| Nguyen TT, Gupta S and Venkatesh S (2021), "Distributional Reinforcement Learning via Moment Matching", In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI). , pp. 9144-9152.
[BibTeX] |
BibTeX:
@inproceedings{Nguyen_etal_AAAI21_mmdrl,
author = {Nguyen, Thanh Tang and Gupta, Sunil and Venkatesh, Svetha},
title = {Distributional Reinforcement Learning via Moment Matching},
booktitle = {The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI)},
year = {2021},
pages = {9144--9152},
note = {(A* conference)}
}
|
| Ha H, Gupta S, Rana S and Venkatesh S (2021), "High Dimensional Level Set Estimation with Bayesian Neural Network", In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI). , pp. 12095-12103.
[BibTeX] |
BibTeX:
@inproceedings{Ha_etal_AAAI21_mmdrl,
author = {Ha, Huong and Gupta, Sunil and Rana, Santu and Venkatesh, Svetha},
title = {High Dimensional Level Set Estimation with Bayesian Neural Network},
booktitle = {The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI)},
year = {2021},
pages = {12095--12103},
note = {(A* conference)}
}
|
| Do K, Tran T and Venkatesh S (2021), "Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization", In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI). , pp. 7236-7244.
[BibTeX] |
BibTeX:
@inproceedings{do2021semi,
author = {Do, Kien and Tran, Truyen and Venkatesh, Svetha},
title = {Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization},
booktitle = {The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI)},
year = {2021},
pages = {7236--7244},
note = {(A* conference)}
}
|
| Tran-The H, Gupta S, Rana S and Venkatesh S (2021), "Bayesian Optimistic Optimisation with Exponentially Decaying Regret", In International Conference on Machine Learning (ICML). , pp. 10390-10400. |
BibTeX:
@inproceedings{tranthe2021bayesian,
author = {Hung Tran-The and Sunil Gupta and Santu Rana and Svetha Venkatesh},
title = {Bayesian Optimistic Optimisation with Exponentially Decaying Regret},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2021},
pages = {10390--10400},
note = {(A* conference)},
url = {http://proceedings.mlr.press/v139/tran-the21a.html}
}
|
| Abdolshah M, Le H, George TK, Gupta S, Rana S and Venkatesh S (2021), "A New Representation of Successor Features for Transfer across Dissimilar Environments", In International Conference on Machine Learning (ICML). , pp. 1-9. |
BibTeX:
@inproceedings{Majid2021RL,
author = {Abdolshah, Majid and Le, Hung and George, Thommen Karimpanal and Gupta, Sunil and Rana, Santu and Venkatesh, Svetha},
title = {A New Representation of Successor Features for Transfer across Dissimilar Environments},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2021},
pages = {1--9},
note = {(A* conference)},
url = {https://proceedings.mlr.press/v139/abdolshah21a.html}
}
|
| Ruberu K, Senadeera M, Rana S, Gupta S, Chung J, Yue Z, Venkatesh S and Wallace G (2021), "Coupling machine learning with 3D bioprinting to fast track optimisation of extrusion printing", Applied Materials Today. Vol. 22, pp. 100914. Elsevier.
[BibTeX] |
BibTeX:
@article{ruberu2021coupling,
author = {Ruberu, Kalani and Senadeera, Manisha and Rana, Santu and Gupta, Sunil and Chung, Johnson and Yue, Zhilian and Venkatesh, Svetha and Wallace, Gordon},
title = {Coupling machine learning with 3D bioprinting to fast track optimisation of extrusion printing},
journal = {Applied Materials Today},
publisher = {Elsevier},
year = {2021},
volume = {22},
pages = {100914},
note = {(Q1 journal)}
}
|
| Morais R, Le V, Venkatesh S and Tran T (2021), "Learning Asynchronous and Sparse Human-Object Interaction in Videos", In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). , pp. 16041-16050.
