YorkSpace has migrated to a new version of its software. Access our Help Resources to learn how to use the refreshed site. Contact diginit@yorku.ca if you have any questions about the migration.
 

Computer Science

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 61
  • ItemOpen Access
    Precision Recall Cover: A Method to Assess Generative Models
    (2023-12-08) Cheema, Fasil Tariq; Urner, Ruth
    Generative modelling has seen enormous practical advances over the past few years from LLMs like ChatGPT to image generation. However, evaluating the quality of a generative system is often still based on subjective human inspection. To overcome this, very recently, the research community has turned to exploring formal evaluation metrics and methods. In this work, we propose a novel evaluation method based on a two-way nearest neighbor test. We define a new measure of mutual coverage for two probability distributions. From this, we derive an empirical analogue and show analytically that it exhibits favorable theoretical properties while it is also straightforward to compute. We show that, while algorithmically simple, our derived method is also statistically sound. We complement our analysis with a systematic experimental evaluation and comparison to other recently proposed measures. Using a wide array of experiments, we demonstrate our algorithm’s strengths over other existing methods and confirm our results from the theoretical analysis.
  • ItemOpen Access
    Investigating Calibrated Classification Scores through the Lens of Interpretability
    (2023-12-08) Torabian, Alireza; Urner, Ruth
    Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a scoring function whose scores correctly reflect underlying label probabilities. Calibration in itself however does not imply classification accuracy, nor human interpretable estimates, nor is it straightforward to verify calibration from finite data. There is a plethora of evaluation metrics (and loss functions) that each assesses a specific aspect of a calibration model. In this work, we initiate an axiomatic study of the notion of calibration and evaluation measures for calibration. We catalogue desirable properties of calibration models as well as evaluation metrics and analyze their feasibility and correspondences. We complement this analysis with an empirical evaluation, comparing two metrics and comparing common calibration methods to employing a simple, interpretable decision tree.
  • ItemOpen Access
    Leveraging Deep Learning for Trajectory Similarity Learning and Trajectory Pathlet Dictionary Construction
    (2023-12-08) Alix, Gian Carlo Idris; Papangelis, Emmanouil
    The rapid development of geospatial technologies and location-based devices have motivated the research community of trajectory data mining, due to numerous applications including route planning and navigation services. Of interest are similarity search tasks that several works addressed through representation learning. Our method ST2Box offers refined representations by first representing trajectories as sets of roads, then adapting set-to-box architectures for learning accurate, versatile, and generalizable set representations of trajectories for preserving similarity. Experimentally, ST2Box outperforms baselines by up to ~38%. Another related problem involves constructing small sets of building blocks that can represent wide-ranging trajectories (pathlet dictionaries). However, currently-existing methods in constructing PDs are memory-intensive. Thus, we propose PathletRL for generating dictionaries that offer significant memory-savings. It initializes unit-length pathlets and iteratively merges them while maximizing utility -- that is approximated using deep reinforcement learning-based method. Empirically, PathletRL can reduce its dictionary's size by up to 65.8% against state-of-the-art methods.
  • ItemOpen Access
    Chart Question Answering with an Universal Vision-Language Pretraining Approach
    (2023-12-08) Parsa Kavehzadeh; Enamul Hoque Prince
    Charts are widely used for data analysis, providing visual representations and insights into complex data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced recently including chart question answering. However, existing methods for these tasks often rely on pretraining on language or vision-language tasks, neglecting the explicit modeling of chart structures. To address this, we first build a large corpus of charts covering diverse topics and visual styles. We then present UniChart, a pretrained model for chart comprehension and reasoning. We propose several chart-specific pretraining tasks that include: (i) low-level tasks to extract the visual elements (e.g., bars, lines) and data from charts, and (ii) high-level tasks to acquire chart understanding and reasoning skills. Our experiments demonstrate that pretraining UniChart on a large corpus with chart-specific objectives, followed by fine-tuning, yields state-of-the-art performance on four downstream tasks. Moreover, our model exhibits superior generalizability to unseen chart corpus, surpassing previous approaches that lack chart-specific objectives and utilize limited chart resources.
