<p>Nowadays an increasing number of people consume, share, and interact with information online. This results in posting and counter-posting on online media by different ideological groups on various polarized topics. Consequently, online media has become the primary platform for political and social influencers to directly interact with the citizens and share their perspectives, views, and stances with the goal of gaining support for their actions, bills, and legislation. Hence, understanding the perspectives and the influencing strategies in online media texts is important for an individual to avoid misinformation and improve trust between the general people and the influencers and the authoritative figures such as the government.</p> <p><br></p> <p>Automatically understanding the perspectives in online media is difficult because of two major challenges. Firstly, the proper grammar or mechanism to characterize the perspectives is not available. Recent studies in Natural Language Processing (NLP) have leveraged resources from social science to explain perspectives. For example, Policy Framing and Moral Foundation Theory are used for understanding how issues are framed and the moral appeal expressed in texts to gain support. However, these theories often fail to capture the nuances in perspectives and cannot generalize over all topics and events. Our research in this dissertation is one of the first studies that adapt social science theories in Natural Language Processing for understanding perspectives to the extent that they can capture differences in ideologies or stances. The second key challenge in understanding perspectives in online media texts is that annotated data is difficult to obtain to build automatic methods to detect the perspectives, that can generalize over the large corpus of online media text on different topics. To tackle this problem, in this dissertation, we used weak sources of supervision such as social network interaction of users who produce and interact with the messages, weak human interaction, or artificial few-shot data using Large Language Models. </p> <p><br></p> <p>Our insight is that various tasks such as perspectives, stances, sentiments toward entities, etc. are interdependent when characterizing online media messages. As a result, we proposed approaches that jointly model various interdependent problems such as perspectives, stances, sentiments toward entities, etc., and perform structured prediction to solve them jointly. Our research findings showed that the messaging choices and perspectives on online media in response to various real-life events and their prominence and contrast in different ideological camps can be efficiently captured using our developed methods.</p>

Indiana University-Purdue University Indianapolis (IUPUI) / Graph Neural Networks (GNNs) have become excessively popular and prominent deep learning techniques to analyze structural graph data for their ability to solve complex real-world problems. Because graphs provide an efficient approach to contriving abstract hypothetical concepts, modern research overcomes the limitations of classical graph theory, requiring prior knowledge of the graph structure before employing traditional algorithms. GNNs, an impressive framework for representation learning of graphs, have already produced many state-of-the-art techniques to solve node classification, link prediction, and graph classification tasks. GNNs can learn meaningful representations of graphs incorporating topological structure, node attributes, and neighborhood aggregation to solve supervised, semi-supervised, and unsupervised graph-based problems. In this study, the usefulness of GNNs has been analyzed primarily from two aspects - clustering and classification. We focus on these two techniques, as they are the most popular strategies in data mining to discern collected data and employ predictive analysis.

Starting in 2027, the high-luminosity Large Hadron Collider (HL-LHC) will begin operation and allow higher-precision measurements and searches for new physics processes between elementary particles. One central problem that arises in the ATLAS detector when reconstructing event information is to separate the rare and interesting hard scatter (HS) interactions from uninteresting pileup (PU) interactions in a spatially compact environment. This problem becomes even harder to solve at higher luminosities. This project relies on leveraging the time dimension and determining a time of the HS interactions to separate them from PU interactions by using information measured by the upcoming High-Granularity Timing Detector (HGTD). The current method relies on using a boosted decision tree (BDT) together with the timing information from the HGTD to determine a time. We suggest a novel approach of utilizing a graph attentional network (GAT) where each bunch-crossing is represented as a graph of tracks and the properties of the GAT are applied on a track level to inspect if such a model can outperform the current BDT. Our results show that we are able to replicate the results of the BDT and even improve some metrics at the expense of increasing the uncertainty of the time determination. We conclude that although there is potential for GATs to outperform the BDT, a more complex model should be applied. Finally, we provide some suggestions for improvement and hope to inspire further study and advancements in this direction which shows promising potential. / Från och med 2027 kommer \textit{high-luminosity Large Hadron Collider} (HL-LHC) att tas i drift och möjliggöra mätningar med högre precision och utforskningar av nya fysikprocesser mellan elementarpartiklar. Ett centralt problem som uppstår i ATLAS-detektorn vid rekonstruktionen av partikelkollisioner är att separera sällsynta och intressanta interaktioner, så kallade \textit{hard-scatters} (HS) från ointressanta \textit{pileup}-interaktioner (PU) i den kompakta rumsliga dimensionen. Svårighetsgraden för detta problem ökar vid högre luminositeter. Med hjälp av den kommande \textit{High-Granularity Timing-detektorns} (HGTD) mätningar kommer även tidsinformation relaterat till interaktionerna att erhållas. I detta projekt används denna information för att beräkna tiden för enskillda interaktioner vilket därmed kan användas för att separera HS-interaktioner från PU-interaktioner. Den nuvarande metoden använder en trädregressionsmetod, s.k. boosted decision tree (BDT) tillsammans med tidsinformationen från HGTD för att bestämma en tid. Vi föreslår ett nytt tillvägagångssätt baserat på ett s.k. uppvaktande grafnätverk (GAT), där varje protonkollision representeras som en graf över partikelspåren och där GAT-egenskaperna tillämpas på spårnivå. Våra resultat visar att vi kan replikera de BDT-baserade resultaten och till och med förbättra resultaten på bekostnad av att öka osäkerheten i tidsbestämningarna. Vi drar slutsatsen att även om det finns potential för GAT-modeller att överträffa BDT-modeller, bör mer komplexa versioner av de förra tillämpas. Vi ger slutligen några förbättringsförslag som vi hoppas ska kunna inspirera till ytterligare studier och framsteg inom detta område, vilket visar lovande potential.

