Search

Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility to adjust model behavior based on varying resource budgets, existing methods are frequently limited by hardware inefficiencies or performance degradation. In this paper, we introduce Balcony, a simple yet highly effective framework for depth-based dynamic inference. By freezing the pretrained LLM and inserting additional transformer layers at selected exit points, Balcony maintains the full model's performance while enabling real-time adaptation to different computational budgets. These additional layers are trained using a straightforward self-distillation loss, aligning the sub-model outputs with those of the full model. This approach requires significantly fewer training tokens and tunable parameters, drastically reducing computational costs compared to prior methods. When applied to the LLaMA3-8B model, using only 0.2% of the original pretraining data, Balcony achieves minimal performance degradation while enabling significant speedups. Remarkably, we show that Balcony outperforms state-of-the-art methods such as Flextron and Layerskip as well as other leading compression techniques on multiple models and at various scales, across a variety of benchmarks.

Given the complexity of multi-tenant cloud environments and the need for real-time threat mitigation, Security Operations Centers (SOCs) must integrate AI-driven adaptive defenses against Advanced Persistent Threats (APTs). However, SOC analysts struggle with countering adaptive adversarial tactics, necessitating intelligent decision-support frameworks. To enhance human-AI collaboration in SOCs, we propose a Cognitive Hierarchy Theory-driven Deep Q-Network (CHT-DQN) framework that models SOC analysts' decision-making against AI-driven APT bots. The SOC analyst (defender) operates at cognitive level-1, anticipating attacker strategies, while the APT bot (attacker) follows a level-0 exploitative policy. By incorporating CHT into DQN, our framework enhances SOC defense strategies via Attack Graph (AG)-based reinforcement learning. Simulation experiments across varying AG complexities show that CHT-DQN achieves higher data protection and lower action discrepancies compared to standard DQN. A theoretical lower bound analysis further validates its superior Q-value performance. A human-in-the-loop (HITL) evaluation on Amazon Mechanical Turk (MTurk) reveals that SOC analysts using CHT-DQN-driven transition probabilities align better with adaptive attackers, improving data protection. Additionally, human decision patterns exhibit risk aversion after failure and risk-seeking behavior after success, aligning with Prospect Theory. These findings underscore the potential of integrating cognitive modeling into deep reinforcement learning to enhance SOC operations and develop real-time adaptive cloud security mechanisms.

Machine Learning (ML) techniques have been successfully applied to design various learned database index structures for both the one- and multi-dimensional spaces. Particularly, a class of traditional multi-dimensional indexes has been augmented with ML models to design ML-enhanced variants of their traditional counterparts. This paper focuses on the R-tree multi-dimensional index structure as it is widely used for indexing multi-dimensional data. The R-tree has been augmented with machine learning models to enhance the R-tree performance. The AI+R-tree is an ML-enhanced R-tree index structure that augments a traditional disk-based R-tree with an ML model to enhance the R-tree's query processing performance, mainly, to avoid navigating the overlapping branches of the R-tree that do not yield query results, e.g., in the presence of high-overlap among the rectangles of the R-tree nodes. We investigate the empirical tradeoffs in processing dynamic query workloads and in supporting updates over the AI+R-tree. Particularly, we investigate the impact of the choice of ML models over the AI+R-tree query processing performance. Moreover, we present a case study of designing a custom loss function for a neural network model tailored to the query processing requirements of the AI+R-tree. Furthermore, we present the design tradeoffs for adopting various strategies for supporting dynamic inserts, updates, and deletes with the vision of realizing a mutable AI+R-tree. Experiments on real datasets demonstrate that the AI+R-tree can enhance the query processing performance of a traditional R-tree for high-overlap range queries by up to 5.4X while achieving up to 99% average query recall., Comment: arXiv admin note: text overlap with arXiv:2207.00550

We show that equalization-enhanced phase noise manifests as a time-varying, frequency-dependent phase error, which can be modeled and reversed by a time-varying all-pass finite impulse response filter., Comment: Accepted at 50th Optical Fiber Communication Conference (OFC), San Fransisco, CA, USA, Mar. 2025

