Related papers: SIFOTL: A Principled, Statistically-Informed Fidel…
A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central…
The increasing demand for privacy-preserving data analytics in various domains necessitates solutions for synthetic data generation that rigorously uphold privacy standards. We introduce the DP-FedTabDiff framework, a novel integration of…
Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their performance in low-data regimes remains limited compared to gradient-boosted decision trees…
Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance.…
The ubiquity of missing data has sparked considerable attention and focus on tabular data imputation methods. Diffusion models, recognized as the cutting-edge technique for data generation, demonstrate significant potential in tabular data…
Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the…
Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic…
Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…
Federated learning~(FL) facilitates the training and deploying AI models on edge devices. Preserving user data privacy in FL introduces several challenges, including expensive communication costs, limited resources, and data heterogeneity.…
Data sharing is a prerequisite for collaborative innovation, enabling organizations to leverage diverse datasets for deeper insights. In real-world applications like FinTech and Smart Manufacturing, transactional data, often in tabular…
Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…
When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…
We revisit the problem of federated learning (FL) with private data from people who do not trust the server or other silos/clients. In this context, every silo (e.g. hospital) has data from several people (e.g. patients) and needs to…
Federated learning (FL) offers a privacy-preserving paradigm for machine learning, but its application in intrusion detection systems (IDS) within IoT networks is challenged by severe class imbalance, non-IID data, and high communication…
Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new…
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…
Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free…
Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices. Hence, the labels in practice are usually annotated by clients of varying expertise or…
Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while…
This study presents Weighted Sampled Split Learning (WSSL), an innovative framework tailored to bolster privacy, robustness, and fairness in distributed machine learning systems. Unlike traditional approaches, WSSL disperses the learning…