Search

In recent years, there has been a growing interest in using machine learning (ML) in query optimization to select more efficient plans. Existing learning-based query optimizers use certain model architectures to convert tree-structured query plans into representations suitable for downstream ML tasks. As the design of these architectures significantly impacts cost estimation, we propose a tree model architecture based on Bidirectional Graph Neural Networks (Bi-GNN) aggregated by Gated Recurrent Units (GRUs) to achieve more accurate cost estimates. The inherent uncertainty of data and model parameters also leads to inaccurate cost estimates, resulting in suboptimal plans and less robust query performance. To address this, we implement a novel learning-to-rank cost model that effectively quantifies the uncertainty in cost estimates using approximate probabilistic ML. This model adaptively integrates quantified uncertainty with estimated costs and learns from comparing pairwise plans, achieving more robust performance. In addition, we propose the first explainability technique specifically designed for learning-based cost models. This technique explains the contribution of any subgraphs in the query plan to the final predicted cost, which can be integrated and trained with any learning-based cost model to significantly boost the model's explainability. By incorporating these innovations, we propose a cost model for a Robust and Explainable Query Optimizer, Reqo, that improves the accuracy, robustness, and explainability of cost estimation, outperforming state-of-the-art approaches in all three dimensions.

In the Telephone Broadcasting problem, the goal is to disseminate a message from a given source vertex of an input graph to all other vertices in a minimum number of rounds, where at each round, an informed vertex can inform at most one of its uniformed neighbours. For general graphs of $n$ vertices, the problem is NP-hard, and the best existing algorithm has an approximation factor of $O(\log n/ \log \log n)$. The existence of a constant factor approximation for the general graphs is still unknown. The problem can be solved in polynomial time for trees. In this paper, we study the problem in two simple families of sparse graphs, namely, cacti and graphs of bounded path width. There have been several efforts to understand the complexity of the problem in cactus graphs, mostly establishing the presence of polynomial-time solutions for restricted families of cactus graphs. Despite these efforts, the complexity of the problem in arbitrary cactus graphs remained open. In this paper, we settle this question by establishing the NP-hardness of telephone broadcasting in cactus graphs. For that, we show the problem is NP-hard in a simple subfamily of cactus graphs, which we call snowflake graphs. These graphs not only are cacti but also have pathwidth $2$. These results establish that, although the problem is polynomial-time solvable in trees, it becomes NP-hard in simple extension of trees. On the positive side, we present constant-factor approximation algorithms for the studied families of graphs, namely, an algorithm with an approximation factor of $2$ for cactus graphs and an approximation factor of $O(1)$ for graphs of bounded pathwidth., Comment: 32 pages, 15 figures, 19 references

Social annotation platforms enable student engagement by integrating discussions directly into course materials. However, in large online courses, the sheer volume of comments can overwhelm students and impede learning. This paper investigates community-based design interventions on a social annotation platform (NB) to address this challenge and foster more meaningful online educational discussions. By examining student preferences and reactions to different curation strategies, this research aims to optimize the utility of social annotations in educational contexts. A key emphasis is placed on how the visibility of comments shapes group interactions, guides conversational flows, and enriches learning experiences. The study combined iterative design and development with two large-scale experiments to create and refine comment curation strategies, involving thousands of students. The study introduced specific features of the platform, such as targeted comment visibility controls, which demonstrably improved peer interactions and reduced discussion overload. These findings inform the design of next-generation social annotation systems and highlight opportunities to integrate Large Language Models (LLMs) for key activities like summarizing annotations, improving clarity in student writing, and assisting instructors with efficient comment curation.

In this paper, we detail recent and current work that is being carried out to fabricate and advance novel SiC UV instrumentation that is aimed at enabling more sensitive measurements across numerous disciplines, with a short discussion of the promise such detectors may hold for the Habitable Worlds Observatory. We discuss SiC instrument development progress that is being carried out under multiple NASA grants, including several PICASSO and SBIR grants, as well as an ECI grant. Testing of pixel design, properties and layout as well as maturation of the integration scheme developed through these efforts provide key technology and engineering advancement for potential HWO detectors. Achieving desired noise characteristics, responsivity, and validating operation of SiC detectors using standard read out techniques offers a compelling platform for operation of denser and higher dimensionality SiC photodiode arrays of interest for use in potential HWO Coronagraph, Spectrograph, and High Resolution Imaging Instruments. We incorporate these SiC detector properties into a simulation of potential NUV exoplanet observations by HWO using SiC detectors and also discuss potential application to HWO., Comment: 8 figures, Submitted to JATIS