Summary Osteoporosis is a skeletal disorder, characterized by a decrease in bone strength and puts the individual at risk for fracture. On the other hand, rheumatoid arthritis is a systemic disease of unknown etiology that causes inflammation of the joints of the organs. Purpose Due to the destructive effects of these diseases and its increasing prevalence and lack of appropriate medication for treatment, the present study aimed to evaluate the therapeutic effect of a new type of healthy and live food supplement on rheumatoid arthritis and induced osteoporosis in rats. Methods In this research, healthy and live food powder were synthesized by a new and green route. This organic biomaterial was named NBS. The NBS food supplement had various vitamins, macro and micro molecules, and ingredients. The new healthy and nutritious diet showed that the use of this supplement led to the return of the parameters to normal levels. Results The concentration of 12.5 mg/ kg showed the least therapeutic effect and 50 mg/ kg had the highest therapeutic effect for osteoporosis. The results of blood parameters involved in inflammation in both healthy and patient groups showed that the use of complete adjuvant induction causes joint inflammation. In the study of the interaction of the concentrations, it was observed that the concentration of 50 mg/ kg had the highest therapeutic effect against the disease in the studied mice. Conclusion The results showed that the new healthy and viable supplement restores the blood osteoporotic and rheumatoid factors of the mice to normal.

Instruction-based computer control agents (CCAs) execute complex action sequences on personal computers or mobile devices to fulfill tasks using the same graphical user interfaces as a human user would, provided instructions in natural language. This review offers a comprehensive overview of the emerging field of instruction-based computer control, examining available agents -- their taxonomy, development, and respective resources -- and emphasizing the shift from manually designed, specialized agents to leveraging foundation models such as large language models (LLMs) and vision-language models (VLMs). We formalize the problem and establish a taxonomy of the field to analyze agents from three perspectives: (a) the environment perspective, analyzing computer environments; (b) the interaction perspective, describing observations spaces (e.g., screenshots, HTML) and action spaces (e.g., mouse and keyboard actions, executable code); and (c) the agent perspective, focusing on the core principle of how an agent acts and learns to act. Our framework encompasses both specialized and foundation agents, facilitating their comparative analysis and revealing how prior solutions in specialized agents, such as an environment learning step, can guide the development of more capable foundation agents. Additionally, we review current CCA datasets and CCA evaluation methods and outline the challenges to deploying such agents in a productive setting. In total, we review and classify 86 CCAs and 33 related datasets. By highlighting trends, limitations, and future research directions, this work presents a comprehensive foundation to obtain a broad understanding of the field and push its future development.

The Adaptive Data Analysis (ADA) problem, where an analyst interacts with a dataset through statistical queries, is often studied under the assumption of adversarial analyst behavior. To decrease this gap, we propose a revised model of ADA that accounts for more constructive interactions between the analysts and the data, where the goal is to enhance inference accuracy. Specifically, we focus on distribution estimation as a central objective guiding analyst's queries. The problem is addressed within a non-parametric Bayesian framework, capturing the flexibility and dynamic evolution of analyst's beliefs. Our hierarchical approach leverages P\'olya trees (PTs) as priors over the distribution space, facilitating the adaptive selection of counting queries to efficiently reduce the estimation error without increasing the number of queries. Furthermore, with its interpretability and conjugacy, the proposed framework allows for intuitive conversion of subjective beliefs into objective priors and their effortless updates to posteriors. Using theoretical derivations, we formalize the PT-based solution as a computational algorithm. Simulations further demonstrate its effectiveness in distribution estimation tasks compared to the non-adaptive approach. By aligning with real-world applications, this structured ADA framework fosters opportunities for collaborative research in related areas, such as human-in-the-loop systems and cognitive studies of belief updating.

Regarding the concepts of urban management, digital transformation, and smart cities, various issues are presented. Currently, we like to attend to location allocation problems that can be a new part of digital transformation in urban management (such as locating and placing facilities, locating and arranging centers such as aid and rescue centers, or even postal hubs, telecommunications, electronic equipment, and data centers, and routing in transportation optimization). These issues, which are seemingly simple but in practice complex, are important in urban environments, and the issue of accurate location allocation based on existing criteria directly impacts cost management, profit, efficiency, and citizen satisfaction. In recent years, researchers have used or presented various models and methods for location allocation problems, some of which will be mentioned in this article. Given the nature of these problems, which are optimization problems, this article will also examine existing research from an optimization perspective in summary. Finally, a brief conclusion will be made of the existing methods and their weaknesses, and suggestions will be made for continuing the path and improving scientific and practical research in this field., Comment: 7 pages, Keywords: Digital Transformation - Smart City - GIS - Location Allocation - Urban Management - Optimization

