REVIEW 15 cited by
REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
Not yet reviewed by Pith; the record is open.
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
REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
read the original abstract
Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a "parent" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent table using a sequence-to-sequence (Seq2Seq) model. We implement target masking to prevent data copying and propose the $Q_{\delta}$ statistic and statistical bootstrapping to detect overfitting. Experiments using real-world datasets show that REaLTabFormer captures the relational structure better than a baseline model. REaLTabFormer also achieves state-of-the-art results on prediction tasks, "out-of-the-box", for large non-relational datasets without needing fine-tuning.
Forward citations
Cited by 15 Pith papers
-
Cross-Flow Correlations Survive Synthesis: Measuring Source-Level Privacy Leakage in Synthetic Network Traces
Synthetic network generators preserve cross-flow correlations enabling source-level membership inference, shown via the TraceBleed attack across five datasets and six generators.
-
TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data
Across 49 datasets and 11 generators, distance-based fidelity overstates synthetic tabular quality: best query-centric score is only 0.75, with systematic failures on high-cardinality support, local conditionals, and ...
-
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
ICL in LLMs shows a sharp ceiling on categorical distributions for high-cardinality tabular data, failing to reproduce rare classes despite examples, while numerical fidelity improves.
-
HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds
HH-SAE factorizes manifolds into nested contextual (L0), atomic (f1), and compository (f2) tiers, achieving 0.9156 cross-domain zero-shot AUC in fraud detection and +9.9% AUPRC lift in steered synthesis.
-
Concordia: Self-Improving Synthetic Tables for Federated LLMs
Concordia aligns synthetic table generation with federated validation utility via client-side utility scorers and group-relative policy optimization to improve LLM adaptation on non-IID tabular tasks.
-
The Power of Order: Fooling LLMs with Adversarial Table Permutations
Semantically invariant row and column permutations can fool LLMs on tabular tasks, and a new gradient-based attack called ATP finds such permutations to significantly degrade performance across models.
-
Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Setting
MT-MIA uses heterogeneous graph neural networks under a No-Box model to expose user-level membership leakage in synthetic relational data that single-table attacks underestimate.
-
Making Logic a First-Class Citizen in Generative ML for Networking
NetNomos is a multi-stage framework that extracts, filters, and enforces first-order logic rules in generative ML models for networking tasks including telemetry imputation, traffic forecasting, and synthetic trace ge...
-
LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
LLM-TabLogic extracts inter-column logical constraints using LLMs and conditions a score-based latent diffusion model on them to generate synthetic tabular data that preserves those relationships.
-
Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval
Permutation-invariant fine-tuning (PI-FT) randomizes field order and applies dropout during embedding model training to eliminate sensitivity to serialization order, reducing order-change penalty from 7.4 to 0.2 nDCG@...
-
The Power of Order: Fooling LLMs with Adversarial Table Permutations
Semantically invariant row and column permutations in tables can cause LLMs to output incorrect answers, and a gradient-based attack called ATP efficiently finds such permutations that degrade performance across many models.
-
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
RDDG is an in-context learning system with dynamic guidance and automatic quality feedback that synthesizes high-fidelity relational data to improve imbalanced classification.
-
Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss
Seq. RC-TGAN adds a spectral envelope loss to RC-TGAN and uses VGM discretization plus simulated benchmarks with known envelopes to generate relational time series that better match frequency-domain features.
-
PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization
PSyGenTAB is a constrained-optimization framework that generates privacy-preserving synthetic clinical tabular data while preserving clinical relationships and downstream model performance.
-
Concordia: Self-Improving Synthetic Tables for Federated LLMs
Concordia aligns synthetic table generation with federated validation utility via client-level LoRA training, utility scorers, and outer GRPO refinement to boost performance over static synthetic baselines.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.