Computing and Information Systems - Theses
Permanent URI for this collection
Search Results
1 - 4 of 4
-
ItemGenerating Deep Network Explanations with Robust Attribution Alignment( 2021)Deep Neural Networks (DNNs) have achieved impressive success in many fields, yet the black-box nature of DNNs hinders their application in critical domains, such as the medical domain. To this end, Interpretable Machine Learning (IML) is a research field aims to understand the mechanism behind DNNs via interpretability methods, which aim to provide explanations to human users and help them understand how black-box models make decisions. Current IML methods produce post-hoc attribution maps on pre-trained models. However, recent studies have shown that most of these methods yield unfaithful and noisy explanations. In this study, we present a new paradigm of interpretability methods to improve the quality of explanations. We treat a model’s explanations as a part of the network’s outputs, then generate attribution maps from the underlying deep network. The generated attribution maps are up-sampled from the last convolutional layer of the network to obtain localization information about the target to be explained. Another intuition behind this study is leveraging the connection between interpretability and adversarial machine learning to improve the quality of explanations. Inspired by recent studies that showed adversarially robust models’ saliency aligns well with human perception, we utilize attribution maps from the robust model to supervise the learned attributions. Our proposed method can produce visually plausible explanations along with the prediction in inference phase. Experiments on real datasets show that our proposed method yields more faithful explanations than post-hoc attribution methods with lighter computational costs.
-
ItemFoundations for reasoning about holistic specifications( 2020)Specifications of sufficient conditions may be enough for reasoning about complete and unchanging programs of a closed system. Nevertheless, there is no luxury of trusting external components of probably unknown provenance in an open world that may be buggy or potentially malicious. It is critical to ensure that our components are robust when cooperating with a wide variety of external components. Holistic specifications, which are concerned with sufficient and necessary conditions, could make programs more robust in an open-world setting. In this thesis, we lay the foundations for reasoning about holistic specifications. We give an Isabelle/HOL mechanization of holistic specifications focusing on object-based programs. We also pave a way to reason about holistic specifications via proving some key lemmas that we hope will be useful in the future to establish a general logic for holistic specifications.
-
ItemLearning to generalise through features( 2020)A Markov decision process (MDP) cannot be used for learning end-to-end control policies in Reinforcement Learning when the dimension of the feature vectors changes from one trial to the next. For example, this difference is present in an environment where the number of blocks to manipulate can vary. Because we cannot learn a different policy for each number of blocks, we suggest framing the problem as a POMDP instead of the MDP. It allows us to construct a constant observation space for a dynamic state space. There are two ways we can achieve such construction. First, we can design a hand-crafted set of observations for a particular problem. However, that set cannot be readily transferred to another problem, and it often requires domain-dependent knowledge. On the other hand, a set of observations can be deduced from visual observations. This approach is universal, and it allows us to easily incorporate the geometry of the problem into the observations, which can be challenging to hard-code in the former method. In this Thesis, we examine both of these methods. Our goal is to learn policies that can be generalised to new tasks. First, we show that a more general observation space can improve the performance of policies tested in untrained tasks. Second, we show that meaningful feature vectors can be obtained from visual observations. If properly regularised, these vectors can reflect the spacial structure of the state space and used for planning. Using these vectors, we construct an auto-generated reward function, able to learn working policies.
-
ItemEmbedding Graphs for Shortest-Path Distance Predictions( 2020)Graph is an important data structure and is used in an abundance of real-world applications including navigation systems, social networks, and web search engines, just to name but a few. We study a classic graph problem – computing graph shortest-path distances. This problem has many applications, such as finding nearest neighbors for place of interest(POI) recommendation or social network friendship recommendation. To compute a shortest-path distance, traditional approaches traverse the graph to find the shortest path and return the path length. These approaches lack time efficiency over large graphs. In the applications above, the distances may be needed first (e.g., to rank POIs), while the actual shortest paths may be computed later (e.g., after a POI has been chosen). Thus, an alternative approach precomputes and stores the distances, and answers distance queries with simple lookups. This approach, however, falls short in the space cost – O(n^2) in the worst-case for vertices, even with various optimizations. To address these limitations, we take an embedding based approach to predict the shortest-path distance between two vertices using their embeddings without computing their path online or storing their distance offline. Graph embedding is an emerging technique for graph analysis that has yielded strong performance in applications such as node classification, link prediction, graph reconstruction, and more. We propose a representation learning approach to learn a k-dimensional (k<