We present a Graph Neural Network (GNN) that accurately simulates a multidisperse suspension of interacting spherical particles. Our machine learning framework is built upon the recent work of Sanchez-Gonzalez et al. ICML, PMLR, 119, 8459-8468 (2020) on graph network simulators, and efficiently learns the intricate dynamics of the interacting particles. Nodes and edges of the GNN correspond, respectively, to the particles with their individual properties/data (e.g., radius, position, velocity) and the pairwise interactions between the particles (e.g., electrostatics, hydrodynamics). A key contribution of our work is to account for the finite dimensions of the particles and their impact on the system dynamics. We test our GNN against a representative case study of a multidisperse mixture of two-dimensional spheres sedimenting under gravity in a liquid and interacting with each other by a Lennard-Jones potential. The present GNN framework offers a fast and accurate method for the theoretical study of complex physical systems such as field-induced behavior of colloidal suspensions and ionic liquids. Our implementation of the GNN is available on GitHub at github.com/rfjd/GNS-DispersedSystems.

Adaptive data analysis (ADA) involves a dynamic interaction between an analyst and a dataset owner, where the analyst submits queries sequentially, adapting them based on previous answers. This process can become adversarial, as the analyst may attempt to overfit by targeting non-generalizable patterns in the data. To counteract this, the dataset owner introduces randomization techniques, such as adding noise to the responses. This noise not only helps prevent overfitting, but also enhances data privacy. However, it must be carefully calibrated to ensure that the statistical reliability of the responses is not compromised. In this paper, we extend the ADA problem to the context of distributed datasets. Specifically, we consider a scenario where a potentially adversarial analyst interacts with multiple distributed responders through adaptive queries. We assume the responses are subject to noise, introduced by the channel connecting the responders and the analyst. We demonstrate how this noise can be opportunistically leveraged through a federated mechanism to enhance the generalizability of ADA, thereby increasing the number of query-response interactions between the analyst and the responders. We illustrate that the careful tuning of the transmission amplitude based on the theoretically achievable bounds can significantly impact the number of accurately answerable queries.

Graph Neural Networks (GNNs) have shown great promise in modeling relationships between nodes in a graph, but capturing higher-order relationships remains a challenge for large-scale networks. Previous studies have primarily attempted to utilize the information from higher-order neighbors in the graph, involving the incorporation of powers of the shift operator, such as the graph Laplacian or adjacency matrix. This approach comes with a trade-off in terms of increased computational and memory demands. Relying on graph spectral theory, we make a fundamental observation: the regular and the Hadamard power of the Laplacian matrix behave similarly in the spectrum. This observation has significant implications for capturing higher-order information in GNNs for various tasks such as node classification and semi-supervised learning. Consequently, we propose a novel graph convolutional operator based on the sparse Sobolev norm of graph signals. Our approach, known as Sparse Sobolev GNN (S2-GNN), employs Hadamard products between matrices to maintain the sparsity level in graph representations. S2-GNN utilizes a cascade of filters with increasing Hadamard powers to generate a diverse set of functions. We theoretically analyze the stability of S2-GNN to show the robustness of the model against possible graph perturbations. We also conduct a comprehensive evaluation of S2-GNN across various graph mining, semi-supervised node classification, and computer vision tasks. In particular use cases, our algorithm demonstrates competitive performance compared to state-of-the-art GNNs in terms of performance and running time.

The development of artificial intelligence has made significant contributions to the financial sector. One of the main interests of investors is price predictions. Technical and fundamental analyses, as well as econometric analyses, are conducted for price predictions; recently, the use of AI-based methods has become more prevalent. This study examines daily Dollar/TL exchange rates from January 1, 2020, to October 4, 2024. It has been observed that among artificial intelligence models, random forest, support vector machines, k-nearest neighbors, decision trees, and gradient boosting models were not suitable; however, multilayer perceptron and linear regression models showed appropriate suitability and despite the sharp increase in Dollar/TL rates in Turkey as of 2019, the suitability of valid models has been maintained.

