Computing and Information Systems - Theses
Permanent URI for this collection
Search Results
1 - 3 of 3
-
ItemExplainable Reinforcement Learning Through a Causal Lens( 2021)This thesis investigates methods for explaining and understanding how and why reinforcement learning agents select actions, from a causal perspective. Understanding the behaviours, decisions and actions exhibited by artificially intelligent agents has been a central theme of interest since the inception of agent research. As systems grow in complexity, the agents' underlying reasoning mechanisms can become opaque and the intelligibility towards humans can be diminished, which can have negative consequences in high-stakes and highly-collaborative domains. The explainable agency of an autonomous agent can aid in transferring the knowledge of this reasoning process to the user to improve intelligibility. If we are to build effective explainable agency, a careful inspection of how humans generate, select and communicate explanations is needed. Explaining the behaviour and actions of sequential decision making reinforcement learning (RL) agents introduces challenges such as handling long-term goals and rewards, in contrast to one-shot explanations in which the attention of explainability literature has largely focused. Taking inspirations from cognitive science and philosophy literature on the nature of explanation, this thesis presents a novel explainable model ---action influence models--- that can generate causal explanations for reinforcement learning agents. A human-centred approach is followed to extend action influence models to handle distal explanations of actions, i.e. explanations that present future causal dependencies. To facilitate an end-to-end explainable agency, an action influence discovery algorithm is proposed to learn the structure of the causal relationships from the RL agent's interactions. Further, a dialogue model is also introduced, that can instantiate the interactions of an explanation dialogue. The original work presented in this thesis reveals how a causal and human-centred approach can bring forth a strong explainable agency in RL agents.
-
ItemMulti-Granular Webpage Information Extraction and Analysis via Deep Joint Learning( 2020)The number of webpages is growing exponentially, which results in a great volume of unstructured information on the web. It takes time either to fully comprehend a webpage or to retrieve relevant information from a complex webpage. Analyzing unstructured webpage and extracting structured information from the webpage automatically is crucial. In this study, we aim to develop algorithms for multi-granular webpage information extraction and analysis to facilitate webpage information understanding. We investigate the problem at three levels of granularity, i.e., micro, meso and macro levels. For every level, we focus on one extraction and analysis task, although the algorithms we developed are general and can be applied to many other similar tasks. At the micro level, we aim to extract webpage entities that have diverse forms, and focus on the application of person name recognition. We propose a fine-grained annotation scheme based on anthroponymy and create the first dataset for fine-grained name recognition. We propose a joint model that learns the different name form classes with two sub-neural networks while fusing the learned signals through co-attention and gated fusion mechanisms. Experimental results show that our annotations can be utilised in different ways to improve the recognition performance. At the meso level, we study the relationships between webpage entities and blocks with a focus on the application of joint recognition of names and publications. We address the person name recognition and publication string recognition tasks in academic homepages jointly based on the insight that the two tasks are inherently correlated. We propose a joint model to capture the interdependencies between entities. We also capture global position patterns of blocks and local position patterns of entities in the model learning process. Empirical results on real datasets show that our model outperforms the state-of-the-art publication string recognition model and person name recognition model. Experimental results also show that our model outperforms baseline joint models. At the macro level, we aim to provide hierarchical analysis for webpages from diverse domains. We introduce the Webpage Briefing (WB) task, which aims to generate a summary of a webpage in a hierarchical manner, starting at the top is an abstract and general description of the topic of the webpage page, followed by high level key attributes extracted from the webpage, and then lower level key attributes, which contain concrete and specific key information. We propose to perform webpage briefing by identifying and summarizing the informative contents, which mimic human behaviour of understanding a complex webpage. We propose a novel Dual Distillation method that has a teacher-student architecture with dual distillation. We further propose a Triple Distillation method to better exploit the inherent correlation of specific key attributes and general topics of webpages. We finally propose a novel Triple Joint model that has a triple joint learning architecture with signal exchange and enhancement mechanisms. Experimental results show the superiority of Bi-Distill method and Tri-Distill over baseline methods. Experimental results also show that Tri-Join outperforms baseline single-task models and baseline jointly trained models.
-
ItemCost-efficient Management of Cloud Resources for Big Data Applications( 2020)Analyzing a vast amount of business and user data on big data analytics frameworks is becoming a common practice in organizations to get a competitive advantage. These frameworks are usually deployed in a computing cluster to meet the analytics demands in every major domain, including business, government, financial markets, and health care. However, buying and maintaining a massive amount of on-premise resources is costly and difficult, especially for start-ups and small business organizations. Cloud computing provides infrastructure, platform, and software systems for storing and processing data. Thus, Cloud resources can be utilized to set up a cluster with a required big data processing framework. However, several challenges need to be addressed for Cloud-based big data processing which includes: deciding how much Cloud resources are needed for each application, how to maximize the utilization of these resources to improve applications' performance, and how to reduce the monetary cost of resource usages. In this thesis, we focus on a user-centric view, where a user can be either an individual or a small/medium business organization who want to deploy a big data processing framework on the Cloud. We explore how resource management techniques can be tailored to various user-demands such as performance improvement, and deadline guarantee for the applications; all while reducing the monetary cost of using the cluster. In particular, we propose efficient resource allocation and scheduling mechanisms for Cloud-deployed Apache Spark clusters.