Tan Chen

—

Unclaimed · AI-structured profileOpenAlex

Wireless-edge federated learning researcher: vehicular FL gradient efficiency and federated continual learning

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

—

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-09-20) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.

Research profile

Output—

No output data is available yet — the snapshot has no publication counts, venue list, or yearly production record. This axis would measure research volume and consistency, including papers per year and authorship roles, once a fuller record is linked.

Impact—

Impact cannot be scored: the snapshot contains no citation counts, h-index, or venue influence metrics. Once citation data is linked, this axis would measure how widely Tan Chen's federated learning and wireless edge work is cited and adopted.

Focus0/100

The focus score is 0 because the reviewed work splits evenly between two field labels: machine learning (federated learning and wireless edge systems) at 0.5, and wireless communications and machine learning (communication-efficient federated learning / vehicular edge intelligence) at 0.5. The two labels describe adjacent, overlapping problems, so the zero reflects taxonomy boundaries rather than genuinely scattered research interests.

Collaboration46/100

The collaboration score is 46, computed from 9 distinct coauthors in the underlying record. The same names recur — Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Yuxuan Bai, and Jintao Yan — indicating a stable core group rather than one-off partnerships. Both reviewed 2026 preprints place Tan Chen in a middle authorship position without corresponding-author status, consistent with contributing inside an established team.

Activity—

Activity is unscored: the record covers only two 2026 arXiv preprints with no multi-year dating. This axis would measure recent research tempo — papers per year, preprint-to-publication follow-through, and continuity of engagement over time.

Reproducibility38/100

Reproducibility averages 38 across the 2 papers reviewed so far. FedPGT is rated medium: simulation gains with a coherent theory-to-algorithm pipeline, but no variance reporting and narrow sparsification baselines. Sylvas is rated low, with a thin, simulation-only evaluation. Neither paper yet shows the open evidence — released code, variance statistics, broad baselines — that lifts reproducibility scores.

Research summary

Tan Chen is an early-stage researcher at the interface of machine learning and wireless communications, focused on communication-efficient federated learning at the wireless edge. The record holds two 2026 arXiv preprints, both with Tan Chen as a middle author and neither as corresponding author. FedPGT targets vehicular federated learning over time-varying channels, progressively uploading dominant gradient entries slot-by-slot with Lyapunov-based resource allocation and convergence analysis; Evolve credits a coherent theory-to-algorithm pipeline with simulation gains but flags missing variance reporting and narrow sparsification baselines. Sylvas proposes a federated continual learning device scheduler built on a synergistic learning value combining drift, collective divergence, and pseudo-label value — a sound, magazine-style concept whose evaluation stays simulation-only and thin. The field distribution splits evenly between two adjacent labels — federated learning with wireless edge systems, and communication-efficient federated learning with vehicular edge intelligence — producing a focus score of 0 that mirrors labeling overlap more than scattered interests. Collaboration is moderate at 46 across 9 distinct coauthors, with a recurring core team of Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Yuxuan Bai, and Jintao Yan. Reproducibility averages 38 across the two papers. With output, impact, and activity unscored, this remains an early-stage profile.

Collaboration pattern

The record shows 9 distinct coauthors and a collaboration score of 46. Recurring names — Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Yuxuan Bai, and Jintao Yan — point to a stable core team rather than a wide ad-hoc network. Both reviewed 2026 preprints list Tan Chen in a middle authorship position without corresponding-author status.

Research keywords

vehicular federated learninggradient sparsificationtime-varying channelsLyapunov optimizationresource allocationconvergence analysisfederated continual learningdevice schedulingedge intelligencesemi-supervised learningpseudo-labelingcatastrophic forgetting

Highlights

Progressive gradient transmission for vehicular federated learning over time-varying channels
In the 2026 arXiv preprint FedPGT, Tan Chen (middle author) contributes to a scheme that progressively uploads dominant gradient entries slot-by-slot under time-varying channels, supported by Lyapunov-based resource allocation and convergence analysis. Evolve's verdict: a coherent theory-to-algorithm pipeline with simulation gains, but no variance reporting and narrow sparsification baselines; reproducibility readiness is medium.
Synergistic learning value for device scheduling in federated continual learning
The 2026 arXiv preprint Sylvas (Tan Chen, middle author) proposes a device scheduler for federated continual learning driven by a synergistic learning value combining drift, collective divergence, and pseudo-label value, set in edge intelligence with semi-supervised cues. Evolve judges the concept sound but the evaluation simulation-only and thin; reproducibility readiness is low.

Timeline

2026FedPGT arXiv preprint appears, introducing progressive gradient transmission for vehicular federated learning over time-varying channels (Tan Chen, middle author).
2026Sylvas arXiv preprint appears, proposing synergistic-learning-value based device scheduling for federated continual learning (Tan Chen, middle author).
2026Both reviewed papers land in the same year, consolidating a research focus on communication-efficient federated learning at the wireless edge.

Papers in the Evolve catalog

Frequent co-authors

Yuxuan Sun×2 Sheng Zhou×2 Zhisheng Niu×2 Yuxuan Bai×1 Yuxuan Sun×1 Tan Chen×1 Sheng Zhou×1 Zhisheng Niu×1 Jintao Yan×1

About this profile

This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.

Radar scores are computed from public bibliometric data (OpenAlex-sourced) only; no citation counts, h-index, or venue metrics are in this snapshot, so output, impact, and activity are unscored.
Tan Chen is a common name; this profile is name-resolved from public bibliographic data, and no ORCID, institution, or country could be confirmed.
Only two 2026 arXiv preprints have been reviewed, so the reproducibility reading (2 papers, mean 38) rests on thin evidence and may change as the catalog grows.
Authorship position (middle) and corresponding-author status follow Evolve's review records; full author lists and individual contribution details are not available.