Pith Number

pith:JC3BMPH4

pith:2026:JC3BMPH4F7VKIOE6ECLJZ7M7X5

not attested not anchored not stored refs resolved

FedHPro: Federated Hyper-Prototype Learning via Gradient Matching

Di Wu, Guansong Pang, Haoran Li, Huan Wang, Jun Shen, Jun Yan, Ousman Manjang, Yanlong Zhai, Zhenyu Yang

Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.

arxiv:2605.13475 v1 · 2026-05-13 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JC3BMPH4F7VKIOE6ECLJZ7M7X5}

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

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

hyper-prototypes produce a more semantically consistent global signal, and FedHPro achieves state-of-the-art performance on several benchmark datasets under diverse heterogeneous scenarios.

C2weakest assumption

That matching gradients computed on real client samples will align hyper-prototypes more reliably than averaging local prototypes, without introducing new privacy leakage or optimization instability.

C3one line summary

FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.

References

14 extracted · 14 resolved · 0 Pith anchors

[1] Geodesic flow kernel for unsupervised domain adaptation 2066

[2] Learning support and trivial prototypes for interpretable image classification 2062

[3] 12 FedHPro: Federated Hyper-Prototype Learning via Gradient Matching A. Algorithm Pseudo-code Flow In this section, we describe the pseudo-code of our FedHPro in Algorithm 1: 1)Server-Side: we optimiz 2023

[4] for the TinyImageNet dataset. The label skew heterogeneity level of clients is controlled by the standard deviation α of the Dirichlet distribution, and the quantity skew heterogeneity level is contro 2021

[5] is used for skin lesion classification and contains 8,912 training samples and 1,103 testing samples with 7 categories, and each sample’s size is scaled to224∗224 . Then, based on (Kaidi et al., 2019) 2019

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:41.477777Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200

Aliases

arxiv: 2605.13475 · arxiv_version: 2605.13475v1 · doi: 10.48550/arxiv.2605.13475 · pith_short_12: JC3BMPH4F7VK · pith_short_16: JC3BMPH4F7VKIOE6 · pith_short_8: JC3BMPH4

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/JC3BMPH4F7VKIOE6ECLJZ7M7X5 \
  | 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: 48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e275fcd8e2594af598ec74a40670d98ccc5b857a4b42cd81479f0d2c576feed5",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T13:01:17Z",
    "title_canon_sha256": "9b20bcc00b31ee7d534a365f5943e681d1fe1ab3e2e3983be80dd4d006f482ae"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13475",
    "kind": "arxiv",
    "version": 1
  }
}