2023
1.
Belkhouja, Taha; Doppa, Janardhan Rao
Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features (Extended Abstract) Proceedings Article
In: pp. 6845–6850, 2023, (ISSN: 1045-0823).
Abstract | Links | BibTeX | Tags: AI
@inproceedings{belkhouja_adversarial_2023,
title = {Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features (Extended Abstract)},
author = {Belkhouja, Taha and Doppa, Janardhan Rao},
url = {https://www.ijcai.org/proceedings/2023/767},
doi = {10.24963/ijcai.2023/767},
year = {2023},
date = {2023-08-01},
urldate = {2023-08-01},
volume = {6},
pages = {6845\textendash6850},
abstract = {Electronic proceedings of IJCAI 2023},
note = {ISSN: 1045-0823},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
Electronic proceedings of IJCAI 2023
2.
Harrison, Galen; Alabsi Aljundi, Amro; Chen, Jiangzhuo; Ravi, S.S.; Vullikanti, Anil Kumar; Marathe, Madhav V.; Adiga, Abhijin
Identifying Complicated Contagion Scenarios from Cascade Data Proceedings Article
In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4135–4145, Association for Computing Machinery, New York, NY, USA, 2023, ISBN: 9798400701030.
Abstract | Links | BibTeX | Tags: AI
@inproceedings{harrison_identifying_2023,
title = {Identifying Complicated Contagion Scenarios from Cascade Data},
author = {Harrison, Galen and Alabsi Aljundi, Amro and Chen, Jiangzhuo and Ravi, S.S. and Vullikanti, Anil Kumar and Marathe, Madhav V. and Adiga, Abhijin},
url = {https://dl.acm.org/doi/10.1145/3580305.3599841},
doi = {10.1145/3580305.3599841},
isbn = {9798400701030},
year = {2023},
date = {2023-08-01},
urldate = {2023-08-01},
booktitle = {Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {4135\textendash4145},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {KDD '23},
abstract = {We consider the setting of cascades that result from contagion dynamics on large realistic contact networks. We address the question of whether the structural properties of a (partially) observed cascade can characterize the contagion scenario and identify the interventions that might be in effect. Using epidemic spread as a concrete example, we study how social interventions such as compliance in social distancing, extent (and efficacy) of vaccination, and the transmissibility of disease can be inferred. The techniques developed are more generally applicable to other contagions as well. Our approach involves the use of large realistic social contact networks of certain regions of USA and an agent-based model (ABM) to simulate spread under two interventions, namely vaccination and generic social distancing (GSD). Through a machine learning approach, coupled with parameter significance analysis, our experimental results show that subgraph counts of the graph induced by the cascade can be used effectively to characterize the contagion scenario even during the initial stages of the epidemic, when traditional information such as case counts alone are not adequate for this task. Further, we show that our approach performs well even for partially observed cascades. These results demonstrate that cascade data collected from digital tracing applications under poor digital penetration and privacy constraints can provide valuable information about the contagion scenario.},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
We consider the setting of cascades that result from contagion dynamics on large realistic contact networks. We address the question of whether the structural properties of a (partially) observed cascade can characterize the contagion scenario and identify the interventions that might be in effect. Using epidemic spread as a concrete example, we study how social interventions such as compliance in social distancing, extent (and efficacy) of vaccination, and the transmissibility of disease can be inferred. The techniques developed are more generally applicable to other contagions as well. Our approach involves the use of large realistic social contact networks of certain regions of USA and an agent-based model (ABM) to simulate spread under two interventions, namely vaccination and generic social distancing (GSD). Through a machine learning approach, coupled with parameter significance analysis, our experimental results show that subgraph counts of the graph induced by the cascade can be used effectively to characterize the contagion scenario even during the initial stages of the epidemic, when traditional information such as case counts alone are not adequate for this task. Further, we show that our approach performs well even for partially observed cascades. These results demonstrate that cascade data collected from digital tracing applications under poor digital penetration and privacy constraints can provide valuable information about the contagion scenario.
3.
Garcia, Rosalinda; Patricia Morreale; Lara Letaw; Amreeta Chatterjee; Pakati Patel; Sarah Yang; Isaac Tijerina Escobar; Geraldine Jimena Noa;; Margaret Burnett
“Regular” CS × Inclusive Design = Smarter Students and Greater Diversity textbar ACM Transactions on Computing Education Journal Article
In: ACM Transactions on Computing Education, 2023.
