An official website of the United States government
Machine learning models often perform poorly under subpopulation shifts in the data distribution. Developing methods that allow machine learning models to better generalize to such shifts is crucial for safe deployment in real-world settings. In this paper, we develop a family of group-aware prior (GAP) distributions over neural network parameters that explicitly favor models that generalize well under subpopulation shifts. We design a simple group-aware prior that only requires access to a small set of data with group information and demonstrate that training with this prior yields state-of-the-art performance -- even when only retraining the final layer of a previously trained non-robust model. Group aware-priors are conceptually simple, complementary to existing approaches, such as attribute pseudo labeling and data reweighting, and open up promising new avenues for harnessing Bayesian inference to enable robustness to subpopulation shifts.
more »
« less
Sample Debiasing in the Themis Open World Database System
Open world database management systems assume tuples not in the database still exist and are becoming an increas- ingly important area of research. We present Themis, the first open world database that automatically rebalances ar- bitrarily biased samples to approximately answer queries as if they were issued over the entire population. We lever- age apriori population aggregate information to develop and combine two different approaches for automatic debiasing: sample reweighting and Bayesian network probabilistic mod- eling. We build a prototype of Themis and demonstrate that Themis achieves higher query accuracy than the default AQP approach, an alternative sample reweighting technique, and a variety of Bayesian network models while maintaining in- teractive query response times. We also show that Themis is robust to differences in the support between the sample and population, a key use case when using social media samples.
more »
« less
- Award ID(s):
- 1907997
- PAR ID:
- 10164636
- Date Published:
- Journal Name:
- SIGMOD
- Page Range / eLocation ID:
- 257 to 268
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Machine learning models often perform poorly under subpopulation shifts in the data distribution. Developing methods that allow machine learning models to better generalize to such shifts is crucial for safe deployment in real-world settings. In this paper, we develop a family of group-aware prior (GAP) distributions over neural network parameters that explicitly favor models that generalize well under subpopulation shifts. We design a simple group-aware prior that only requires access to a small set of data with group information and demonstrate that training with this prior yields state-of-the-art performance -- even when only retraining the final layer of a previously trained non-robust model. Group aware-priors are conceptually simple, complementary to existing approaches, such as attribute pseudo labeling and data reweighting, and open up promising new avenues for harnessing Bayesian inference to enable robustness to subpopulation shifts.more » « less
-
null (Ed.)Differential privacy has been widely adopted to release continuous- and scalar-valued information on a database without compromising the privacy of individual data records in it. The problem of querying binary- and matrix-valued information on a database in a differentially private manner has rarely been studied. However, binary- and matrix-valued data are ubiquitous in real-world applications, whose privacy concerns may arise under a variety of circumstances. In this paper, we devise an exclusive or (XOR) mechanism that perturbs binary- and matrix-valued query result by conducting an XOR operation on the query result with calibrated noises attributed to a matrix-valued Bernoulli distribution. We first rigorously analyze the privacy and utility guarantee of the proposed XOR mechanism. Then, to generate the parameters in the matrix-valued Bernoulli distribution, we develop a heuristic approach to minimize the expected square query error rate under ϵ -differential privacy constraint. Additionally, to address the intractability of calculating the probability density function (PDF) of this distribution and efficiently generate samples from it, we adapt an Exact Hamiltonian Monte Carlo based sampling scheme. Finally, we experimentally demonstrate the efficacy of the XOR mechanism by considering binary data classification and social network analysis, all in a differentially private manner. Experiment results show that the XOR mechanism notably outperforms other state-of-the-art differentially private methods in terms of utility (such as classification accuracy and F 1 score), and even achieves comparable utility to the non-private mechanisms.more » « less
-
Fairness Artificial Intelligence (AI) aims to identify and mitigate bias throughout the AI development process, spanning data collection, modeling, assessment, and deployment—a critical facet of establishing trustworthy AI systems. Tackling data bias through techniques like reweighting samples proves effective for promoting fairness. This paper undertakes a systematic exploration of reweighting samples for conventional Machine-Learning (ML) models, utilizing five models for binary classification on datasets such as Adult Income and COMPAS, incorporating various protected attributes. In particular, AI Fairness 360 (AIF360) from IBM, a versatile open-source library aimed at identifying and mitigating bias in machine-learning models throughout the entire AI application lifecycle, is employed as the foundation for conducting this systematic exploration. The evaluation of prediction outcomes employs five fairness metrics from AIF360, elucidating the nuanced and model-specific efficacy of reweighting samples in fostering fairness within traditional ML frameworks. Experimental results illustrate that reweighting samples effectively reduces bias in traditional ML methods for classification tasks. For instance, after reweighting samples, the balanced accuracy of Decision Tree (DT) improves to 100%, and its bias, as measured by fairness metrics such as Average Odds Difference (AOD), Equal Opportunity Difference (EOD), and Theil Index (TI), is mitigated to 0. However, reweighting samples does not effectively enhance the fairness performance of K Nearest Neighbor (KNN). This sheds light on the intricate dynamics of bias, underscoring the complexity involved in achieving fairness across different models and scenarios.more » « less
-
Abstract The big graph database provides strong modeling capabilities and efficient querying for complex applications. Subgraph isomorphism which finds exact matches of a query graph in the database efficiently, is a challenging problem. Current subgraph isomorphism approaches mostly are based on the pruning strategy proposed by Ullmann. These techniques have two significant drawbacks- first, they are unable to efficiently handle complex queries, and second, their implementations need the large indexes that require large memory resources. In this paper, we describe a new subgraph isomorphism approach, the HyGraph algorithm, that is efficient both in querying and with memory requirements for index creation. We compare the HyGraph algorithm with two popular existing approaches, GraphQL and Cypher using complexity measures and experimentally using three big graph data sets—(1) a country-level population database, (2) a simulated bank database, and (3) a publicly available World Cup big graph database. It is shown that the HyGraph solution performs significantly better (or equally) than competing algorithms for the query operations on these big databases, making it an excellent candidate for subgraph isomorphism queries in real scenarios.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3318464.3380606