Graphs are often considered an excellent way of modeling complex real-world problems since they allow to capture relationships between items. Because of their ubiquity, graph embedding techniques have occupied research groups, seeking how vertices can be encoded into a low-dimensional latent space, useful to then perform machine learning. Recently Graph Neural Networks (GNN) have dominated the space of embeddings generation due to their inherent ability to encode latent node dependencies. Moreover, the newly introduced Inductive Graph Neural Networks gained much popularity for inductively learning and representing node embeddings through neighborhood aggregate measures. Even when an entirely new node, unseen during training, appears in the graph, it can still be properly represented by its neighboring nodes. Although this approach appears suitable for dynamic graphs, available systems and training methodologies are agnostic of dynamicity and solely rely on re-processing full graph snapshots in batches, an approach that has been criticized for its high computational costs. This work provides a thorough solution to this particular problem via an efficient prioritybased method for selecting rehearsed samples that guarantees low complexity and high accuracy. Finally, a data-parallel inference method has been evaluated at scale using Apache Flink, a data stream processor for real-time predictions on high volume graph data streams. / Molti problemi nel mondo reale possono essere rappresentati come grafi poichè queste strutture dati consentono di modellare relazioni tra elementi. A causa del loro vasto uso, molti gruppi di ricerca hanno tentato di rappresentare i vertici in uno spazio a bassa dimensione, utile per poi poter utilizzare tecniche di apprendimento automatico. Le reti neurali per grafi sono state ampiamente utilizzate per via della loro capacità di codificare dipendenze tra vertici. Le reti neurali induttive recentemente introdotte, inoltre, hanno guadagnato popolarità poichè consentono di generare rappresentazioni di vertici aggregando altri vertici. In questo modo anche un nodo completamente nuovo può comunque essere rappresentato utilizzando i suoi nodi vicini. Sebbene questo approccio sia adatto per grafici dinamici, i sistemi ad oggi disponibili e gli algoritmi di addestramento si basano esclusivamente sulla continua elaborazione di grafi statici, un approccio che è stato criticato per i suoi elevati costi di calcolo. Questa tesi fornisce una soluzione a questo problema tramite un metodo efficiente per l’allenamento di reti neurali induttive basato su un’euristica per la selezione dei vertici. Viene inoltre descritto un metodo per eseguire predizioni in modo scalabile in tempo reale utilizzando Apache Flink, un sistema per l’elaborazione di grandi quantità di flussi di dati in tempo reale. / Grafer anses ofta vara ett utmärkt sätt att modellera komplexa problem i verkligheten eftersom de gör det möjligt att fånga relationer mellan objekt. På grund av deras allestädes närhet har grafinbäddningstekniker sysselsatt forskningsgrupper som undersöker hur hörn kan kodas in i ett lågdimensionellt latent utrymme, vilket är användbart för att sedan utföra maskininlärning. Nyligen har Graph Neural Networks (GNN) dominerat utrymmet för inbäddningsproduktion tack vare deras inneboende förmåga att koda latenta nodberoenden. Dessutom fick de nyinförda induktiva grafiska nervnäten stor popularitet för induktivt lärande och representerande nodbäddningar genom sammanlagda åtgärder i grannskapet. Även när en helt ny nod, osynlig under träning, visas i diagrammet, kan den fortfarande representeras ordentligt av dess angränsande noder. Även om detta tillvägagångssätt tycks vara lämpligt för dynamiska grafer, är tillgängliga system och träningsmetodologier agnostiska för dynamik och förlitar sig bara på att behandla fullständiga ögonblicksbilder i partier, en metod som har kritiserats för dess höga beräkningskostnader. Detta arbete ger en grundlig lösning på detta specifika problem via en effektiv prioriteringsbaserad metod för att välja repeterade prover som garanterar låg komplexitet och hög noggrannhet. Slutligen har en dataparallell inferensmetod utvärderats i skala med Apache Flink, en dataströmprocessor för realtidsprognoser för grafiska dataströmmar med hög volym.