Links | BibTeX | Tags: Human-Computer Interaction
@article{noauthor_regular_nodate,
title = {“Regular” CS × Inclusive Design = Smarter Students and Greater Diversity textbar ACM Transactions on Computing Education},
author = {Garcia, Rosalinda; Patricia Morreale; Lara Letaw; Amreeta Chatterjee; Pakati Patel; Sarah Yang; Isaac Tijerina Escobar; Geraldine Jimena Noa; and Margaret Burnett},
url = {https://dl.acm.org/doi/10.1145/3603535},
year = {2023},
date = {2023-07-22},
urldate = {2023-07-22},
journal = {ACM Transactions on Computing Education},
keywords = {Human-Computer Interaction},
pubstate = {published},
tppubtype = {article}
}
4.
Wang, T.; Sankari, P.; Brown, J.; Paudel, A.; He, L.; Karkee, M.; Thompson, A.; Grimm, C.; Davidson, J.r.; Todorovic, S.
Automatic estimation of trunk cross sectional area using deep learning Proceedings Article
In: Precision agriculture, pp. 491–498, Wageningen Academic Publishers, 2023, ISBN: 978-90-8686-393-8, (Section: 62).
Links | BibTeX | Tags: AI, Labor, Pruning
@inproceedings{wang_62_2023,
title = {Automatic estimation of trunk cross sectional area using deep learning},
author = {Wang, T. and Sankari, P. and Brown, J. and Paudel, A. and He, L. and Karkee, M. and Thompson, A. and Grimm, C. and Davidson, J.r. and Todorovic, S.},
url = {https://www.wageningenacademic.com/doi/10.3920/978-90-8686-947-3_62},
doi = {10.3920/978-90-8686-947-3_62},
isbn = {978-90-8686-393-8},
year = {2023},
date = {2023-07-01},
urldate = {2023-07-01},
booktitle = {Precision agriculture},
pages = {491\textendash498},
publisher = {Wageningen Academic Publishers},
note = {Section: 62},
keywords = {AI, Labor, Pruning},
pubstate = {published},
tppubtype = {inproceedings}
}
5.
Parayil, N.; You, A.; Grimm, C.; Davidson, J.r.
Follow the leader: a path generator and controller for precision tree scanning with a robotic manipulator Proceedings Article
In: Precision agriculture, pp. 167–174, Wageningen Academic Publishers, 2023, ISBN: 978-90-8686-393-8, (Section: 19).
@inproceedings{parayil_19_2023,
title = {Follow the leader: a path generator and controller for precision tree scanning with a robotic manipulator},
author = {Parayil, N. and You, A. and Grimm, C. and Davidson, J.r.},
url = {https://www.wageningenacademic.com/doi/10.3920/978-90-8686-947-3_19},
doi = {10.3920/978-90-8686-947-3_19},
isbn = {978-90-8686-393-8},
year = {2023},
date = {2023-07-01},
urldate = {2023-07-01},
booktitle = {Precision agriculture},
pages = {167\textendash174},
publisher = {Wageningen Academic Publishers},
note = {Section: 19},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
6.
Belkhouja, Taha; Yan, Yan; Doppa, Janardhan Rao
Dynamic Time Warping Based Adversarial Framework for Time-Series Domain Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 6, pp. 7353–7366, 2023, ISSN: 1939-3539, (Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence).
Abstract | Links | BibTeX | Tags: AI
@article{belkhouja_dynamic_2023,
title = {Dynamic Time Warping Based Adversarial Framework for Time-Series Domain},
author = {Belkhouja, Taha and Yan, Yan and Doppa, Janardhan Rao},
url = {https://ieeexplore.ieee.org/document/9970291},
doi = {10.1109/TPAMI.2022.3224754},
issn = {1939-3539},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {45},
number = {6},
pages = {7353\textendash7366},
abstract = {Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as Dynamic Time Warping for Adversarial Robustness (DTW-AR) using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training.},
note = {Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence},
keywords = {AI},
pubstate = {published},
tppubtype = {article}
}
Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as Dynamic Time Warping for Adversarial Robustness (DTW-AR) using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training.
7.
