Pith. sign in

REVIEW 12 cited by

Think Locally, Act Globally: Federated Learning with Local and Global Representations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2001.01523 v3 pith:MI47VKV6 submitted 2020-01-06 cs.LG cs.DCstat.ML

Paul Pu Liang , Terrance Liu , Liu Ziyin , Nicholas B. Allen , Randy P. Auerbach , David Brent , Ruslan Salakhutdinov , Louis-Philippe Morency This is my paper
classification cs.LGcs.DCstat.ML
keywords localdataglobalmodelsrepresentationsdevicedevicesfederated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalization analysis which shows that a combination of local and global models reduces both variance in the data as well as variance across device distributions. Empirically, we demonstrate that local models enable communication-efficient training while retaining performance. We also evaluate on the task of personalized mood prediction from real-world mobile data where privacy is key. Finally, local models handle heterogeneous data from new devices, and learn fair representations that obfuscate protected attributes such as race, age, and gender.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Sharing class-relation topology with reliability weighting beats parameter, distillation, and prototype sharing under heterogeneous federated backbones on CIFAR and Tiny-ImageNet.

  2. Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Bidirectional Manifold Consistency measures geometric stability of dLLM trajectories and is claimed to indicate reasoning correctness for diagnosis, rejection sampling, and reward-based alignment.

  3. FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A federated LoRA fine-tuning method that builds a client-similarity tree and adapts aggregation depth layer-by-layer outperforms flat or global aggregation baselines on NLU and NLG tasks.

  4. Adaptive collaboration for online personalized distributed learning with heterogeneous clients

    stat.ML 2025-07 conditional novelty 6.0 of 10

    An adaptive gradient-similarity criterion dynamically selects collaboration partners in personalized federated learning, provably recovering the oracle-optimal sample complexity of All-for-one without knowing client h...

  5. Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A masked diffusion imputer plus dual distillation (MMFeD3-HidE) improves link prediction on a new federated multimodal knowledge graph benchmark with 50% missing visual/textual modalities.

  6. HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark

    cs.LG 2025-06 conditional novelty 6.0 of 10

    HtFLlib is a unified benchmark and library with 12 datasets, 40 heterogeneous model architectures, and systematic accuracy, convergence, and cost evaluations of 10 HtFL methods.

  7. PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes

    cs.LG 2026-01 conditional novelty 5.0 of 10

    A new federated transformer architecture uses personalized patch embeddings and a global variable-embedding table to forecast when different nodes have different sampling rates and variable sets.

  8. TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Compressing class prototypes with per-class masks and a sample-count scaling trick cuts communication cost in prototype-based federated learning by up to several times without hurting accuracy.

  9. Generalizable Federated Learning using Client Adaptive Focal Modulation

    cs.CV 2025-08 reject novelty 4.0 of 10

    The abstract describes AdaptFED, a claimed federated learning method, but the full text is an unrelated graph theory paper, so the claimed results are absent from the submission.

  10. Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A federated learning method that communicates only adapters and prototypes achieves accuracy close to the best adapter-only baseline while offering prototype-based visual explanations.

  11. PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems

    cs.MA 2025-06 reject novelty 4.0 of 10

    A decentralized multi-agent training method with a shared and a private adapter claims O(1/sqrt(NK)) convergence and big communication savings, but the evidence is incomplete.

  12. Heterogeneous Federated Learning with Prototype Alignment and Upscaling

    cs.LG 2025-07 conditional novelty 3.0 of 10

    ProtoNorm adds server-side prototype alignment and a per-dataset scaling factor to FedProto-style federated learning, improving accuracy but with the gain largely driven by the tuned scaling factor.

Pith tools