Ever since the Dennard scaling broke down in the early 2000s and the frequency of the CPU stalled, vendors have started to increase the core count in each CPU chip at the expense of introducing heterogeneity, thus ushering the era of NUMA processors. Since then, the heterogeneity in the design space of hardware has only increased to the point that DBMS performance may vary significantly up to an order of magnitude in modern servers. An important factor that affects performance includes the location of the logical cores where the DBMS queries are scheduled, and the locations of the data that the queries access. This paper introduces P-MOSS, a learned spatial scheduling framework that schedules query execution to certain logical cores, and places data accordingly to certain integrated memory controllers (IMC), to integrate hardware consciousness into the system. In the spirit of hardware-software synergy, P-MOSS solely guides its scheduling decision based on low-level hardware statistics collected by performance monitoring counters with the aid of a Decision Transformer. Experimental evaluation is performed in the context of the B-tree and R-tree indexes. Performance results demonstrate that P-MOSS has up to 6x improvement over traditional schedules in terms of query throughput.

In this paper, we present an unconditionally secure $N$-party comparison scheme based on Shamir secret sharing, utilizing the binary representation of private inputs to determine the $\max$ without disclosing any private inputs or intermediate results. Specifically, each party holds a private number and aims to ascertain the greatest number among the $N$ available private numbers without revealing its input, assuming that there are at most $T < \frac{N}{2}$ honest-but-curious parties. The proposed scheme demonstrates a lower computational complexity compared to existing schemes that can only compare two secret numbers at a time. To the best of our knowledge, our scheme is the only information-theoretically secure method for comparing $N$ private numbers without revealing either the private inputs or any intermediate results. We demonstrate that by modifying the proposed scheme, we can compute other well-known non-polynomial functions of the inputs, including the minimum, median, and rank. Additionally, in the proposed scheme, before the final reveal phase, each party possesses a share of the result, enabling the nodes to compute any polynomial function of the comparison result. We also explore various applications of the proposed comparison scheme, including federated learning., Comment: 11 pages, 4 figures

This paper explores the challenges of PAC learning in semi-enclosed environments that face persistent disruptive noise and demonstrates the weaknesses of traditional learning models based on noise-free data. We present a novel algorithm that enhances noise robustness in semiconservative learning by using robust optimization techniques and advanced error correction methods and improves learning accuracy without adding additional computational cost. We also prove that this algorithm is very resistant to hostile noises. Experimental results on various datasets demonstrate its effectiveness. They provide a scalable solution for increasing the reliability of machine learning in noisy environments which contributes to noise-resilient learning and increased confidence in ML applications.

In recent years, interest in vision-language tasks has grown, especially those involving chart interactions. These tasks are inherently multimodal, requiring models to process chart images, accompanying text, underlying data tables, and often user queries. Traditionally, Chart Understanding (CU) relied on heuristics and rule-based systems. However, recent advancements that have integrated transformer architectures significantly improved performance. This paper reviews prominent research in CU, focusing on State-of-The-Art (SoTA) frameworks that employ transformers within End-to-End (E2E) solutions. Relevant benchmarking datasets and evaluation techniques are analyzed. Additionally, this article identifies key challenges and outlines promising future directions for advancing CU solutions. Following the PRISMA guidelines, a comprehensive literature search is conducted across Google Scholar, focusing on publications from Jan'20 to Jun'24. After rigorous screening and quality assessment, 32 studies are selected for in-depth analysis. The CU tasks are categorized into a three-layered paradigm based on the cognitive task required. Recent advancements in the frameworks addressing various CU tasks are also reviewed. Frameworks are categorized into single-task or multi-task based on the number of tasks solvable by the E2E solution. Within multi-task frameworks, pre-trained and prompt-engineering-based techniques are explored. This review overviews leading architectures, datasets, and pre-training tasks. Despite significant progress, challenges remain in OCR dependency, handling low-resolution images, and enhancing visual reasoning. Future directions include addressing these challenges, developing robust benchmarks, and optimizing model efficiency. Additionally, integrating explainable AI techniques and exploring the balance between real and synthetic data are crucial for advancing CU research.

Artifacts often degrade the visual quality of virtual try-on (VTON) and pose transfer applications, impacting user experience. This study introduces a novel conditional inpainting technique designed to detect and remove such distortions, improving image aesthetics. Our work is the first to present an end-to-end framework addressing this specific issue, and we developed a specialized dataset of artifacts in VTON and pose transfer tasks, complete with masks highlighting the affected areas. Experimental results show that our method not only effectively removes artifacts but also significantly enhances the visual quality of the final images, setting a new benchmark in computer vision and image processing.