  • ItemOpen Access
    Evaluating Temporal Queries over Videos
    (2023-12-08) Chen, Yueting; Yu, Xiaohui
    Videos have been an important part of people's daily lives and are continuously growing in terms of volume, size, and variety of content. Recent advances in Computer Vision (CV) algorithms have improved accuracy and efficiency, making video annotations possible with high accuracy. In this work, we follow a general framework to first obtain annotations utilizing state-of-the-art CV algorithms, and then consider three research problems on evaluating temporal queries with such annotations. Specifically, we first investigate the temporal queries that consider only co-occurrence relationships between objects on video feeds, where we take the first step and define such queries in a way that they incorporate certain physical aspects of video capture such as object occlusion. We propose two techniques, Marked Frame Set (MFS) and Sparse State Graph (SSG), to organize all detected objects in the intermediate data generation layer, which effectively, given the queries, minimizes the number of objects and frames that have to be considered during query evaluation. Then, we consider the query with a ranking mechanism that aims to retrieve clips from large video repositories in which objects co-occur in a query-specified fashion. We propose a two-phased approach, where we build indexes during the Ingestion Phase, and then answer queries during the Query Phase using the Partition-Based Query Processing (PBQP) algorithm, which efficiently produces the desired (query-specified) number of results with the highest scores. Finally, we further consider both spatial and temporal information with graph representations and define the problem of Spatial and Temporal Constrained Ranked Retrieval (STAR Retrieval) over videos. Based on the graph representation, we propose a two-phase approach, consisting of the ingestion phase, where we construct and materialize the Graph Index (GI), and the query phase, where we compute the top-ranked windows (video clips) according to the window matching score efficiently. We propose two algorithms to perform Spatial Matching (SMA) and Temporal Matching (TM) separately with an early-stopping mechanism. We present the details of the above three research problems and our proposed methods. Via experiments conducted on various datasets, we show the effectiveness of our proposed methods.
  • ItemOpen Access
    Fine Granularity is Critical for Intelligent Neural Network Pruning
    (2023-12-08) Heyman, Andrew Baldwin; Zylberberg, Joel
    Neural network pruning is a popular approach to reducing the computational costs of training and/or deploying a network, and aims to do so while minimizing accuracy loss. Pruning methods that remove individual weights (fine granularity) yield better ratios of accuracy to parameter count, while methods that preserve some or all of a network’s structure (coarser granularity, e.g. pruning channels from a CNN) take better advantage of hardware and software optimized for dense matrix computations. We compare intelligent iterative pruning using several different criteria sampled from the literature against random pruning at initialization across multiple granularities on two different image classification architectures and tasks. We find that the advantage of intelligent pruning (with any criterion) over random pruning decreases dramatically as granularity becomes coarser. Our results suggest that, compared to coarse pruning, fine pruning combined with efficient implementation of the resulting networks is a more promising direction for improving accuracy-to-cost ratios.
  • ItemOpen Access
    A 360-degree Omnidirectional Photometer Using a Ricoh Theta Z1
    (2023-12-08) MacPherson, Ian Michael; Brown, Michael S.
    Spot photometers measure the luminance emitted or reflected from a small surface area in a physical environment. Because the measurement is limited to a "spot," capturing dense luminance readings for an entire environment is impractical. This thesis demonstrates the potential of using an off-the-shelf commercial camera to operate as a 360-degree luminance meter. The method uses the Ricoh Theta Z1 camera, which provides a full 360-degree omnidirectional field of view and an API to access the camera's minimally processed RAW images. Working from the RAW images, this thesis describes a calibration method to map the RAW images under different exposures and ISO settings to luminance values. By combining the calibrated sensor with multi-exposure high-dynamic-range imaging, a cost-effective mechanism for capturing dense luminance maps of environments is provided. The results show that the Ricoh Theta calibrated as a luminance meter performs well when validated against a significantly more expensive spot photometer.