Time synchronization is a process of ensuring all the time difference between the clocks of network components(like base stations, boundary clocks, grandmasters, etc.) in the mobile network is zero or negligible. It is one of the important factors responsible for ensuring effective communication between two user-equipments in a mobile network. Nevertheless, the presence of asymmetries can lead to faults, making the detection of these errors indispensable, especially in technologies demanding ultra-low latency, such as 5G technology. Developing methods to ensure time-synchronized mobile networks, would not only improve the network performance, and contribute towards cost-effective telecommunication infrastructure. A rulebased simulator to simulate the mobile network was built, using the rules provided by the domain experts, in order to generate more data for further studies. The possibility of using Reinforcement Learning to perform fault detection in the mobile network was explored. In addition to the simulator dataset, an unlabelled customer dataset, which consists of time error differences between the base stations, and additional features for each of its network components was provided. Classification algorithms to label the customer dataset were designed, and a comparative analysis of each of them has been presented. Mathematical algorithm and Graph Neural Network models were built to detect error, for both the simulator and customer dataset, for the faulty node detection task. The approach of using a Mathematical algorithm and Graph Neural Network architectures provided an accuracy of 95% for potential fault node detection. The feature importance of the additional features of the network components was analyzed using the best Graph Neural Network model which was used to train for the node classification task (to classify the base stations as faulty and non-faulty). Additionally, an attempt was made to predict the individual time error value for each of the links using Graph Neural Network, however, it failed potentially due to the presence of fewer features to train from. / Tidssynkronisering är en process för att säkerställa att all tidsskillnad mellan klockorna för nätverkskomponenter (som basstationer, gränsklockor, stormästare, etc.) i mobilnätet är noll eller försumbar. Det är en av de viktiga faktorerna som är ansvariga för att säkerställa effektiv kommunikation mellan två användarutrustningar i ett mobilnät. Icke desto mindre kan närvaron av asymmetrier leda till fel, vilket gör upptäckten av dessa fel oumbärlig, särskilt i tekniker som kräver ultralåg latens, som 5G-teknik. En regelbaserad simulator för att simulera mobilnätet byggdes, med hjälp av reglerna från domänexperterna, för att generera mer data för vidare studier. Möjligheten att använda RL för att utföra feldetektering i mobilnätet undersöktes. Utöver simulatordataset tillhandahölls en omärkt kunddatauppsättning, som består av tidsfelsskillnader mellan basstationerna och ytterligare funktioner för var och en av dess nätverkskomponenter. Klassificeringsalgoritmer för att märka kunddataset utformades, och en jämförande analys av var och en av dem har presenterats. Matematisk algoritm och GNN-modeller byggdes för att upptäcka fel, för både simulatorn och kunddatauppsättningen, för uppgiften att detektera felaktig nod. Metoden att använda en matematisk algoritm och GNN-arkitekturer gav en noggrannhet på 95% för potentiell felnoddetektering. Funktionens betydelse för de ytterligare funktionerna hos nätverkskomponenterna analyserades med den bästa GNN-modellen som användes för att träna för nodklassificeringsuppgiften (för att klassificera basstationerna som felaktiga och icke-felaktiga). Dessutom gjordes ett försök att förutsäga det individuella tidsfelsvärdet för var och en av länkarna med GNN, men det misslyckades potentiellt på grund av närvaron av färre funktioner att träna från.

