Pith Number

pith:JC6IYE4D

pith:2019:JC6IYE4DGRH5EMDF2BIERXPYPS

not attested not anchored not stored refs pending

Federated Learning with Personalization Layers

Aaditya Kumar Singh, Manoj Ghuhan Arivazhagan, Sunav Choudhary, Vinay Aggarwal

Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.

arxiv:1912.00818 v1 · 2019-12-02 · cs.LG · cs.DC · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JC6IYE4DGRH5EMDF2BIERXPYPS}

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

FedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, can combat the ill-effects of statistical heterogeneity.

C2weakest assumption

That splitting the network into shared base layers and local personalization layers is sufficient to overcome statistical heterogeneity without needing additional regularization or adaptation mechanisms.

C3one line summary

FedPer uses shared base layers and per-user personalization layers to enable effective federated training of deep networks despite non-identical data distributions.

Formal links

2 machine-checked theorem links

Cited by

24 papers in Pith

Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions

Inpatient Overflow Management with Proximal Policy Optimization

Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection

FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs

Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis

Receipt and verification

First computed	2026-05-18T03:38:44.381648Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f

Aliases

arxiv: 1912.00818 · arxiv_version: 1912.00818v1 · doi: 10.48550/arxiv.1912.00818 · pith_short_12: JC6IYE4DGRH5 · pith_short_16: JC6IYE4DGRH5EMDF · pith_short_8: JC6IYE4D

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/JC6IYE4DGRH5EMDF2BIERXPYPS \
  | 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: 48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2aeb3a4804dda085f6efdf618d4e061bc3d1137aac260836dc6e5601ada5daa0",
    "cross_cats_sorted": [
      "cs.DC",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2019-12-02T14:29:00Z",
    "title_canon_sha256": "aaff00967d94412e74e8775461e4dd1f418194cb3260248c9afd35e76343df94"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1912.00818",
    "kind": "arxiv",
    "version": 1
  }
}