  • ItemOpen Access
    Query-Aware Data Systems Tuning via Machine Learning
    (2023-12-08) Henderson, Connor Dustin; Szlichta, Jarek
    Modern data systems have hundreds of system configuration parameters which heavily influence the performance of business queries. Manual configuration by experts is painstaking and time consuming. We propose a query-informed tuning system called BLUTune which uses deep reinforcement learning based on advantage actor-critic neural networks to tune configurations within defined resource constraints. We translate high-dimensional query execution plans into a low-dimensional embedding space and illustrate the usefulness of query embeddings for the downstream task of data systems tuning. We train our model based on the estimated cost of queries then fine-tune it using query execution times. We present an experimental study over various synthetic and real-world workloads. One model uses TPC-DS queries such that there are tables from the schema that are not seen during training time. The second is trained under resource constraints to show how the model performs when we limit the memory the system has access to.
  • ItemOpen Access
    Automation in Open Source Software: A GitHub Marketplace Analysis
    (2023-12-08) Saroar, Sk Golam; Nayebi, Maleknaz
    This thesis comprises two papers that examine automation tools in the Open Source Software (OSS) ecosystem on GitHub, focusing on GitHub Actions as well as the GitHub Marketplace, which is a platform for sharing these Actions for collaboration and reuse. Our research aims to understand and explore the state of automation in OSS, as existing studies have mainly focused on statistical analysis of a sample of GitHub repositories, neither considering developers’ perspectives nor leveraging the GitHub Marketplace. The first paper conducted a survey analysis to investigate the motivations, decision criteria, and challenges associated with creating, publishing, and using Actions. The second paper explores the GitHub Market- place and presents a mapping study by analyzing 7,878 Actions and 515 research papers mapped into 32 different categories. We found a substantial industry-academia gap, with researchers focusing on experimentation and practitioners relying more on exploration tools. The limited number of OSS automation tools published in academia contrasted with the convenient access practitioners had to the marketplace offerings. This thesis contributes to the understanding of automation in the OSS ecosystem, highlights the industry-academia gap, offers insights for researchers to build on existing work, and aids practitioners in navigating technology and finding synergies.
  • ItemOpen Access
    Fault Analysis and Control of DFIGs for Grid Code Compliance and Protection of Power System
    (2023-12-08) Mohammadpour, Hassan; Hooshyar, Ali
    Inverter-based resources (IBRs) are growing at exponential rates in today's power systems. Therefore, a sizable portion of the measurements of relays is expected to come from IBRs. However, the fault current characteristics of IBRs put the operation of the relays in jeopardy as they are different than that of synchronous generators' (SGs) based on which the relays' operating principles are developed. Therefore, different countries have progressively revised their grid codes (GCs) to reduce the likelihood of protection malfunctions and ensure stable and continuous operation of power systems. Similar to emerging regional GCs, the recently approved IEEE 2800 Standard mandates that IBRs generate negative-sequence current during low-voltage ride-through (LVRT) conditions. The 2800 Standard requires that the IBRs' negative-sequence current lead the negative-sequence voltage by 90-100 degrees to emulate SGs and reduce the likelihood of protection malfunction. However, the limitations of existing doubly-fed induction generators (DFIGs) led the Standard to exempt the DFIGs from this requirement and allow a wider range for their negative-sequence current angle. Meanwhile, the 2800 Standard also acknowledged that this exemption had unidentified and potentially negative impacts on protective relays. This dissertation, for the first time, (i) sheds light on several so-far-unknown DFIG characteristics that impact the angle of the negative-sequence current during LVRT, (ii) reveals the impacts of the above DFIG exemption on industrial relays, and (iii) develops a solution to prevent the need for this exemption in the future revisions of the IEEE 2800 Standard. This dissertation also investigates the challenges brought about by the DFIGs during the crowbar connection and rectification mode of operation, i.e., interrupted control of the DFIG's converters, now affecting the performance of distance relays that are installed at a DFIG-based wind farm substation. The focus is on the relays implemented using the apparent impedance approach and the commercially developed reactance method. It is revealed that the phase elements of a distance relay that uses these methods are prone to under-/over-reach in the systems with DFIGs. The exclusive fault behavior of DFIGs along with different units of a distance relay is scrutinized to identify the root causes. To address the relay problems, a communication-assisted method with minimal bandwidth requirement is developed, which provides non-delayed fast tripping over the entire length of the line.
