相关论文: Censoring chemical data to mitigate dual use risk

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming…

As predictive models -- e.g., from machine learning -- give likely outcomes, they may be used to reason on the effect of an intervention, a causal-inference task. The increasing complexity of health data has opened the door to a plethora of…

Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based…

The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security…

Studies of human decision-making demonstrate that environmental regularities, such as natural image statistics or intentionally nonuniform stimulus probabilities, can be exploited to improve efficiency (termed `efficient-coding').…

This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level…

Recent advancements in generative machine learning have enabled rapid progress in biological design tools (BDTs) such as protein structure and sequence prediction models. The unprecedented predictive accuracy and novel design capabilities…

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Accurately predicting drug responses to cancer is an important problem hindering oncologists' efforts to find the most effective drugs to treat cancer, which is a core goal in precision medicine. The scientific community has focused on…

Classifier chains have recently been proposed as an appealing method for tackling the multi-label classification task. In addition to several empirical studies showing its state-of-the-art performance, especially when being used in its…

Dynamic learning systems subject to selective labeling exhibit censoring, i.e. persistent negative predictions assigned to one or more subgroups of points. In applications like consumer finance, this results in groups of applicants that are…

In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to…

Neural network (NN) interatomic potentials provide fast prediction of potential energy surfaces, closely matching the accuracy of the electronic structure methods used to produce the training data. However, NN predictions are only reliable…

Two-dimensional electronic spectroscopy (2DES) has enabled significant discoveries in both biological and synthetic energy-transducing systems. Although deriving chemical information from 2DES is a complex task, machine learning (ML) offers…

Due to the redundant nature of DNA synthesis and sequencing technologies, a basic model for a DNA storage system is a multi-draw "shuffling-sampling" channel. In this model, a random number of noisy copies of each sequence is observed at…

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world…

Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models. In the financial services sector, this can result in discrimination from certain financial instruments and…