相关论文: Private, Augmentation-Robust and Task-Agnostic Dat…

Deep generative models are often trained on sensitive data, such as genetic sequences, health data, or more broadly, any copyrighted, licensed or protected content. This raises critical concerns around privacy-preserving synthetic data, and…

For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being. To this end, we harness the power of social media data, a rich source of public sentiment, to enhance the…

Joint distribution estimation of a dataset under differential privacy is a fundamental problem for many privacy-focused applications, such as query answering, machine learning tasks and synthetic data generation. In this work, we examine…

Personal data is an attractive source of insights for a diverse field of research and business. While our data is highly valuable, it is often privacy-sensitive. Thus, regulations like the GDPR restrict what data can be legally published,…

We envision AI marketplaces to be platforms where consumers, with very less data for a target task, can obtain a relevant model by accessing many private data sources with vast number of data samples. One of the key challenges is to…

Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit testing frameworks are largely task-agnostic: they validate…

Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data…

The Adaptive Data Analysis (ADA) problem, where an analyst interacts with a dataset through statistical queries, is often studied under the assumption of adversarial analyst behavior. To decrease this gap, we propose a revised model of ADA…

While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the…

Data assets are data commodities that have been processed, produced, priced, and traded based on actual demand. Reasonable pricing mechanism for data assets is essential for developing the data market and realizing their value. Most…

Designing truthful, revenue maximizing auctions is a core problem of auction design. Multi-item settings have long been elusive. Recent work (arXiv:1706.03459) introduces effective deep learning techniques to find such auctions for the…

In the field of emotion recognition and Human-Machine Interaction (HMI), personalised approaches have exhibited their efficacy in capturing individual-specific characteristics and enhancing affective prediction accuracy. However,…

Training data attribution (TDA) methods aim to identify which training examples influence a model's predictions on specific test data most. By quantifying these influences, TDA supports critical applications such as data debugging,…

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

We study how to enable auctions in the big data context to solve many upcoming data-based decision problems in the near future. We consider the characteristics of the big data including, but not limited to, velocity, volume, variety, and…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of annotators. However, the consensus might fail in settings, especially when a wide spectrum…

There is an increased sensitivity by people about how companies collect information about them, and how this information is packaged, used and sold. This perceived lack of control is highlighted by the helplessness of users of various…

We propose two synthetic microdata approaches to generate private tabular survey data products for public release. We adapt a pseudo posterior mechanism that downweights by-record likelihood contributions with weights $\in [0,1]$ based on…

In distributed networks, calculating the maximum element is a fundamental task in data analysis, known as the distributed maximum consensus problem. However, the sensitive nature of the data involved makes privacy protection essential.…