Microsoft

An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises

Differentially private (DP) synthetic datasets are a powerful approach for training machine learning models while respecting the privacy of individual data providers. The effect of DP on the fairness ...
Microsoft

Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

The 17th ACM International Conference on Web Search and Data Mining (WSDM '24) | March 2024 ...
IEEE

Analysis of design patterns for composite telco services

Abstract: The adoption of IT-based interfaces to monitor and control telco capabilities is a consolidated approach. In such a scenario the end-users design composite services that orchestrate ...
GitHub

On Embeddings for Numerical Features in Tabular Deep Learning (NeurIPS 2022)

In one sentence: transforming the original scalar continuous features to vectors before mixing them in the main backbone (e.g. in MLP, Transformer, etc.) improves the downstream performance of tabular ...
IEEE

Pre-Trained Tabular Transformer for Real-Time, Efficient, Stable Radiomics Data Processing: A Comprehensive Study

Abstract: Radiomics is an important research direction in the field of medical image analysis. Although the number of publications is increasing year by year, it has been difficult to translate into ...