[BibTeX] |
BibTeX:
@inproceedings{morais2021learning,
author = {Morais, Romero and Le, Vuong and Venkatesh, Svetha and Tran, Truyen},
title = {Learning Asynchronous and Sparse Human-Object Interaction in Videos},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021},
pages = {16041--16050},
note = {(A* conference)}
}
|
| Nguyen D, Gupta S, Nguyen T, Rana S, Nguyen P, Tran T, Le K, Ryan S and Venkatesh S (2021), "Knowledge Distillation with Distribution Mismatch", In The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD). Vol. 12976, pp. 250-265. |
BibTeX:
@inproceedings{nguyen2021kd,
author = {Nguyen, Dang and Gupta, Sunil and Nguyen, Trong and Rana, Santu and Nguyen, Phuoc and Tran, Truyen and Le, Ky and Ryan, Shannon and Venkatesh, Svetha},
title = {Knowledge Distillation with Distribution Mismatch},
booktitle = {The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)},
year = {2021},
volume = {12976},
pages = {250--265},
note = {(A conference)},
doi = {10.1007/978-3-030-86520-7_16}
}
|
| Nguyen P, Tran T, Le K, Gupta S, Rana S, Nguyen D, Nguyen T, Ryan S and Venkatesh S (2021), "Fast Conditional Network Compression Using Bayesian HyperNetworks", In The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD). Vol. 12977, pp. 330-345. |
BibTeX:
@inproceedings{nguyen2021compression,
author = {Nguyen, Phuoc and Tran, Truyen and Le, Ky and Gupta, Sunil and Rana, Santu and Nguyen, Dang and Nguyen, Trong and Ryan, Shannon and Venkatesh, Svetha},
title = {Fast Conditional Network Compression Using Bayesian HyperNetworks},
booktitle = {The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)},
year = {2021},
volume = {12977},
pages = {330--345},
note = {(A conference)},
doi = {10.1007/978-3-030-86523-8_20}
}
|
| Harikumar H, Quinn TP, Rana S, Gupta S and Venkatesh S (2021), "Personalized single-cell networks: a framework to predict the response of any gene to any drug for any patient", BioData Mining. Vol. 14(37), pp. 1-15. |
BibTeX:
@article{harikumar2021personalized,
author = {Harikumar, Haripriya and Quinn, Thomas P and Rana, Santu and Gupta, Sunil and Venkatesh, Svetha},
title = {Personalized single-cell networks: a framework to predict the response of any gene to any drug for any patient},
journal = {BioData Mining},
year = {2021},
volume = {14},
number = {37},
pages = {1--15},
note = {(Q2 journal)},
doi = {10.1186/s13040-021-00263-w}
}
|
| Yang A, Li C, Rana S, Gupta S and Venkatesh S (2021), "Sparse Spectrum Gaussian Process for Bayesian Optimization", In Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD). Vol. 12713, pp. 257-268. Springer. |
| Abstract: We propose a novel sparse spectrum approximation of Gaussian process (GP) tailored for Bayesian optimization (BO). Whilst the current sparse spectrum methods provide desired approximations for regression problems, it is observed that this particular form of sparse approximations generates an overconfident GP, i.e., it produces less epistemic uncertainty than the original GP. Since the balance between the predictive mean and variance is the key determinant to the success of BO, the current methods are less suitable for BO. We derive a new regularized marginal likelihood for finding the optimal frequencies to fix this overconfidence issue, particularly for BO. The regularizer trades off the accuracy in the model fitting with targeted increase in the predictive variance of the resultant GP. Specifically, we use the entropy of the global maximum distribution (GMD) from the posterior GP as the regularizer that needs to be maximized. Since the GMD cannot be calculated analytically, we first propose a Thompson sampling based approach and then a more efficient sequential Monte Carlo based approach to estimate it. Later, we also show that the Expected Improvement acquisition function can be used as a proxy for it, thus making the process further efficient. |
BibTeX:
@inproceedings{yang2021sparse,
author = {Yang, Ang and Li, Cheng and Rana, Santu and Gupta, Sunil and Venkatesh, Svetha},
title = {Sparse Spectrum Gaussian Process for Bayesian Optimization},
booktitle = {Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},
publisher = {Springer},
year = {2021},
volume = {12713},
pages = {257--268},
note = {(A conference)},
doi = {10.1007/978-3-030-75765-6_21}
}
|
| Li C, Rana S, Gill A, Nguyen D, Gupta S and Venkatesh S (2021), "Factor Screening using Bayesian Active Learning and Gaussian Process Meta-Modelling", In International Conference on Pattern Recognition (ICPR). , pp. 3288-3295.
[BibTeX] |
BibTeX:
@inproceedings{li2021factor,
author = {Li, Cheng and Rana, Santu and Gill, Andrew and Nguyen, Dang and Gupta, Sunil and Venkatesh, Svetha},
title = {Factor Screening using Bayesian Active Learning and Gaussian Process Meta-Modelling},
booktitle = {International Conference on Pattern Recognition (ICPR)},
year = {2021},
pages = {3288--3295},
note = {(B conference)}
}
|
| Nguyen D, Gupta S, Rana S, Shilton A and Venkatesh S (2021), "Fairness Improvement for Black-box Classifiers with Gaussian Process", Information Sciences. Vol. 576, pp. 542-556. Elsevier.
