Pith Number

pith:ILK7VY6J

pith:2018:ILK7VY6J7ZIUPP4333ZMLUDFCV

not attested not anchored not stored refs resolved

Federated Learning with Non-IID Data

Damon Civin, Liangzhen Lai, Meng Li, Naveen Suda, Vikas Chandra, Yue Zhao

A small globally shared data subset recovers up to 30% accuracy lost to non-IID data in federated learning.

arxiv:1806.00582 v2 · 2018-06-02 · cs.LG · 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{ILK7VY6J7ZIUPP4333ZMLUDFCV}

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

Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.

C2weakest assumption

That a small globally shared data subset can be created and distributed without violating the privacy or regulatory constraints that motivated federated learning in the first place.

C3one line summary

Non-IID data causes up to 55% accuracy loss in federated learning due to weight divergence measured by earth mover's distance; 5% globally shared data recovers 30% accuracy on CIFAR-10.

References

23 extracted · 23 resolved · 7 Pith anchors

[1] Hello edge: Keyword spotting on microcontrollers 2017 · arXiv:1711.07128

[2] CMSIS-NN: Efficient neural network kernels for ARM Cortex-M CPUs 2018 · arXiv:1801.06601

[3] Communication-efﬁcient learning of deep networks from decentralized data, 2017

[4] Federated optimization: Dis- tributed optimization beyond the datacenter.arXiv preprint arXiv:1511.03575 2015 · arXiv:1511.03575

[5] Federated learning: Collaborative machine learning without centralized training data, 2017

Formal links

2 machine-checked theorem links

Cited by

31 papers in Pith

FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning

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

Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning

Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning

REVERB-FL: Server-Side Adversarial and Reserve-Enhanced Federated Learning for Robust Audio Classification

Receipt and verification

First computed	2026-05-17T23:38:48.204579Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

42d5fae3c9fe5147bf9bdef2c5d065154555329e5ab2e379c17ab4bf747f2eb6

Aliases

arxiv: 1806.00582 · arxiv_version: 1806.00582v2 · doi: 10.48550/arxiv.1806.00582 · pith_short_12: ILK7VY6J7ZIU · pith_short_16: ILK7VY6J7ZIUPP43 · pith_short_8: ILK7VY6J

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/ILK7VY6J7ZIUPP4333ZMLUDFCV \
  | 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: 42d5fae3c9fe5147bf9bdef2c5d065154555329e5ab2e379c17ab4bf747f2eb6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9966f33a42ee725d7f8da443d95995915eee321865583111c457d6b57714106f",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2018-06-02T04:45:58Z",
    "title_canon_sha256": "60793869653bc39cf520f01906c6876ef56ef521c0e3466b865e029107c2ebac"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1806.00582",
    "kind": "arxiv",
    "version": 2
  }
}