  • ItemOpen Access
    Cyber-Physical Attacks Detection and Resilience Methods in Smart Grids
    (2023-12-08) Sawas, Abdullah; Farag, Hany E. Z.
    Backed by the deployment of increasingly reliable Information and Communication Technologies (ICT) infrastructure, modern power systems heavily depend on computerized circuits to function within an interconnected environment. In particular, Smart Grids (SGs) core domain relies on ICTs networks and components to communicate control signals and data measurements to improve the efficiency of power generation and distribution while maintaining safe and reliable operations. ICTs have also extended the SG domain of interaction to include other utilities, such as the natural gas grid to efficiently utilize multiple energy forms and resources. In the consumer domain, a growing number of appliances and autonomous smart loads equipped with Internet of Things (IoT) technology are being deployed into SG, the results in large portions of electric demand being remotely controlled. Despite their advantages, ICTs are vulnerable to cyber–attacks that can deteriorate SGs' operational safety and integrity. Thus, new approaches to enhance the resiliency of SGs against cyber-physical attacks are needed. To that extent, this thesis develops new resiliency investigation approaches under the three aforementioned domains. First, in the SG domain, an efficient False Data Injection Attack (FDIA) approach is developed imitating an intelligent adversary behavior searching for an optimal attack vector against State Estimation (SE) modules. Simulation results show that using this approach, an adversary can identify attack vectors with minimal size and superior flexibility to manipulate, in real-time, power flow measurements of the system lines as perceived by the SE without the need to acquire additional measurements. Hence, attacks constructed using this approach require less computational time and resources compared to the existing methods making it beneficial for the analysis of cyber–security vulnerabilities and the design of resilient SE modules. Second, under the Integrated Energy System (IES) domain, an operational framework model is developed to be used as a testbed for performing and analyzing the impact of cyber–attacks. The framework models steady–state power and gas flow operations, and presents a new financial interdependency operation scheduling model. The framework is validated on standard power distribution and transmission systems with variable generation and demand scenarios and high renewable penetration levels. Using this framework, an attack resiliency method is developed based on signal processing and machine-learning tools. The method is able to detect 98.6% and 94.5% of the external signals and internal control commands respectively. Third, the vulnerability of Power Distribution Systems (PDSs) to compromised collections of IoT-enabled appliances is investigated, and a stealthy attack strategy is presented. Accordingly, a new index is developed, referred to as Feeder Loading Abnormal Power Spectrum (FLAPS), and used in a novel real-time detection and prediction approach to counter stealthy attacks and estimate the attack onset time. Results demonstrate that the method is able to detect and alert for stealthy attacks in a timely manner, thereby enabling the system to operate reliably and securely. By identifying new attacks, and proposing detection methods and countermeasures, this thesis contributes to the collective efforts to address the risks associated with cyber–attacks against the SGs components. Specifically, the quantitative results show that deploying the proposed methods will enhance the resiliency of SE and IESs, and protect the PDSs against threats of large-scale deployment of IoT-enabled appliances.