Mishra, Ritwick; Heavey, Jack; Kaur, Gursharn; Adiga, Abhijin; Vullikanti, Anil
Reconstructing an Epidemic Outbreak Using Steiner Connectivity Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 10, pp. 11613–11620, 2023, ISSN: 2374-3468, (Number: 10).
Abstract | Links | BibTeX | Tags: AI
@article{mishra_reconstructing_2023,
title = {Reconstructing an Epidemic Outbreak Using Steiner Connectivity},
author = {Mishra, Ritwick and Heavey, Jack and Kaur, Gursharn and Adiga, Abhijin and Vullikanti, Anil},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/26372},
doi = {10.1609/aaai.v37i10.26372},
issn = {2374-3468},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {37},
number = {10},
pages = {11613\textendash11620},
abstract = {Only a subset of infections is actually observed in an outbreak, due to multiple reasons such as asymptomatic cases and under-reporting. Therefore, reconstructing an epidemic cascade given some observed cases is an important step in responding to such an outbreak. A maximum likelihood solution to this problem ( referred to as CascadeMLE ) can be shown to be a variation of the classical Steiner subgraph problem, which connects a subset of observed infections. In contrast to prior works on epidemic reconstruction, which consider the standard Steiner tree objective, we show that a solution to CascadeMLE, based on the actual MLE objective, has a very different structure. We design a logarithmic approximation algorithm for CascadeMLE, and evaluate it on multiple synthetic and social contact networks, including a contact network constructed for a hospital. Our algorithm has significantly better performance compared to a prior baseline.},
note = {Number: 10},
keywords = {AI},
pubstate = {published},
tppubtype = {article}
}
Only a subset of infections is actually observed in an outbreak, due to multiple reasons such as asymptomatic cases and under-reporting. Therefore, reconstructing an epidemic cascade given some observed cases is an important step in responding to such an outbreak. A maximum likelihood solution to this problem ( referred to as CascadeMLE ) can be shown to be a variation of the classical Steiner subgraph problem, which connects a subset of observed infections. In contrast to prior works on epidemic reconstruction, which consider the standard Steiner tree objective, we show that a solution to CascadeMLE, based on the actual MLE objective, has a very different structure. We design a logarithmic approximation algorithm for CascadeMLE, and evaluate it on multiple synthetic and social contact networks, including a contact network constructed for a hospital. Our algorithm has significantly better performance compared to a prior baseline.
8.
Ghosh, Subhankar; Belkhouja, Taha; Yan, Yan; Doppa, Janardhan Rao
Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis Journal Article
In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 6, pp. 7722–7730, 2023, ISSN: 2374-3468, (Number: 6).
Abstract | Links | BibTeX | Tags: AI, Water
@article{ghosh_improving_2023,
title = {Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis},
author = {Ghosh, Subhankar and Belkhouja, Taha and Yan, Yan and Doppa, Janardhan Rao},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/25936},
doi = {10.1609/aaai.v37i6.25936},
issn = {2374-3468},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {37},
number = {6},
pages = {7722\textendash7730},
abstract = {Safe deployment of deep neural networks in high-stake real-world applications require theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of deep models in the form of prediction set for classification tasks with a user-specified coverage (i.e., true class label is contained with high probability). This paper proposes a novel algorithm referred to as Neighborhood Conformal Prediction (NCP) to improve the efficiency of uncertainty quantification from CP for deep classifiers (i.e., reduce prediction set size). The key idea behind NCP is to use the learned representation of the neural network to identify k nearest-neighbor calibration examples for a given testing input and assign them importance weights proportional to their distance to create adaptive prediction sets. We theoretically show that if the learned data representation of the neural network satisfies some mild conditions, NCP will produce smaller prediction sets than traditional CP algorithms. Our comprehensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using diverse deep neural networks strongly demonstrate that NCP leads to significant reduction in prediction set size over prior CP methods.},
note = {Number: 6},
keywords = {AI, Water},
pubstate = {published},
tppubtype = {article}
}
Safe deployment of deep neural networks in high-stake real-world applications require theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of deep models in the form of prediction set for classification tasks with a user-specified coverage (i.e., true class label is contained with high probability). This paper proposes a novel algorithm referred to as Neighborhood Conformal Prediction (NCP) to improve the efficiency of uncertainty quantification from CP for deep classifiers (i.e., reduce prediction set size). The key idea behind NCP is to use the learned representation of the neural network to identify k nearest-neighbor calibration examples for a given testing input and assign them importance weights proportional to their distance to create adaptive prediction sets. We theoretically show that if the learned data representation of the neural network satisfies some mild conditions, NCP will produce smaller prediction sets than traditional CP algorithms. Our comprehensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using diverse deep neural networks strongly demonstrate that NCP leads to significant reduction in prediction set size over prior CP methods.