[BibTeX] |
BibTeX:
@article{nguyen2021fairness,
author = {Nguyen, Dang and Gupta, Sunil and Rana, Santu and Shilton, Alistair and Venkatesh, Svetha},
title = {Fairness Improvement for Black-box Classifiers with Gaussian Process},
journal = {Information Sciences},
publisher = {Elsevier},
year = {2021},
volume = {576},
pages = {542--556},
note = {(Q1 journal)}
}
|
| Nguyen P, Tran T, Gupta S, Rana S, Dam H-C and Venkatesh S (2021), "Variational Hyper-Encoding Networks", In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD). Vol. 12976, pp. 100-115. |
| Abstract: We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters are sampled from a distribution in the model space modeled by a hyper-level VAE. We propose a variational inference framework to implicitly encode the parameter distributions into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution for the parameters. HyperVAE can encode the target parameters in full in contrast to common hyper-networks practices, which generate only the scale and bias vectors to modify the target-network parameters. Thus HyperVAE preserves information about the model for each task in the latent space. We derive the training objective for HyperVAE using the minimum description length (MDL) principle to reduce the complexity of HyperVAE. We evaluate HyperVAE in density estimation tasks, outlier detection and discovery of novel design classes, demonstrating its efficacy. |
BibTeX:
@inproceedings{phuoc2021hypervae,
author = {Nguyen, Phuoc and Tran, Truyen and Gupta, Sunil and Rana, Santu and Dam, Hieu-Chi and Venkatesh, Svetha},
title = {Variational Hyper-Encoding Networks},
booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD)},
year = {2021},
volume = {12976},
pages = {100--115},
note = {(A conference)},
doi = {10.1007/978-3-030-86520-7_7}
}
|
| Arun Kumar AV, Shilton A, Rana S, Gupta S and Venkatesh S (2021), "Kernel Functional Optimisation", In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS). , pp. 4725-4737.
[BibTeX] |
BibTeX:
@inproceedings{arun2021neurips,
author = {A V, Arun Kumar and Shilton, Alistair and Rana, Santu and Gupta, Sunil and Venkatesh, Svetha},
title = {Kernel Functional Optimisation},
booktitle = {Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS)},
year = {2021},
pages = {4725--4737},
note = {(A* conference)}
}
|
| Le H, Karimpanal George T, Abdolshah M, Tran T and Venkatesh S (2021), "Model-Based Episodic Memory Induces Dynamic Hybrid Controls", In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS). , pp. 30313-30325.
[BibTeX] |
BibTeX:
@inproceedings{hung2021neurips,
author = {Le, Hung and Karimpanal George, Thommen and Abdolshah, Majid and Tran, Truyen and Venkatesh, Svetha},
title = {Model-Based Episodic Memory Induces Dynamic Hybrid Controls},
booktitle = {Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS)},
year = {2021},
pages = {30313--30325},
note = {(A* conference)}
}
|
| Nguyen-Thai B, Le V, Morgan C, Badawi N, Tran T and Venkatesh S (2021), "A Spatio-Temporal Attention-Based Model for Infant Movement Assessment From Videos", IEEE Journal of Biomedical and Health Informatics. Vol. 25(10), pp. 3911-3920. |
| Abstract: The absence or abnormality of fidgety movements of joints or limbs is strongly indicative of cerebral palsy in infants. Developing computer-based methods for assessing infant movements in videos is pivotal for improved cerebral palsy screening. Most existing methods use appearance-based features and are thus sensitive to strong but irrelevant signals caused by background clutter or a moving camera. Moreover, these features are computed over the whole frame, thus they measure gross whole body movements rather than specific joint/limb motion. Addressing these challenges, we develop and validate a new method for fidgety movement assessment from consumer-grade videos using human poses extracted from short clips. Human poses capture only relevant motion profiles of joints and limbs and are thus free from irrelevant appearance artifacts. The dynamics and coordination between joints are modeled using spatio-temporal graph convolutional networks. Frames and body parts that contain discriminative information about fidgety movements are selected through a spatio-temporal attention mechanism. We validate the proposed model on the cerebral palsy screening task using a real-life consumer-grade video dataset collected at an Australian hospital through the Cerebral Palsy Alliance, Australia. Our experiments show that the proposed method achieves the ROC-AUC score of 81.87%, significantly outperforming existing competing methods with better interpretability. |
BibTeX:
@article{binh2021jbhi,
author = {Nguyen-Thai, Binh and Le, Vuong and Morgan, Catherine and Badawi, Nadia and Tran, Truyen and Venkatesh, Svetha},
title = {A Spatio-Temporal Attention-Based Model for Infant Movement Assessment From Videos},
journal = {IEEE Journal of Biomedical and Health Informatics},
year = {2021},
volume = {25},
number = {10},
pages = {3911-3920},
note = {(Q1 journal)},
doi = {10.1109/JBHI.2021.3077957}
}
|
| Do K, Tran T and Venkatesh S (2021), "Clustering by maximizing mutual information across views", In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). , pp. 9928-9938.