A forcing set for a perfect matching of a graph is defined as a subset of the edges of that perfect matching such that there exists a unique perfect matching containing it. A complete forcing set for a graph is a subset of its edges, such that it intersects the edges of every perfect matching in a forcing set of that perfect matching. The size of a smallest complete forcing set of a graph is called the complete forcing number of the graph. In this paper, we derive new upper bounds for the complete forcing number of graphs in terms of other graph theoretical parameters such as the degeneracy or the spectral radius of the graph. We show that for graphs with the number of edges more than some constant times the number of vertices, our result outperforms the best known upper bound for the complete forcing number. For the set of edge-transitive graphs, we present a lower bound for the complete forcing number in terms of maximum forcing number. This result in particular is applied to the hypercube graphs and Cartesian powers of even cycles., Comment: 18 pages

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased computational demands, particularly during inference and fine-tuning. To address these challenges, we introduce EchoAtt, a novel framework aimed at optimizing transformer-based models by analyzing and leveraging the similarity of attention patterns across layers. Our analysis reveals that many inner layers in LLMs, especially larger ones, exhibit highly similar attention matrices. By exploiting this similarity, EchoAtt enables the sharing of attention matrices in less critical layers, significantly reducing computational requirements without compromising performance. We incorporate this approach within a knowledge distillation setup, where a pre-trained teacher model guides the training of a smaller student model. The student model selectively shares attention matrices in layers with high similarity while inheriting key parameters from the teacher. Our best results with TinyLLaMA-1.1B demonstrate that EchoAtt improves inference speed by 15\%, training speed by 25\%, and reduces the number of parameters by approximately 4\%, all while improving zero-shot performance. These findings highlight the potential of attention matrix sharing to enhance the efficiency of LLMs, making them more practical for real-time and resource-limited applications.

Disaggregating memory from compute offers the opportunity to better utilize stranded memory in cloud data centers. It is important to cache data in the compute nodes and maintain cache coherence across multiple compute nodes. However, the limited computing power on disaggregated memory servers makes traditional cache coherence protocols suboptimal, particularly in the case of stranded memory. This paper introduces SELCC; a Shared-Exclusive Latch Cache Coherence protocol that maintains cache coherence without imposing any computational burden on the remote memory side. It aligns the state machine of the shared-exclusive latch protocol with the MSI protocol , thereby ensuring both atomicity of data access and cache coherence with sequential consistency. SELCC embeds cache-ownership metadata directly into the RDMA latch word, enabling efficient cache ownership management via RDMA atomic operations. SELCC can serve as an abstraction layer over disaggregated memory with APIs that resemble main-memory accesses. A concurrent B-tree and three transaction concurrency control algorithms are realized using SELCC's abstraction layer. Experimental results show that SELCC significantly outperforms Remote-Procedure-Call-based protocols for cache coherence under limited remote computing power. Applications on SELCC achieve comparable or superior performance over disaggregated memory compared to competitors.

We present a 3D food printing (3DFP) method to create coiled structures, harnessing the liquid rope coiling effect as a rapid method of food printing with tunable fractural properties. By studying the printability and coil-forming ability of pea, carrot, and cookie dough inks, we identified optimal printing parameters to induce steady and controlled coiling, enabling the creation of coiled structures with tunable porosities using a single nozzle. Fracture profiles from post-processed coiled structures showed complex responses but presented direct correlations between the porosity and textural parameters, including hardness, brittleness, and initial stiffness. This study provides a foundation for the fabrication of coiled food structures using 3DFP and highlights its potential application in designing textural properties and a range of unique sensory experiences., Comment: Main text: 19 pages, 9 figures. SI: 10 pages, 11 figures

Multimodal learning involves integrating information from various modalities to enhance learning and comprehension. We compare three modality fusion strategies in person identification and verification by processing two modalities: voice and face. In this paper, a one-dimensional convolutional neural network is employed for x-vector extraction from voice, while the pre-trained VGGFace2 network and transfer learning are utilized for face modality. In addition, gammatonegram is used as speech representation in engagement with the Darknet19 pre-trained network. The proposed systems are evaluated using the K-fold cross-validation technique on the 118 speakers of the test set of the VoxCeleb2 dataset. The comparative evaluations are done for single-modality and three proposed multimodal strategies in equal situations. Results demonstrate that the feature fusion strategy of gammatonegram and facial features achieves the highest performance, with an accuracy of 98.37% in the person identification task. However, concatenating facial features with the x-vector reaches 0.62% for EER in verification tasks., Comment: This paper was accepted at the ICNLSP2024 conference