  • ItemOpen Access
    Online and Hierarchical Agent Supervision
    (2017-12) Banihashemi, Bita; Lesperance, Yves
    Agent supervision is a form of control/customization where a supervisor restricts the behavior of an agent to enforce certain requirements, while leaving the agent as much autonomy as possible. This framework is based on the situation calculus and a variant of the ConGolog agent programming language. In this dissertation, we focus on two of the open problems with the original account of agent supervision. The first open problem is supervising an agent that may acquire new knowledge about her environment during an online execution, for example, by sensing. The second open problem concerns the supervision of agents that operate in complex domains and have complex behavior. Such agents typically need to represent and reason about a large amount of knowledge. One approach to cope with this challenge is to use abstraction, which involves developing an abstract/high-level model of the agent behavior that suppresses less important details. Hence, we first investigate abstracting an agent's behavior in offline executions, and formalize a notion of sound and/or complete abstractions. Sound abstractions can be used to perform several forms of reasoning about action, such as planning, agent monitoring, and generating high-level explanations of low-level/concrete agent behavior. Moreover, we investigate abstraction of agent's behavior in online executions, and discuss its relation to hierarchical contingent planning. We then use our results on offline agent abstraction to formalize hierarchical agent supervision: in a first step, we only consider the high-level model and obtain the maximally permissive supervisor to customize the abstract agent behavior; then in a second step, we obtain a low-level supervisor by refining the high-level supervisor's actions locally. We show that this process can be done incrementally, without precomputing the local refinements.
  • ItemOpen Access
    Batch Query Memory Prediction Using Deep Query Template Representations
    (2023-08-04) Jaramillo, Nicolas Andres; Papagelis, Manos; Litoiu, Marin
    This thesis introduces a novel approach called LearnedWMP for predicting the memory cost demand of a batch of queries in a database workload. Existing techniques focus on estimating the resource demand of individual queries, failing to capture the net resource demand of a workload. LearnedWMP leverages the query plan and groups queries with similar characteristics into pre-built templates. A histogram representation of these templates is generated for the workload, and a regressor predicts the resource demand, specifically memory cost, based on this histogram. Experimental results using three database benchmarks demonstrate a 47.6% improvement in memory estimation compared to the state-of-the-art. Additionally, the approach outperforms various machine and deep learning techniques for individual query prediction, offering a 3x to 10x faster and at least 50% smaller model size.
  • ItemOpen Access
    Few-Shot User Intent Detection and Response Selection for Conversational Dialogue System Using Deep Learning
    (2023-08-04) Yuan, Wei; An, Aijun
    Conversational dialogue systems (CDSs), also known as conversational agents, have made significant development in recent years, driven by advances in natural language processing, machine learning, and artificial intelligence techniques. As a result, CDSs have been implemented across various industries, including education, e-commerce, and customer service in messaging apps, websites, and mobile apps to engage with users through natural language. The primary objective of chatbots is to facilitate communication with people and make numerous repetitious tasks easier for humans. This thesis investigates the application of deep learning methodologies in enterprise CDSs to enhance interpretability, fostering user trust in decision-making processes. The contributions of this thesis include proposing example and description-driven approaches that focus on the semantic similarities between the user input and the intent examples or descriptions in a topological tree for few-shot intent detection in enterprise CDSs. Moreover, this thesis presents a novel Topic-Aware Response Selection (TARS) model to retrieve the most suitable and coherent response from a set of candidates based on contextual information for users in persona-based CDSs.