[BibTeX] |
BibTeX:
@inproceedings{do2021clustering,
author = {Do, Kien and Tran, Truyen and Venkatesh, Svetha},
title = {Clustering by maximizing mutual information across views},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
year = {2021},
pages = {9928--9938},
note = {(A* conference)}
}
|
| Nguyen T, Lee SC, Quinn TP, Truong B, Li X, Tran T, Venkatesh S and Le TD (2021), "PAN: Personalized Annotation-based Networks for the Prediction of Breast Cancer Relapse", IEEE/ACM Transactions on Computational Biology and Bioinformatics. Vol. 18(6), pp. 2841-2847. IEEE.
[BibTeX] |
BibTeX:
@article{nguyen2021pan,
author = {Nguyen, Thin and Lee, Samuel C and Quinn, Thomas P and Truong, Buu and Li, Xiaomei and Tran, Truyen and Venkatesh, Svetha and Le, Thuc Duy},
title = {PAN: Personalized Annotation-based Networks for the Prediction of Breast Cancer Relapse},
journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
publisher = {IEEE},
year = {2021},
volume = {18},
number = {6},
pages = {2841--2847},
note = {(Q2 journal)}
}
|
| O’Dea B, Boonstra TW, Larsen ME, Nguyen T, Venkatesh S and Christensen H (2021), "The relationship between linguistic expression in blog content and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study", Plos one. Vol. 16(5), pp. e0251787. Public Library of Science San Francisco, CA USA.
[BibTeX] |
BibTeX:
@article{o2021relationship,
author = {O’Dea, Bridianne and Boonstra, Tjeerd W and Larsen, Mark E and Nguyen, Thin and Venkatesh, Svetha and Christensen, Helen},
title = {The relationship between linguistic expression in blog content and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study},
journal = {Plos one},
publisher = {Public Library of Science San Francisco, CA USA},
year = {2021},
volume = {16},
number = {5},
pages = {e0251787},
note = {(Q1 journal)}
}
|
| Nguyen T, Le H, Quinn TP, Nguyen T, Le TD and Venkatesh S (2021), "GraphDTA: Predicting drug--target binding affinity with graph neural networks", Bioinformatics. Vol. 37(8), pp. 1140-1147. Oxford University Press.
[BibTeX] |
BibTeX:
@article{nguyen2021graphdta,
author = {Nguyen, Thin and Le, Hang and Quinn, Thomas P and Nguyen, Tri and Le, Thuc Duy and Venkatesh, Svetha},
title = {GraphDTA: Predicting drug--target binding affinity with graph neural networks},
journal = {Bioinformatics},
publisher = {Oxford University Press},
year = {2021},
volume = {37},
number = {8},
pages = {1140--1147},
note = {(Q1 journal)}
}
|
| Ansari MS, Alok AK, Jain D, Rana S, Gupta S, Salwan R and Venkatesh S (2021), "Predictive Model Based on Health Data Analysis for Risk of Readmission in Disease-Specific Cohorts", Perspectives in Health Information Management. Vol. 18(Spring), pp. PMID: 34035791. American Health Information Management Association.
[BibTeX] |
BibTeX:
@article{ansari2021predictive,
author = {Ansari, Md Shahid and Alok, Abhay Kumar and Jain, Dinesh and Rana, Santu and Gupta, Sunil and Salwan, Roopa and Venkatesh, Svetha},
title = {Predictive Model Based on Health Data Analysis for Risk of Readmission in Disease-Specific Cohorts},
journal = {Perspectives in Health Information Management},
publisher = {American Health Information Management Association},
year = {2021},
volume = {18},
number = {Spring},
pages = {PMID: 34035791},
note = {(Q3 journal)}
}
|
| Le TM, Le V, Venkatesh S and Tran T (2021), "Hierarchical Conditional Relation Networks for Multimodal Video Question Answering", International Journal of Computer Vision. Vol. 129(11), pp. 3027-3050. Springer.