Compositional generalization is crucial for artificial intelligence agents to solve complex vision-language reasoning tasks. Neuro-symbolic approaches have demonstrated promise in capturing compositional structures, but they face critical challenges: (a) reliance on predefined predicates for symbolic representations that limit adaptability, (b) difficulty in extracting predicates from raw data, and (c) using non-differentiable operations for combining primitive concepts. To address these issues, we propose NeSyCoCo, a neuro-symbolic framework that leverages large language models (LLMs) to generate symbolic representations and map them to differentiable neural computations. NeSyCoCo introduces three innovations: (a) augmenting natural language inputs with dependency structures to enhance the alignment with symbolic representations, (b) employing distributed word representations to link diverse, linguistically motivated logical predicates to neural modules, and (c) using the soft composition of normalized predicate scores to align symbolic and differentiable reasoning. Our framework achieves state-of-the-art results on the ReaSCAN and CLEVR-CoGenT compositional generalization benchmarks and demonstrates robust performance with novel concepts in the CLEVR-SYN benchmark., Comment: AAAI 2025 Project Page: https://iamdanialkamali.github.io/publication/neuro-symbolic-concept-composer

Join order selection is a sub-field of query optimization that aims to find the optimal join order for an SQL query with the minimum cost. The challenge lies in the exponentially growing search space as the number of tables increases, making exhaustive enumeration impractical. Traditional optimizers use static heuristics to prune the search space, but they often fail to adapt to changes or improve based on feedback from the DBMS. Recent research addresses these limitations with Deep Reinforcement Learning (DRL), allowing models to use feedback to dynamically search for better join orders and enhance performance over time. Existing research primarily focuses on capturing join order sequences and their representations at various levels, with limited comparative analysis of reinforcement learning methods. In this paper, we propose GTDD, a novel framework that integrates Graph Neural Networks (GNN), Treestructured Long Short-Term Memory (Tree LSTM), and DuelingDQN. We conduct a series of experiments that demonstrate a clear advantage of GTDD over state-of the-art techniques.

We explore a model of a pseudo-Nambu-Goldstone boson inflaton field coupled to a non-Abelian $SU(2)$ gauge field. This model naturally leads to a warm inflation scenario, where the inflationary dynamics is dominated by thermal dissipation. In this work, we consider a scenario where the inflaton, an axion-like field, is coupled to the $SU(2)$ gauge field, similar to chromoinflation models. Both the inflaton and the gauge field with a non-vanishing vacuum expectation value are coupled to a thermal radiation bath. We demonstrate that the presence of the thermal bath during warm chromoinflation induces a thermal plasma mass for the background gauge field. This thermal mass can significantly disrupt the dynamics of the background gauge field, thereby driving it to its trivial null solution., Comment: 17 pages, 5 figures. Replaced with the version matching the one published in the JCAP

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

The main goal of this paper is to introduce a new fractional anisotropic Sobolev space with variable exponent where the basic qualitative properties (completeness, separability, reflexivity, ...) are established, including the continuous and compact embedding results. Moreover, some functional proprieties of anisotropic fractional $\vec{p}(.,.)$-Laplacian operator are proved. As an application, we use the mountain pass theorem and Ekeland's variational principle to ensure the existence of a weak solution for a nonlocal anisotropic problem with variable exponent.

Industrial Internet of Things (IIoT) is highly sensitive to data privacy and cybersecurity threats. Federated Learning (FL) has emerged as a solution for preserving privacy, enabling private data to remain on local IIoT clients while cooperatively training models to detect network anomalies. However, both synchronous and asynchronous FL architectures exhibit limitations, particularly when dealing with clients with varying speeds due to data heterogeneity and resource constraints. Synchronous architecture suffers from straggler effects, while asynchronous methods encounter communication bottlenecks. Additionally, FL models are prone to adversarial inference attacks aimed at disclosing private training data. To address these challenges, we propose a Buffered FL (BFL) framework empowered by homomorphic encryption for anomaly detection in heterogeneous IIoT environments. BFL utilizes a novel weighted average time approach to mitigate both straggler effects and communication bottlenecks, ensuring fairness between clients with varying processing speeds through collaboration with a buffer-based server. The performance results, derived from two datasets, show the superiority of BFL compared to state-of-the-art FL methods, demonstrating improved accuracy and convergence speed while enhancing privacy preservation.

