Search for: All records

Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model performance is challenging. Existing works mainly exploit input and output space and classification loss, which can result in ineffective unlearning or performance loss. In addition, they utilize unlearning or remaining samples ineffectively, sacrificing either unlearning efficacy or efficiency. Our main insight is that the direct optimization on the representation space utilizing both unlearning and remaining samples can effectively remove influence of unlearning samples while maintaining representations learned from remaining samples. We propose a contrastive unlearning framework, leveraging the concept of representation learning for more effective unlearning. It removes the influence of unlearning samples by contrasting their embeddings against the remaining samples' embeddings so that their embeddings are closer to the embeddings of unseen samples. Experiments on a variety of datasets and models on both class unlearning and sample unlearning showed that contrastive unlearning achieves the best unlearning effects and efficiency with the lowest performance loss compared with the state-of-the-art algorithms. In addition, it is generalizable to different contrastive frameworks and other models such as vision-language models. Our main code is available on github.com/Emory-AIMS/Contrastive-Unlearning 

The increased availability of datasets during the COVID-19 pandemic enabled machine-learning approaches for modeling and forecasting infectious diseases. However, such approaches are known to amplify the bias in the data they are trained on. Bias in such input data like clinical case data for COVID-19 is difficult to measure due to disparities in testing availability, reporting standards, and healthcare access among different populations and regions. Furthermore, the way such biases may propagate through the modeling pipeline to decision-making is relatively unknown. Therefore, we present a system that leverages a highly detailed agent-based model (ABM) of infectious disease spread in a city to simulate the collection of biased clinical case data where the bias is known. Our system allows users to load either a pre-selected region or select their own (using OpenStreetMap data for the environment and census data for the population), specify population and infectious disease parameters, and the degree(s) to which different populations will be overrepresented or underrepresented in the case data. In addition to the system, we provide a large number of benchmark datasets that produce case data at different levels of bias for different regions. Wehope that infectious disease modelers will use these datasets to investigate how well their models are robust to data bias or whether their model is overfit to biased data. 

Human mobility anomaly detection based on location is essential in areas such as public health, safety, welfare, and urban planning. Developing models and approaches for location-based anomaly detection requires a comprehensive dataset. However, privacy concerns and the absence of ground truth hinder the availability of publicly available datasets. With this paper, we provide extensive simulated human mobility datasets featuring various anomaly types created using an existing Urban Patterns of Life Simulation. To create these datasets, we inject changes in the logic of individual agents to change their behavior. Specifically, we create four of anomalous agent behavior by (1) changing the agents’ appetite (causing agents to have meals more frequently), (2) changing their group of interest (causing agents to interact with different agents from another group). (3) changing their social place selection (causing agents to visit different recreational places) and (4) changing their work schedule (causing agents to skip work), For each type of anomaly, we use three degrees of behavioral change to tune the difficulty of detecting the anomalous agents. To select agents to inject anomalous behavior into, we employ three methods: (1) Random selection using a centralized manipulation mechanism, (2) Spread based selection using an infectious disease model, and (3) through exposure of agents to a specific location. All datasets are split into normal and anomalous phases. The normal phase, which can be used for training models of normalcy, exhibits no anomalous behavior. The anomalous phase, which can be used for testing for anomalous detection algorithm, includes ground truth labels that indicate, for each five-minute simulation step, which agents are anomalous at that time. Datasets are generated using the maps (roads and buildings) for Atlanta and Berlin having 1k agents in each simulation. All datasets are openly available at https://osf.io/dg6t3/. Additionally, we provide instructions to regenerate the data for other locations and numbers of agents.