  • ItemOpen Access
    Trajectory-User Linking Using Higher-Order Mobility Flow Representations
    (2023-08-04) Alsaeed, Mahmoud; Papangelis, Emmanouil
    Trajectory-user linking (TUL) is a problem in trajectory classification that links anonymous trajectories to the users who generated them. TUL has various uses such as identity verification, personalized recommendation, epidemiological monitoring, and threat assessments. A major challenge in TUL modeling is sparse data. Previous TUL research heavily relies on recurrent neural networks models such as RNNs and LSTMs, with trajectory segmentation to combat sparsity, but segmentation does not sufficiently address the issue and existing models often ignore data skewness, resulting in poor precision and performance. To address these problems, we present TULHOR, a TUL model inspired by BERT, a popular language representation model. One of TULHOR's innovations is the use of higher-order mobility flow data representations enabled by geographic area tessellation. This allows the model to alleviate the sparsity problem and also to generalize better. TULHOR consists of a spatial embedding layer, a spatial-temporal embedding layer and an encoder layer, which encodes properties and learns a rich trajectory representation. It is trained in two steps, first using a masked language modeling task to learn general embeddings, then fine-tuned using a balanced cross-entropy loss to make predictions while handling imbalanced data. Experiments on real-life mobility data show TULHOR's effectiveness as compared to current state-of-the-art models.
  • ItemOpen Access
    A Graph-Based Deep Learning Model for Anti-Money Laundering
    (2023-08-04) Bakhshinejad, Nazanin; Nguyen, Uyen T.
    Anti-money laundering (AML) refers to a set of laws, regulations, and procedures that financial institutions and other regulated entities are required to implement to identify and prevent the use of their services for illicit financial activities. Current AML solutions rely on rule-based algorithms, which are not scalable and ineffective against new, evolving or complex money laundering patterns. On the other hand, the rapid advancement of technology and new sophisticated financial instruments have increased the complexity of money laundering methods. Machine learning has the capability to learn and identify new or complex money laundering patterns. Within this context, the thesis offers two major contributions. First, we conducted a survey that provides a comprehensive review of existing machine learning-based AML solutions from a data-oriented perspective. We studied existing machine learning models proposed for AML in terms of datasets used, input and output data, approaches to the class imbalance problem, and classification metrics. To the best of our knowledge, this survey is the first that focuses on different aspects of data, classification metrics and related issues (e.g., the class imbalance problem). Second, we propose an AML detection system and a graph-based machine learning model to identify suspicious transactions. The detection system first transforms a dataset of accounts and transactions into a graph structure and applies the node2vec (N2V) algorithm to convert the graphs into feature vectors. The feature vectors are then input into a graph convolution network (GCN), which will then classify the transactions as normal or suspicious. (Each suspicious transaction, which is known as an alarm, will be investigated manually by a financial analyst to confirm if it is a normal transaction or a money laundering transaction.) To overcome the inherent class imbalance of AML data (i.e., the number of money laundering transactions in a dataset is much smaller than the number of normal transactions), we use a combination of techniques, including over-sampling and classifier threshold moving. Our experimental results show that the proposed N2V-GCN system can achieve very low false negative rates (money laundering transactions misclassified as normal transactions), reaching zero in one experiment. At the same time, the proposed system lowers the false alarm rates (normal transactions classified as suspicious transactions) to under 50%, much lower than the current industry standard of 90% or more.
  • ItemOpen Access
    Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention
    (2023-08-04) Do, Viet Ho Tam Thuc; Cheung, Gene
    We study 3D point cloud attribute compression using a volumetric approach: given a target volumetric attribute function $f : \mathbb{R}^3 \rightarrow \mathbb{R}$, we quantize and encode parameter vector $\theta$ that characterizes $f$ at the encoder, for reconstruction $f_{\hat{\theta}}(\x)$ at known 3D points $\x$'s at the decoder, where $\hat{\theta}$ is a quantized version of $\theta$. Extending a previous work Region Adaptive Hierarchical Transform (RAHT) that employs piecewise constant functions to span a nested sequence of function spaces, we propose a feedforward linear network that implements higher-order B-spline bases spanning function spaces without eigen-decomposition. Feedforward network architecture means that the system is amenable to end-to-end neural learning. The key to our network is space-varying convolution, similar to a graph operator, whose weights are computed from the known 3D geometry for normalization. We show that the number of layers in the normalization at the encoder is equivalent to the number of terms in a matrix inverse Taylor series. Experimental results on real-world 3D point clouds show up to 2-3 dB gain over RAHT in energy compaction and 20-30\% in bitrate reduction.