The high level of photorealism in state-of-the-art diffusion models like Midjourney, Stable Diffusion, and Firefly makes it difficult for untrained humans to distinguish between real photographs and AI-generated images. To address this problem, we designed a guide to help readers develop a more critical eye toward identifying artifacts, inconsistencies, and implausibilities that often appear in AI-generated images. The guide is organized into five categories of artifacts and implausibilities: anatomical, stylistic, functional, violations of physics, and sociocultural. For this guide, we generated 138 images with diffusion models, curated 9 images from social media, and curated 42 real photographs. These images showcase the kinds of cues that prompt suspicion towards the possibility an image is AI-generated and why it is often difficult to draw conclusions about an image's provenance without any context beyond the pixels in an image. Human-perceptible artifacts are not always present in AI-generated images, but this guide reveals artifacts and implausibilities that often emerge. By drawing attention to these kinds of artifacts and implausibilities, we aim to better equip people to distinguish AI-generated images from real photographs in the future., Comment: 54 pages, 189 Figures

The rise of instruction-tuned Large Language Models (LLMs) marks a significant advancement in artificial intelligence (AI) (tailored to respond to specific prompts). Despite their popularity, applying such models to debug security vulnerabilities in hardware designs, i.e., register transfer language (RTL) modules, particularly at system-on-chip (SoC) level, presents considerable challenges. One of the main issues lies in the need for precisely designed instructions for pinpointing and mitigating the vulnerabilities, which requires substantial time and expertise from human experts. In response to this challenge, this paper proposes Self-HWDebug, an innovative framework that leverages LLMs to automatically create required debugging instructions. In Self-HWDebug, a set of already identified bugs from the most critical hardware common weakness enumeration (CWE) listings, along with mitigation resolutions, is provided to the framework, followed by prompting the LLMs to generate targeted instructions for such mitigation. The LLM-generated instructions are subsequently used as references to address vulnerabilities within the same CWE category but in totally different designs, effectively demonstrating the framework's ability to extend solutions across related security issues. Self-HWDebug significantly reduces human intervention by using the model's own output to guide debugging. Through comprehensive testing, Self-HWDebug proves not only to reduce experts' effort/time but also to even improve the quality of the debugging process.

Studies conducted on financial market prediction lack a comprehensive feature set that can carry a broad range of contributing factors; therefore, leading to imprecise results. Furthermore, while cooperating with the most recent innovations in explainable AI, studies have not provided an illustrative summary of market-driving factors using this powerful tool. Therefore, in this study, we propose a novel feature matrix that holds a broad range of features including Twitter content and market historical data to perform a binary classification task of one step ahead prediction. The utilization of our proposed feature matrix not only leads to improved prediction accuracy when compared to existing feature representations, but also its combination with explainable AI allows us to introduce a fresh analysis approach regarding the importance of the market-driving factors included. Thanks to the Lime interpretation technique, our interpretation study shows that the volume of tweets is the most important factor included in our feature matrix that drives the market's movements.

We use the reconfiguration framework to analyze problems that involve the rearrangement of items among groups. In various applications, a group of items could correspond to the files or jobs assigned to a particular machine, and the goal of rearrangement could be improving efficiency or increasing locality. To cover problems arising in a wide range of application areas, we define the general Repacking problem as the rearrangement of multisets of multisets. We present hardness results for the general case and algorithms for various classes of instances that arise in real-life scenarios. By limiting the total size of items in each multiset, our results can be viewed as an offline approach to Bin Packing, in which each bin is represented as a multiset. In addition to providing the first results on reconfiguration of multisets, our contributions open up several research avenues: the interplay between reconfiguration and online algorithms and parallel algorithms; the use of the tools of linear programming in reconfiguration; and, in the longer term, a focus on extra resources in reconfiguration., Comment: A preliminary version of this paper appeared in the proceedings of the 18th International Conference and Workshops on Algorithms and Computation (WALCOM 2024)

Learning representations for query plans play a pivotal role in machine learning-based query optimizers of database management systems. To this end, particular model architectures are proposed in the literature to transform the tree-structured query plans into representations with formats learnable by downstream machine learning models. However, existing research rarely compares and analyzes the query plan representation capabilities of these tree models and their direct impact on the performance of the overall optimizer. To address this problem, we perform a comparative study to explore the effect of using different state-of-the-art tree models on the optimizer's cost estimation and plan selection performance in relatively complex workloads. Additionally, we explore the possibility of using graph neural networks (GNNs) in the query plan representation task. We propose a novel tree model BiGG employing Bidirectional GNN aggregated by Gated recurrent units (GRUs) and demonstrate experimentally that BiGG provides significant improvements to cost estimation tasks and relatively excellent plan selection performance compared to the state-of-the-art tree models.

