Early-career SJTU researcher advancing relational table learning with graph neural networks and attention mechanisms
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
0
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
Not yet scored. This axis measures publication volume and productivity over time; with h-index 0, i10-index 0, and all indexed works dated 2026, the record is too early-stage for a reliable output estimate.
Impact—
Not yet scored. This axis measures citation-based influence via citations, h-index and i10-index; the record shows h-index 0 and i10-index 0 with 2026-dated work, leaving no meaningful citation window, so no impact score is estimated.
Focus0/100
Scores 0 on focus. The field distribution splits evenly (0.5 / 0.5) between 'machine learning (tabular and relational data learning)' and 'machine learning — graph learning on relational databases', so the metric records minimal concentration; in practice the two labels describe the same relational-table-learning theme, suggesting the low score reflects label granularity more than genuinely scattered interests.
Collaboration36/100
Scores 36 on collaboration. The OpenAlex record lists 5 distinct co-authors in the recent window, with a tight recurring group — Weichen Li, Zheng Wang, Li Pan and Jianhua Li — indicating work within a small, stable team rather than wide external networks. Both catalog papers are multi-authored arXiv efforts, with first authorship on MetaRTL and a middle position on InRTL, and no corresponding-author credit recorded, consistent with an early-career collaboration pattern.
Activity52/100
Scores 52 on activity, a moderate level. The snapshot counts 5 works in the last three years (recent3yWorks = 5), and the per-year record attributes all 5 to 2026, indicating a burst of output concentrated in the current year rather than a sustained multi-year cadence — consistent with an indexed publication record that has only just begun.
Reproducibility55/100
Scores 55 on reproducibility, computed from Evolve's review of 2 papers (reproMean = 55, reproPapers = 2). Both MetaRTL and InRTL carry a medium repro-readiness rating: MetaRTL reports broad state-of-the-art claims across 24 tasks but omits seed variance and runtime-baseline comparisons, while InRTL's benchmark wins are described as razor-thin and lacking variance or significance tests.
Research summary
Ken Zhong is an early-stage machine learning researcher at Shanghai Jiao Tong University whose indexed work centers on relational table learning — applying graph neural networks and attention mechanisms to tabular data stored in relational databases. The Evolve catalog contains two 2026 arXiv preprints: MetaRTL, where Zhong is first author and proposes two-stage meta-path attention with state-of-the-art claims across 24 tasks, and InRTL, a middle-authorship paper unifying intra- and inter-table attention through linearized attention and heterogeneous GNNs. OpenAlex topics reinforce this concentration — 'Advanced Database Systems and Queries' (4 hits), 'Data Mining Algorithms and Applications' (2), and 'Advanced Graph Neural Networks' (2) — while the field distribution splits evenly between tabular/relational machine learning and graph learning on relational databases. Activity is moderate (score 52): 5 works in the last three years, all dated 2026, produced with a compact set of 5 distinct co-authors including Weichen Li, Zheng Wang, Li Pan and Jianhua Li. Citation impact is not yet scoreable, with h-index and i10-index both 0, and reproducibility scores 55 across the 2 reviewed papers, both rated medium.
Collaboration pattern
Ken Zhong's collaboration footprint is compact: 5 distinct co-authors in the OpenAlex window, dominated by a recurring group of Weichen Li, Zheng Wang, Li Pan and Jianhua Li. The two 2026 arXiv papers are team products — first authorship on MetaRTL and a middle position on InRTL — with no corresponding-author credit recorded, indicating work inside a small, stable team rather than dispersed external partnerships.
Research keywords
Highlights
MetaRTL: first-authored meta-path attention for relational table learning
InRTL: unifying intra- and inter-table attention
Timeline
- 2026First-authored MetaRTL posted to arXiv, proposing meta-path attention enhanced relational table learning.
- 2026Co-authored InRTL posted to arXiv, unifying intra- and inter-table interaction learning for relational tables.
- 2026OpenAlex records 5 works in this year — the earliest, and so far only, year in the indexed publication record.
Papers in the Evolve catalog
Frequent co-authors
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.
- Identity and bibliometrics are name-resolved from OpenAlex, with ORCID 0009-0002-0429-7473; no other citation indexes are reflected.
- h-index 0 and i10-index 0 mean the output and impact axes are unscored; this reflects an early-stage record, not a negative finding.
- Both catalog papers are 2026 arXiv preprints; peer-review status and publication venues are unknown from the provided data.
- The co-author record lists 'Zheng Wang' twice, likely a duplicate name entry, so the distinct co-author count may vary slightly.