8476b9e229c29b85eee7321611ef60844

Aliases

arxiv: 2605.12584 · arxiv_version: 2605.12584v1 · doi: 10.48550/arxiv.2605.12584 · pith_short_12: RLTYJFMEGC7H · pith_short_16: RLTYJFMEGC7H4G3T · pith_short_8: RLTYJFME

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/RLTYJFMEGC7H4G3TA5UWNDO75B \
  | 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: 8ae784958430be7e1b730769668ddfe8476b9e229c29b85eee7321611ef60844

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d9019523ab3d6f8a94ae9cb00dfa8eb5512b2061462e18ed0a91c6e4c5ad91f7",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T17:30:15Z",
    "title_canon_sha256": "d30f037e7417ed359c3c399d7c54e871960abc3a0feee58bd01e9d1e7103d55b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12584",
    "kind": "arxiv",
    "version": 1
  }
}