  • ItemOpen Access
    Sparse Shape Encoding for Improved Instance Segmentation
    (2023-08-04) Liu, Keyi; Elder, James
    Neurophysiological studies suggest that neurons in the intermediate visual area V4 of the primate cortex encode a sparse representation of object shape. While there are metabolic arguments for such sparse representations, there are also potential advantages for inference. Here we explore whether sparse shape encoding can yield benefits for instance segmentation. Specifically, we encode 2D object shape using a Distance Transform Map(DTM) and learn a sparse basis for this representation. To make use of this encoding, we design an instance segmentation head to estimate the sparse coefficients of each object, and then recover the shape from the zero-crossing level set of the corresponding DTM. Our novel SparseShape encoding approach produces fewer topological errors than the state-of-the-art, yields competitive mask AP on the MS COCO benchmark, and exhibits superior generalization performance on the Cityscapes traffic instance segmentation task.
  • ItemOpen Access
    Augmented Reality Water-Level Task
    (2023-08-04) Abadi, Romina; Allison, Robert
    The``Water Level Task'' asks participants to draw the water level in a tilted container. Studies showed that many adults have difficulty with the task. Our study aimed to determine if the misconception about water orientation happens in a more natural environment. We implemented an AR water-in-container effect to create an augmented reality (AR) version of the Water-Level task (AR-WLT). In the AR-WLT, participants interacted with two containers half full of water in a Hololens2 AR display and were asked to determine which looked more natural. In at least one of the two simulations, the water surface did not remain horizontal. A traditional online WLT was created to recruit low and high-scoring participants. Our results showed that low-scoring individuals were likelier to make errors in the AR version. However, participants did not choose simulations close to their 2D drawings, suggesting different cognitive and perceptual factors were involved in different environments.
  • ItemOpen Access
    Learning Effective Embeddings for Dynamic Graphs and Quantifying Graph Embedding Interpretability
    (2023-03-28) Khoshraftar, Shima; An, Aijun
    Graph representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate representation vectors that accurately capture the structure and features of large graphs. This is especially important because the quality of the graph representation vectors will affect the performance of these vectors in downstream tasks such as node classification and link prediction. Many techniques have been proposed for generating effective graph representation vectors. These methods can be applied to both static and dynamic graphs. A static graph is a single fixed graph, while a dynamic graph evolves over time, and its nodes and edges can be added or deleted from the graph. We surveyed the graph embedding methods for both static and dynamic graphs. The majority of the existing graph embedding methods are developed for static graphs. Therefore, since most real-world graphs are dynamic, developing novel graph embedding methods suitable for evolving graphs is essential. This dissertation proposes three dynamic graph embedding models. In previous dynamic methods, the inputs were mainly adjacency matrices of graphs which are not memory efficient and may not capture the neighbourhood structure in graphs effectively. Therefore, we developed Dynnode2vec based on random walks using the static model Node2vec. Dynnode2vec generates node embeddings in each snapshot by initializing the current model with previous embedding vectors and training the model using a set of random walks obtained for nodes in the snapshot. Our second model, LSTM-Node2vec, is also based on random walks. This method leverages the LSTM model to capture the long-range dependencies between nodes in combination with Node2vec to generate node embeddings. Finally, inspired by the importance of substructures in the graphs, our third model TGR-Clique generates node embeddings by considering the effects of neighbours of a node in the maximal cliques containing the node. Experiments on real-world datasets demonstrate the effectiveness of our proposed methods in comparison to the state-of-the-art models. In addition, motivated by the lack of proper measures for quantifying and comparing graph embeddings interpretability, we proposed two interpretability measures for graph embeddings using the centrality properties of graphs.