[pt] Esta dissertação introduz um simulador híbrido inovador que combina um resolvedor de Equações Diferenciais Parciais (EDP) numérico de Elementos Finitos (FE) com uma Rede Neural de Passagem de Mensagens (MPNN) para realizar simulações de dinâmicas de sólidos deformáveis em malhas pouco refinadas. Nosso trabalho visa fornecer simulações precisas com um erro comparável ao obtido com malhas mais refinadas em discretizações FE,mantendo a eficiência computacional ao usar um componente MPNN que corrige os erros numéricos associados ao uso de uma malha menos refinada. Avaliamos nosso modelo focando na precisão, capacidade de generalização e velocidade computacional em comparação com um solucionador numérico de referência que usa malhas 64 vezes mais refinadas. Introduzimos um novo conjunto de dados para essa comparação, abrangendo três casos de referência numéricos: (i) deformação livre após um impulso inicial, (ii) alongamento e (iii)torção de sólidos deformáveis. Baseado nos resultados de simulação, o estudo discute as forças e fraquezas do nosso método. O estudo mostra que nosso método corrige em média 95,4 por cento do erro numérico associado à discretização, sendo até 88 vezes mais rápido que o solucionador de referência. Além disso, nosso modelo é totalmente diferenciável em relaçao a funções de custo e pode ser incorporado em uma camada de rede neural, permitindo que seja facilmente estendido por trabalhos futuros. Dados e código estão disponíveis em https://github.com/Kerber31/fast_coarse_FEM para investigações futuras. / [en] This thesis introduces a novel hybrid simulator that combines a numerical Finite Element (FE) Partial Differential Equation solver with a Message Passing Neural Network (MPNN) to perform simulations of deformable solid dynamics on coarse meshes. Our work aims to provide accurate simulations with an error comparable to that obtained with more refined meshes in FE discretizations while maintaining computational efficiency by using an MPNN component that corrects the numerical errors associated with using a coarse mesh. We evaluate our model focusing on accuracy, generalization capacity, and computational speed compared to a reference numerical solver that uses 64 times more refined meshes. We introduce a new dataset for this comparison, encompassing three numerical benchmark cases: (i) free deformation after an initial impulse, (ii) stretching, and (iii) torsion of deformable solids. Based on simulation results, the study thoroughly discusses our method s strengths and weaknesses. The study shows that our method corrects an average of 95.4 percent of the numerical error associated with discretization while being up to 88 times faster than the reference solver. On top of that, our model is fully differentiable in relation to loss functions and can be embedded into a neural network layer, allowing it to be easily extended by future work. Data and code are made available on https://github.com/Kerber31/fast_coarse_FEM for further investigations.

Za posledné roky je zaznamenaný nárast prác zahrňujúcich komplexnú detekciu malvéru. Pre potreby zachytenia správania je často vhodné pouziť formát grafov. To je prípad antivírusového programu Avast, ktorého behaviorálny štít deteguje škodlivé správanie a ukladá ich vo forme grafov. Keďže sa jedná o proprietárne riešenie a Avast antivirus pracuje s vlastnou sadou charakterizovaného správania bolo nutné navrhnúť vlastnú metódu detekcie, ktorá bude postavená nad týmito grafmi správania. Táto práca analyzuje grafy správania škodlivého softvéru zachytené behavioralnym štítom antivírusového programu Avast pre proces hlbšej detekcie škodlivého softvéru. Detekcia škodlivého správania sa začína analýzou a abstrakciou vzorcov z grafu správania. Izolované vzory môžu efektívnejšie identifikovať dynamicky sa meniaci malware. Grafy správania sú uložené v databáze grafov Neo4j a každý deň sú zachytené tisíce z nich. Cieľom tejto práce bolo navrhnúť algoritmus na identifikáciu správania škodlivého softvéru s dôrazom na rýchlosť skenovania a jasnosť identifikovaných vzorcov správania. Identifikácia škodlivého správania spočíva v nájdení najdôležitejších vlastností natrénovaných klasifikátorov a následnej extrakcie podgrafu pozostávajúceho iba z týchto dôležitých vlastností uzlov a vzťahov medzi nimi. Následne je navrhnuté pravidlo pre hodnotenie extrahovaného podgrafu. Diplomová práca prebehla v spolupráci so spoločnosťou Avast Software s.r.o.

<p><strong>Graph Neural Networks</strong> (GNNs) have become excessively popular and prominent deep learning techniques to analyze structural graph data for their ability to solve complex real-world problems. Because graphs provide an efficient approach to contriving abstract hypothetical concepts, modern research overcomes the limitations of classical graph theory, requiring prior knowledge of the graph structure before employing traditional algorithms. GNNs, an impressive framework for representation learning of graphs, have already produced many state-of-the-art techniques to solve node classification, link prediction, and graph classification tasks. GNNs can learn meaningful representations of graphs incorporating topological structure, node attributes, and neighborhood aggregation to solve supervised, semi-supervised, and unsupervised graph-based problems. In this study, the usefulness of GNNs has been analyzed primarily from two aspects - <strong>clustering and classification</strong>. We focus on these two techniques, as they are the most popular strategies in data mining to discern collected data and employ predictive analysis.</p>