ARXIV:2603.04194 · FEDERATED LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

arXiv

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon…

METHOD

Full abstract

Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training. Various client selection strategies have been developed to align the volatility of renewable energy with stable and fair model training in a federated system. However, due to the privacy-preserving nature of Federated Learning, the quality of data on client devices remains unknown, posing challenges for effective model training. In this paper, we introduce a modular approach on top to state-of-the-art client selection strategies for carbon-efficient Federated Learning. Our method enhances robustness by incorporating a noisy client data filtering, improving both model performance and sustainability in scenarios with unknown data quality. Additionally, we explore the impact of carbon budgets on model convergence, balancing efficiency and sustainability. Through extensive evaluations, we demonstrate that modern client selection strategies based on local client loss tend to select clients with noisy data, ultimately degrading model performance. To address this, we propose a gradient norm thresholding mechanism using probing rounds for more effective client selection and noise detection, contributing to the practical deployment of carbon-efficient Federated Learning.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training.

WHY NOW

Federated Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainNoise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2603.04194 · FEDERATED LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

arXiv

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Federated Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainNoise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.04194

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback21 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Federated Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the carbon footprint of AI training.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Federated Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Federated Learning

Competitors

not indexed

Competitive landscape

Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.

Segment

Federated Learning

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.04194 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(21)

Data-driven Algorithm Selection for Carbon-Aware Scheduling

2024Roozbeh Bostandoost, Walid A. Hanafy et al.

CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers✱

2023Jieming Bian, Lei Wang et al.

Critical Learning Periods Emerge Even in Deep Linear Networks

2023Michael Kleinman, A. Achille et al.

CriticalFL: A Critical Learning Periods Augmented Client Selection Framework for Efficient Federated Learning

2023Gang Yan, Hao Wang et al.

On the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the Cloud

2023Thanathorn Sukprasert, Abel Souza et al.

FedZero: Leveraging Renewable Excess Energy in Federated Learning

2023Philipp Wiesner, R. Khalili et al.

Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model

2022A. Luccioni, S. Viguier et al.

ACT: designing sustainable computer systems with an architectural carbon modeling tool

2022Udit Gupta, Mariam Elgamal et al.

Critical Learning Periods in Federated Learning

2021Gang Yan, Hao Wang et al.

Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning

2021Xinyi Xu, L. Lyu et al.

Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies

2020Yae Jee Cho, Jianyu Wang et al.

A Principled Approach to Data Valuation for Federated Learning

2020Tianhao Wang, Johannes Rausch et al.

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

2019Minghong Fang, Xiaoyu Cao et al.

Coresets for Data-efficient Training of Machine Learning Models

2019Baharan Mirzasoleiman, J. Bilmes et al.

Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence

2019Aditya Golatkar, A. Achille et al.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

2019Mingxing Tan, Quoc V. Le

Dealing with Noise Problem in Machine Learning Data-sets: A Systematic Review

2019Shivani Gupta, Atul Gupta

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length

2018Stanislaw Jastrzebski, Zachary Kenton et al.

Critical Learning Periods in Deep Neural Networks

2017A. Achille, Matteo Rovere et al.

Communication-Efficient Learning of Deep Networks from Decentralized Data

2016H. B. McMahan, Eider Moore et al.

Showing 20 of 21 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

none indexed

Extension

none indexed

Commercially relevant

Higher ViabilityFedLECC: Cluster- and Loss-Guided Client Selection for Federated Learning under Non-IID Data

6.0

Higher ViabilityFedZMG: Efficient Client-Side Optimization in Federated Learning

7.0

Higher ViabilityFedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation

7.0

Higher ViabilityClient-Conditional Federated Learning via Local Training Data Statistics

7.0

Higher ViabilityData-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

7.0

Higher ViabilityFedDES: Graph-Based Dynamic Ensemble Selection for Personalized Federated Learning

7.0

Higher ViabilityResource-Adaptive Federated Text Generation with Differential Privacy

7.0

Higher ViabilitySubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport

7.0

Conflicting

Competing ApproachFedVG: Gradient-Guided Aggregation for Enhanced Federated Learning

5.0

Competing ApproachEnhancing Robustness of Federated Learning via Server Learning

4.0

Related Resources

Hierarchical Federated Learning(glossary)
Federated Learning(glossary)
What are the considerations for optimizing NLP models in a federated learning setting?(question)
How can machine unlearning be applied to federated learning systems?(question)
How can graph neural networks be adapted for federated learning scenarios on distributed graph data?(question)

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.04194
Route: /paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding
Active tab: read
Artifact: noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding/paper-pack
REST build passport API/api/v1/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "8066cfa0-2af3-460b-ac79-855d0ec08292",
  "arxiv_id": "2603.04194",
  "canonical_route": "/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
  "endpoints": {
    "paper_pack": "/api/v1/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding/paper-pack",
    "build_passport": "/api/v1/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Canonical ID noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding | Route /paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.04194"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding",
  "normalized_query": "2603.04194",
  "route": "/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
  "paper_ref": "noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

