Angela HUO received the B.Eng and Ph.D. degrees from Northeastern University, China in 2002 and 2007, both in Computer Science and Technology. Her research interests include data stream management technology, advanced data analysis, and data-driven cybersecurity.
From 2012 to 2014, Angela HUO taught at the Department of Computer Information System, the University of the Fraser Valley in Canada, and studied at the University of Waterloo as a visiting scholar for one year.
Angela HUO has been awarded the National Outstanding Instructor five times for organizing the students and coaching the teams to win the Champions and Runner-ups in National Software Innovation Contests, ACM-ICPC Asia Regional Contests, World Odyssey of the Mind China Finals, Shanghai International Blockchain Hackathon, Technovation for girls programming since 2011.
Can supervise: YES
Zhang, T, Zhu, T, Xiong, P, Huo, H, Tari, Z & Zhou, W 2020, 'Correlated Differential Privacy: Feature Selection in Machine Learning', IEEE Transactions on Industrial Informatics, pp. 1-1.View/Download from: Publisher's site
Liu, X, Iftikhar, N, Huo, H, Li, R & Nielsen, PS 2019, 'Two approaches for synthesizing scalable residential energy consumption data', Future Generation Computer Systems, vol. 95, pp. 586-600.View/Download from: Publisher's site
© 2019 Elsevier B.V. Many fields require scalable and detailed energy consumption data for different study purposes. However, due to privacy issues, it is often difficult to obtain sufficiently large datasets. This paper proposes two different methods for synthesizing fine-grained energy consumption data for residential households, namely a regression-based method and a probability-based method. They each use a supervised machine learning method, which trains models with a relatively small real-world dataset and then generates large-scale time series based on the models. This paper describes the two methods in details, including data generation process, optimization techniques, and parallel data generation. This paper evaluates the performance of the two methods, which compare the resulting consumption profiles with real-world data, including patterns, statistics, and parallel data generation in the cluster. The results demonstrate the effectiveness of the proposed methods and their efficiency in generating large-scale datasets.
Distantly supervised relation extraction intrinsically suffers from noisy
labels due to the strong assumption of distant supervision. Most prior works
adopt a selective attention mechanism over sentences in a bag to denoise from
wrongly labeled data, which however could be incompetent when there is only one
sentence in a bag. In this paper, we propose a brand-new light-weight neural
framework to address the distantly supervised relation extraction problem and
alleviate the defects in previous selective attention framework. Specifically,
in the proposed framework, 1) we use an entity-aware word embedding method to
integrate both relative position information and head/tail entity embeddings,
aiming to highlight the essence of entities for this task; 2) we develop a
self-attention mechanism to capture the rich contextual dependencies as a
complement for local dependencies captured by piecewise CNN; and 3) instead of
using selective attention, we design a pooling-equipped gate, which is based on
rich contextual representations, as an aggregator to generate bag-level
representation for final relation classification. Compared to selective
attention, one major advantage of the proposed gating mechanism is that, it
performs stably and promisingly even if only one sentence appears in a bag and
thus keeps the consistency across all training examples. The experiments on NYT
dataset demonstrate that our approach achieves a new state-of-the-art
performance in terms of both AUC and top-n precision metrics.
CHEN, F, Pan, S, Jiang, J, Huo, H & Long, G 2019, 'DAGCN: Dual Attention Graph Convolutional Networks', 2019 International Joint Conference on Neural Networks (IJCNN), International Joint Conference on Neural Networks, IEEE, Budapest, Hungary.View/Download from: Publisher's site
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classification task: (1)when only the largest sub-graph structure (k-hop neighbor) is used for neighborhood aggregation, a large amount of early-stage information is lost during the graph convolution step; (2) simple average/sum pooling or max pooling utilized, which loses the characteristics of each node and the topology between nodes. In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems. DAGCN automatically learns the importance of neighbors at different hops using a novel attention graph convolution layer, and then employs a second attention component, a self-attention pooling layer, to generalize the graph representation from the various aspects of a matrix graph embedding. The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods. The experimental results show that our framework not only outperforms other baselines but also achieves a better rate of convergence.
Aung, TWW, Huo, H & Sui, Y 2019, 'Interactive Traceability Links Visualization using Hierarchical Trace Map', 2019 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE International Conference on Software Maintenance and Evolution, IEEE, Cleveland, Ohio.View/Download from: Publisher's site
Traceability links between various software artifacts of a system aid software engineers in system comprehension, verification and change impact analysis. Establishing trace links between software artifacts manually is an error-prone and costly task. Recently, studies in automated traceability link recovery area have received broad attention in the software maintenance community aiming to overcome the challenges of manual trace links maintenance process. In these studies, the trace links results generated by an automated trace recovery approach are presented either in a bland textual matrix format (e.g., tabular format) or two-dimensional graphical formats (e.g. tree view, hierarchical leaf node). Therefore, it is challenging for software engineers to explore the inter-relationships between various artifacts at once (e.g., which test cases and source code files/methods are related to a particular requirement). In this position paper, we propose a hierarchical trace map visualization technique to explore inter-relationships between various artifacts at once naturally and intuitively