Automating hardware (HW) security vulnerability detection and mitigation during the design phase is imperative for two reasons: (i) It must be before chip fabrication, as post-fabrication fixes can be costly or even impractical; (ii) The size and complexity of modern HW raise concerns about unknown vulnerabilities compromising CIA triad. While Large Language Models (LLMs) can revolutionize both HW design and testing processes, within the semiconductor context, LLMs can be harnessed to automatically rectify security-relevant vulnerabilities inherent in HW designs. This study explores the seeds of LLM integration in register transfer level (RTL) designs, focusing on their capacity for autonomously resolving security-related vulnerabilities. The analysis involves comparing methodologies, assessing scalability, interpretability, and identifying future research directions. Potential areas for exploration include developing specialized LLM architectures for HW security tasks and enhancing model performance with domain-specific knowledge, leading to reliable automated security measurement and risk mitigation associated with HW vulnerabilities.

We present the first learning-augmented data structure for implementing dictionaries with optimal consistency and robustness. Our data structure, named RobustSL, is a skip list augmented by predictions of access frequencies of elements in a data sequence. With proper predictions, RobustSL has optimal consistency (achieves static optimality). At the same time, it maintains a logarithmic running time for each operation, ensuring optimal robustness, even if predictions are generated adversarially. Therefore, RobustSL has all the advantages of the recent learning-augmented data structures of Lin, Luo, and Woodruff (ICML 2022) and Cao et al. (arXiv 2023), while providing robustness guarantees that are absent in the previous work. Numerical experiments show that RobustSL outperforms alternative data structures using both synthetic and real datasets., Comment: 11 pages plus 4 pages appendix

Malaria is the leading cause of death globally, especially in sub-Saharan African countries claiming over 400,000 deaths globally each year, underscoring the critical need for continued efforts to combat this preventable and treatable disease. The objective of this study is to provide statistical guidance on the optimal preventive and control measures against malaria. Data have been collected from reliable sources, such as World Health Organization, UNICEF, Our World in Data, and STATcompiler. Data were categorized according to the factors and sub-factors related to deaths caused by malaria. These factors and sub-factors were determined based on root cause analysis and data sources. Using JMP 16 Pro software, both linear and multiple linear regression were conducted to analyze the data. The analyses aimed to establish a linear relationship between the dependent variable (malaria deaths in the overall population) and independent variables, such as life expectancy, malaria prevalence in children, net usage, indoor residual spraying usage, literate population, and population with inadequate sanitation in each selected sample country. The statistical analysis revealed that using insecticide treated nets (ITNs) by children and individuals significantly decreased the death count, as 1,000 individuals sleeping under ITNs could reduce the death count by eight. Based on the statistical analysis, this study suggests more rigorous research on the usage of ITNs.

Query optimizers in relational database management systems (RDBMSs) search for execution plans expected to be optimal for a given queries. They use parameter estimates, often inaccurate, and make assumptions that may not hold in practice. Consequently, they may select execution plans that are suboptimal at runtime, when these estimates and assumptions are not valid, which may result in poor query performance. Therefore, query optimizers do not sufficiently support robust query optimization. Recent years have seen a surge of interest in using machine learning (ML) to improve efficiency of data systems and reduce their maintenance overheads, with promising results obtained in the area of query optimization in particular. In this paper, inspired by these advancements, and based on several years of experience of IBM Db2 in this journey, we propose Robust Optimization of Queries, (Roq), a holistic framework that enables robust query optimization based on a risk-aware learning approach. Roq includes a novel formalization of the notion of robustness in the context of query optimization and a principled approach for its quantification and measurement based on approximate probabilistic ML. It also includes novel strategies and algorithms for query plan evaluation and selection. Roq also includes a novel learned cost model that is designed to predict query execution cost and the associated risks and performs query optimization accordingly. We demonstrate experimentally that Roq provides significant improvements to robust query optimization compared to the state-of-the-art., Comment: 13 pages, 9 figures, submitted to SIGMOD 2024