Pith Number

pith:VZAZBDIC

pith:2019:VZAZBDIC752UTMEZASMQWQ7JBA

not attested not anchored not stored refs resolved

Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification

Hang Qi, Matthew Brown, Tzu-Ming Harry Hsu

Non-identical data distributions degrade federated averaging performance on visual tasks, but server momentum recovers most of the accuracy loss.

arxiv:1909.06335 v1 · 2019-09-13 · cs.LG · cs.CV · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VZAZBDIC752UTMEZASMQWQ7JBA}

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

Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.

C2weakest assumption

The synthetic non-identical datasets created by the authors accurately capture the statistical heterogeneity present in real-world federated visual data collected from mobile devices.

C3one line summary

Non-identical data distributions degrade federated averaging accuracy on visual classification, but server momentum raises CIFAR-10 accuracy from 30.1% to 76.9% in the most skewed regimes.

References

20 extracted · 20 resolved · 4 Pith anchors

[3] Learning multiple layers of features from tiny images 2009

[4] International Conference on Learning Representations , year = 1907

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

[6] Gradient methods for minimizing composite objective function 2007

[10] Advanced convolutional neural networks

Formal links

1 machine-checked theorem link

Cited by

19 papers in Pith

On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning

Random Walk Learning and the Pac-Man Attack

Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data

DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning

DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training

Receipt and verification

First computed	2026-05-17T23:38:13.504555Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ae41908d02ff7549b09904990b43e908350564c0858783c17d226d1d1b63b6ae

Aliases

arxiv: 1909.06335 · arxiv_version: 1909.06335v1 · doi: 10.48550/arxiv.1909.06335 · pith_short_12: VZAZBDIC752U · pith_short_16: VZAZBDIC752UTMEZ · pith_short_8: VZAZBDIC

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/VZAZBDIC752UTMEZASMQWQ7JBA \
  | 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: ae41908d02ff7549b09904990b43e908350564c0858783c17d226d1d1b63b6ae

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ea16202aaf1c40a1a276d37b9147b273854430fed81d2d85e909613bdca48229",
    "cross_cats_sorted": [
      "cs.CV",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2019-09-13T17:26:20Z",
    "title_canon_sha256": "bdf8dc665285f408ac522b864cb845415d7e8dfc30ccbca9450d38eaf2efea69"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1909.06335",
    "kind": "arxiv",
    "version": 1
  }
}