[BibTeX] |
BibTeX:
@article{le2021hierarchical,
author = {Le, Thao Minh and Le, Vuong and Venkatesh, Svetha and Tran, Truyen},
title = {Hierarchical Conditional Relation Networks for Multimodal Video Question Answering},
journal = {International Journal of Computer Vision},
publisher = {Springer},
year = {2021},
volume = {129},
number = {11},
pages = {3027--3050},
note = {(Q1 journal)}
}
|
| Ansari S, Jain D, Harikumar H, Rana S, Gupta S, Budhiraja S, Venkatesh S and others (2021), "Identification of predictors and model for predicting prolonged length of stay in dengue patients", Health care management science. Vol. 24(4), pp. 786-798.
[BibTeX] |
BibTeX:
@article{ansari2021identification,
author = {Ansari, Shahid and Jain, Dinesh and Harikumar, Haripriya and Rana, Santu and Gupta, Sunil and Budhiraja, Sandeep and Venkatesh, Svetha and others},
title = {Identification of predictors and model for predicting prolonged length of stay in dengue patients},
journal = {Health care management science},
year = {2021},
volume = {24},
number = {4},
pages = {786--798},
note = {(Q1 journal)}
}
|
| Luong P, Nguyen D, Gupta S, Rana S and Venkatesh S (2021), "Adaptive cost-aware Bayesian optimization", Knowledge-Based Systems. Vol. 232, pp. 107481. Elsevier.
[BibTeX] |
BibTeX:
@article{luong2021adaptive,
author = {Luong, Phuc and Nguyen, Dang and Gupta, Sunil and Rana, Santu and Venkatesh, Svetha},
title = {Adaptive cost-aware Bayesian optimization},
journal = {Knowledge-Based Systems},
publisher = {Elsevier},
year = {2021},
volume = {232},
pages = {107481},
note = {(Q1 journal)}
}
|
| Rana S, Luo W, Tran T, Venkatesh S, Talman P, Phan T, Phung D and Clissold B (2021), "Application of Machine Learning Techniques to Identify Data Reliability and Factors Affecting Outcome After Stroke Using Electronic Administrative Records", Frontiers in Neurology. , pp. 1695.
[BibTeX] |
BibTeX:
@article{rana2021application,
author = {Rana, Santu and Luo, Wei and Tran, Truyen and Venkatesh, Svetha and Talman, Paul and Phan, Thanh and Phung, Dinh and Clissold, Benjamin},
title = {Application of Machine Learning Techniques to Identify Data Reliability and Factors Affecting Outcome After Stroke Using Electronic Administrative Records},
journal = {Frontiers in Neurology},
year = {2021},
pages = {1695},
note = {(Q2 journal)}
}
|
| Zong W, Chow Y-W, Susilo W, Rana S and Venkatesh S (2021), "Targeted Universal Adversarial Perturbations for Automatic Speech Recognition", In International Conference on Information Security. , pp. 358-373.
[BibTeX] |
BibTeX:
@inproceedings{zong2021targeted,
author = {Zong, Wei and Chow, Yang-Wai and Susilo, Willy and Rana, Santu and Venkatesh, Svetha},
title = {Targeted Universal Adversarial Perturbations for Automatic Speech Recognition},
booktitle = {International Conference on Information Security},
year = {2021},
pages = {358--373}
}
|
| Joseph J, Senadeera M, Chao Q, Shamlaye K, Rana S, Gupta S, Venkatesh S, Hodgson P, Barnett M and Fabijanic D (2021), "Computational design of thermally stable and precipitation-hardened Al-Co-Cr-Fe-Ni-Ti high entropy alloys", Journal of Alloys and Compounds. Vol. 888, pp. 161496.
[BibTeX] |
BibTeX:
@article{joseph2021computational,
author = {Joseph, J and Senadeera, M and Chao, Q and Shamlaye, KF and Rana, S and Gupta, S and Venkatesh, S and Hodgson, P and Barnett, M and Fabijanic, D},
title = {Computational design of thermally stable and precipitation-hardened Al-Co-Cr-Fe-Ni-Ti high entropy alloys},
journal = {Journal of Alloys and Compounds},
year = {2021},
volume = {888},
pages = {161496},
note = {(Q1 journal)}
}
|