/buildability/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

Watchwatch

Subject: Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

Paper ref

noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding

arXiv id

2603.04194

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

a80e1faf8a59419e8754ea81bb2c4bbfb66fd08914756ceb584de78aa3fe5e86

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding#webpage",
      "url": "https://sciencetostartup.com/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
      "name": "Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding",
      "description": "Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding#scholarlyArticle",
      "headline": "Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding",
      "description": "Noise-aware client selection improves carbon efficiency and robustness in Federated Learning through gradient norm thresholding.",
      "url": "https://sciencetostartup.com/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding",
      "sameAs": "https://arxiv.org/abs/2603.04194",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.04194"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-04T15:43:48.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a3411bb591ca25d6737bcc554aa57e92ece37bba"
          },
          "url": "https://www.semanticscholar.org/paper/a3411bb591ca25d6737bcc554aa57e92ece37bba"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "18c7495caaed44e77715fcd007e04e7f8a72cab2"
          },
          "url": "https://www.semanticscholar.org/paper/18c7495caaed44e77715fcd007e04e7f8a72cab2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6bfd69154625da38241c56690f65f19d22f7763d"
          },
          "url": "https://www.semanticscholar.org/paper/6bfd69154625da38241c56690f65f19d22f7763d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "46541da449d6468980c7b37825404f84ef4e042a"
          },
          "url": "https://www.semanticscholar.org/paper/46541da449d6468980c7b37825404f84ef4e042a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8c38d84c1875d0552ff76a4ea5e0460624bbd26f"
          },
          "url": "https://www.semanticscholar.org/paper/8c38d84c1875d0552ff76a4ea5e0460624bbd26f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cdfbf55a5ea0c3602c957f4c183bbc475e85ac9f"
          },
          "url": "https://www.semanticscholar.org/paper/cdfbf55a5ea0c3602c957f4c183bbc475e85ac9f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bd8412c233bf3815d8e905911b58e12bd6f279da"
          },
          "url": "https://www.semanticscholar.org/paper/bd8412c233bf3815d8e905911b58e12bd6f279da"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5c6f8f980e01085672dfa03309b9973b002f93cd"
          },
          "url": "https://www.semanticscholar.org/paper/5c6f8f980e01085672dfa03309b9973b002f93cd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e5ec04b519d6c626100093a8ef12465f38fdc7e9"
          },
          "url": "https://www.semanticscholar.org/paper/e5ec04b519d6c626100093a8ef12465f38fdc7e9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e245f15bdddac514454fecf32f2a3ecb069f6dec"
          },
          "url": "https://www.semanticscholar.org/paper/e245f15bdddac514454fecf32f2a3ecb069f6dec"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7c3fe0f79f3a665c634e5d7b37f3a6b5b1d6c506"
          },
          "url": "https://www.semanticscholar.org/paper/7c3fe0f79f3a665c634e5d7b37f3a6b5b1d6c506"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0a1574ce29eec463bd3e0b50b82157f3e5a1f81d"
          },
          "url": "https://www.semanticscholar.org/paper/0a1574ce29eec463bd3e0b50b82157f3e5a1f81d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "790985a4bee821046992ff3d5322ff11dd1b4262"
          },
          "url": "https://www.semanticscholar.org/paper/790985a4bee821046992ff3d5322ff11dd1b4262"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0c386e6cf5650457eee64c55afdb3e8f98824fae"
          },
          "url": "https://www.semanticscholar.org/paper/0c386e6cf5650457eee64c55afdb3e8f98824fae"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4f2eda8077dc7a69bb2b4e0a1a086cf054adb3f9"
          },
          "url": "https://www.semanticscholar.org/paper/4f2eda8077dc7a69bb2b4e0a1a086cf054adb3f9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5f9e2f6d4a844189b2e34da8fd0ba282f3f36c6f"
          },
          "url": "https://www.semanticscholar.org/paper/5f9e2f6d4a844189b2e34da8fd0ba282f3f36c6f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3124a3a6fed01e2ce200defb23c8ca1f5f78d6ce"
          },
          "url": "https://www.semanticscholar.org/paper/3124a3a6fed01e2ce200defb23c8ca1f5f78d6ce"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d1dbf643447405984eeef098b1b320dee0b3b8a7"
          },
          "url": "https://www.semanticscholar.org/paper/d1dbf643447405984eeef098b1b320dee0b3b8a7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "91d6ef180179a8c91ed6ad6a86a2b39b751435e5"
          },
          "url": "https://www.semanticscholar.org/paper/91d6ef180179a8c91ed6ad6a86a2b39b751435e5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "62637bf5efddcedb6507853490c28b66b425fd49"
          },
          "url": "https://www.semanticscholar.org/paper/62637bf5efddcedb6507853490c28b66b425fd49"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Federated Learning"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Federated Learning",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Noise-aware Client Selection for carbon-efficient Federated ",
          "item": "https://sciencetostartup.com/paper/noise-aware-client-selection-for-carbon-efficient-federated-learning-via-gradient-norm-thresholding"
        }
      ]
    }
  ]
}

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(21)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(21)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline