Graphs are commonly employed to model complex data and discover latent patterns and relationships between entities in the real world. Canonical graph learning models have achieved remarkable progress in modeling and inference on graph-structured data that consists of nodes connected by edges. Generally, they leverage abundant labeled data for model training and thus inevitably suffer from the label scarcity issue due to the expense and hardship of data annotation in practice. Data-efficient graph learning attempts to address the prevailing data scarcity issue in graph mining problems, of which the key idea is to transfer knowledge from the related resources to obtain the models with good generalizability to the target graph-related tasks with mere annotations. However, the generalization of the models to data-scarce scenarios is faced with challenges including 1) dealing with graph structure and structural heterogeneity to extract transferable knowledge; 2) selecting beneficial and fine-grained knowledge for effective transfer; 3) addressing the divergence across different resources to promote knowledge transfer. Motivated by the aforementioned challenges, the dissertation mainly focuses on three perspectives, i.e., knowledge extraction with graph heterogeneity, knowledge selection, and knowledge transfer. The purposed models are applied to various node classification and graph classification tasks in the low-data regimes, evaluated on a variety of datasets, and have shown their effectiveness compared with the state-of-the-art baselines.

The purpose of this study was to measure the change in joint energy of the hip,knee and ankle of the right and left leg, in the sagittal plane during the delivery phase of the rotational shot put. We hypothesized that (1) throwers who produced a greater total hip energy change would have greater horizontal displacement and (2) throwers who produced a higher ratio of hip energy, in each leg independently, would produce greater horizontal displacement. Subjects (n = 8) must have been right-handed, collegiate or post collegiate level throwers trained in the rotational technique. Vicon Nexus System (Denver, CO, USA) used six MX13+, two F20, two T20 cameras recorded at 240 Hz, and the body Plug-in Gait model to track the body position during each trial. Two AMTI force plates (OR-6, Watertown, MA, USA) were used for collecting ground reaction force data at 960 Hz. A linear regression analysis was performed to determine a relationship between total hip energy change and horizontal displacement. A mixed model regression was used to determine any correlation between horizontal distance and left and right energy change ratios. Athletes who produced a greater total hip energy change had the greatest horizontal displacement (p = .022). Also throwers who produced a higher ratio of left hip energy change to total left leg energy produced the greatest horizontal displacement (p = .02). The ratio of right hip energy change to right leg energy change was found to not be significant to horizontal displacement (p = .955). We feel the findings on the left leg energy change are an attempt by the athlete to both accelerate the shot put as well as stop the rotational progression to allow the athlete to complete a fair throw. The athlete extending both the right and the left hip rapidly during the delivery phase can help explain the combined right and left hip energy change. This action accelerates the ball in a proximal-distal sequence, which allows athletes to reach high final shot put velocities. The higher the final velocity on the shot put positively correlates with the horizontal displacement.

Zero-Shot Learning (ZSL) for image classification aims to recognize images from novel classes for which we have no training examples. A common approach to tackling such a problem is by transferring knowledge from seen to unseen classes using some auxiliary semantic information of class labels in the form of class embeddings. Most of the existing methods represent image features and class embeddings as point vectors, and such vector representation limits the expressivity in terms of modeling the intra-class variability of the image classes. In this thesis, we propose three novel ZSL methods that represent image features and class labels as distributions and learn their corresponding parameters as distribution embeddings. Therefore, the intra-class variability of image classes is better modeled. The first model is a Triplet model, where image features and class embeddings are projected as Gaussian distributions in a common space, and their associations are learned by metric learning. Next, we have a Triplet-VAE model, where two VAEs are trained with triplet based distributional alignment for ZSL. The third model is a simple Probabilistic Classifier for ZSL, which is inspired by energy-based models. When evaluated on the common benchmark ZSL datasets, the proposed methods result in an improvement over the existing state-of-the-art methods for both traditional ZSL and more challenging Generalized-ZSL (GZSL) settings. / Zero-Shot Learning (ZSL) för bildklassificering syftar till att känna igen bilder från nya klasser som vi inte har några utbildningsexempel för. Ett vanligt tillvägagångssätt för att ta itu med ett sådant problem är att överföra kunskap från sett till osynliga klasser med hjälp av någon semantisk information om klassetiketter i form av klassinbäddningar. De flesta av de befintliga metoderna representerar bildfunktioner och klassinbäddningar som punktvektorer, och sådan vektorrepresentation begränsar uttrycksförmågan när det gäller att modellera bildklassernas variation inom klass. I denna avhandling föreslår vi tre nya ZSL-metoder som representerar bildfunktioner och klassetiketter som distributioner och lär sig deras motsvarande parametrar som distributionsinbäddningar. Därför är bildklassernas variation inom klass bättre modellerad. Den första modellen är en Triplet-modell, där bildfunktioner och klassinbäddningar projiceras som Gaussiska fördelningar i ett gemensamt utrymme, och deras föreningar lärs av metrisk inlärning. Därefter har vi en Triplet-VAE-modell, där två VAEs tränas med tripletbaserad fördelningsinriktning för ZSL. Den tredje modellen är en enkel Probabilistic Classifier för ZSL, som är inspirerad av energibaserade modeller. När de utvärderas på de vanliga ZSLdatauppsättningarna, resulterar de föreslagna metoderna i en förbättring jämfört med befintliga toppmoderna metoder för både traditionella ZSL och mer utmanande Generalized-ZSL (GZSL) -inställningar.

Wireless networks are vulnerable to adversarial devices by spoofing the digital identity of valid wireless devices, allowing unauthorized devices access to the network. Instead of validating devices based on their digital identity, it is possible to use their unique "physical fingerprint" caused by changes in the signal due to deviations in wireless hardware. In this thesis, the physical fingerprint was validated by performing classification with complex-valued neural networks (NN), achieving a high level of accuracy in the process. Additionally, zero-shot learning (ZSL) was implemented to learn discriminant features to separate legitimate from unauthorized devices using outlier detection and then further separate every unauthorized device into their own cluster. This approach allows 42\% of unauthorized devices to be identified as unauthorized and correctly clustered

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.