9.
Ghosh, Subhankar; Shi, Yuanjie; Belkhouja, Taha; Yan, Yan; Doppa, Jana; Jones, Brian
Probabilistically Robust Conformal Prediction Proceedings Article
In: 2023.
Abstract | Links | BibTeX | Tags: AI
@inproceedings{ghosh_probabilistically_2023,
title = {Probabilistically Robust Conformal Prediction},
author = {Ghosh, Subhankar and Shi, Yuanjie and Belkhouja, Taha and Yan, Yan and Doppa, Jana and Jones, Brian},
url = {https://openreview.net/forum?id=4xI4oaqIs2},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
abstract = {Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate labels with a user-specified coverage (i.e., true class label is contained with high probability). Almost all the existing work on CP assumes clean testing data and there is not much known about the robustness of CP algorithms w.r.t natural/adversarial perturbations to testing examples. This paper studies the problem of probabilistically robust conformal prediction (PRCP) which ensures robustness to most perturbations around clean input examples. PRCP generalizes the standard CP (cannot handle perturbations) and adversarially robust CP (ensures robustness w.r.t worst-case perturbations) to achieve better trade-offs between nominal performance and robustness. We propose a novel adaptive PRCP (aPRCP) algorithm to achieve probabilistically robust coverage. The key idea behind aPRCP is to determine two parallel thresholds, one for data samples and another one for the perturbations on data (aka "quantile-of-quantile'' design). We provide theoretical analysis to show that aPRCP algorithm achieves robust coverage. Our experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using deep neural networks demonstrate that aPRCP achieves better trade-offs than state-of-the-art CP and adversarially robust CP algorithms.},
keywords = {AI},
pubstate = {published},
tppubtype = {inproceedings}
}
Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate labels with a user-specified coverage (i.e., true class label is contained with high probability). Almost all the existing work on CP assumes clean testing data and there is not much known about the robustness of CP algorithms w.r.t natural/adversarial perturbations to testing examples. This paper studies the problem of probabilistically robust conformal prediction (PRCP) which ensures robustness to most perturbations around clean input examples. PRCP generalizes the standard CP (cannot handle perturbations) and adversarially robust CP (ensures robustness w.r.t worst-case perturbations) to achieve better trade-offs between nominal performance and robustness. We propose a novel adaptive PRCP (aPRCP) algorithm to achieve probabilistically robust coverage. The key idea behind aPRCP is to determine two parallel thresholds, one for data samples and another one for the perturbations on data (aka "quantile-of-quantile'' design). We provide theoretical analysis to show that aPRCP algorithm achieves robust coverage. Our experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using deep neural networks demonstrate that aPRCP achieves better trade-offs than state-of-the-art CP and adversarially robust CP algorithms.
10.
He, Liqiang; Wei Wang, Albert Chen; Min Sun; Cheng-hao Kuo; Sinisa Todorovic
Bidirectional alignment for domain adaptive detection with transformers Proceedings Article
In: Proceedings of International Conference on Computer Vision, 2023.
Abstract | Links | BibTeX | Tags: Pruning
@inproceedings{noauthor_bidirectional_nodate,
title = {Bidirectional alignment for domain adaptive detection with transformers},
author = {He, Liqiang; Wei Wang, Albert Chen; Min Sun; Cheng-hao Kuo; Sinisa Todorovic},
url = {https://www.amazon.science/publications/bidirectional-alignment-for-domain-adaptive-detection-with-transformers},
year = {2023},
date = {2023-03-08},
urldate = {2023-03-08},
journal = {Amazon Science},
publisher = {Proceedings of International Conference on Computer Vision},
abstract = {We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance. Existing adversarial learning based methods use gradient reverse layer (GRL) to reduce the domain gap between the source and target domains in feature…},
keywords = {Pruning},
pubstate = {published},
tppubtype = {inproceedings}
}
We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance. Existing adversarial learning based methods use gradient reverse layer (GRL) to reduce the domain gap between the source and target domains in feature…