In automatic speech recognition, any factor that alters the acoustic properties of speech can pose a challenge to the system's performance. This paper presents a novel approach for automatic whispered speech recognition in the Irish dialect using the self-supervised WavLM model. Conventional automatic speech recognition systems often fail to accurately recognise whispered speech due to its distinct acoustic properties and the scarcity of relevant training data. To address this challenge, we utilized a pre-trained WavLM model, fine-tuned with a combination of whispered and normal speech data from the wTIMIT and CHAINS datasets, which include the English language in Singaporean and Irish dialects, respectively. Our baseline evaluation with the OpenAI Whisper model highlighted its limitations, achieving a Word Error Rate (WER) of 18.8% and a Character Error Rate (CER) of 4.24% on whispered speech. In contrast, the proposed WavLM-based system significantly improved performance, achieving a WER of 9.22% and a CER of 2.59%. These results demonstrate the efficacy of our approach in recognising whispered speech and underscore the importance of tailored acoustic modeling for robust automatic speech recognition systems. This study provides valuable insights into developing effective automatic speech recognition solutions for challenging speech affected by whisper and dialect. The source codes for this paper are freely available., Comment: This paper was accepted at the ICCKE2024 conference

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings, while crucial for aesthetic quality, do not significantly contribute towards the subject and background consistency of video outputs. Moreover, the computationally expensive cross-attention mechanism can be effectively replaced by a simpler linear layer. This layer is computed only once at the first diffusion inference step, and its output is then cached and reused throughout the inference process, thereby enhancing efficiency while maintaining high-quality outputs. Building on these insights, we introduce the VCUT, a training-free approach optimized for efficiency within the SVD architecture. VCUT eliminates temporal cross-attention and replaces spatial cross-attention with a one-time computed linear layer, significantly reducing computational load. The implementation of VCUT leads to a reduction of up to 322T Multiple-Accumulate Operations (MACs) per video and a decrease in model parameters by up to 50M, achieving a 20% reduction in latency compared to the baseline. Our approach demonstrates that conditioning during the Semantic Binding stage is sufficient, eliminating the need for continuous computation across all inference steps and setting a new standard for efficient video generation.

Industry 5.0, which focuses on human and Artificial Intelligence (AI) collaboration for performing different tasks in manufacturing, involves a higher number of robots, Internet of Things (IoTs) devices and interconnections, Augmented/Virtual Reality (AR), and other smart devices. The huge involvement of these devices and interconnection in various critical areas, such as economy, health, education and defense systems, poses several types of potential security flaws. AI itself has been proven a very effective and powerful tool in different areas of cybersecurity, such as intrusion detection, malware detection, and phishing detection, among others. Just as in many application areas, cybersecurity professionals were reluctant to accept black-box ML solutions for cybersecurity applications. This reluctance pushed forward the adoption of eXplainable Artificial Intelligence (XAI) as a tool that helps explain how decisions are made in ML-based systems. In this survey, we present a comprehensive study of different XAI-based intrusion detection systems for industry 5.0, and we also examine the impact of explainability and interpretability on Cybersecurity practices through the lens of Adversarial XIDS (Adv-XIDS) approaches. Furthermore, we analyze the possible opportunities and challenges in XAI cybersecurity systems for industry 5.0 that elicit future research toward XAI-based solutions to be adopted by high-stakes industry 5.0 applications. We believe this rigorous analysis will establish a foundational framework for subsequent research endeavors within the specified domain., Comment: 57 pages, 6 figures

HTAP systems are designed to handle transactional and analytical workloads. Besides a mixed workload at any given time, the workload can also change over time. A popular type of continuously changing workload is one that oscillates between being write-heavy at times and being read-heavy at other times. Oscillating workloads can be observed in many applications. Indexes, e.g., the B+-tree and the LSM-tree, cannot perform equally well all the time. Conventional adaptive indexing does not solve this issue as it focuses on adapting in one direction. This paper studies how to support oscillating workloads with adaptive indexes that adapt the underlying index structures in both directions. With the observation that real-world datasets are skewed, the focus is to optimize the index within the hotspot regions. The Adaptive Hotspot-Aware Tree (or AHA-tree, for short) is introduced, where its adaptation is bi-directional. Experimental evaluation show that AHA-tree can behave competitively as compared to an LSM-tree for write-heavy transactional workloads. Upon switching to a read-heavy analytical workload, AHA-tree can gradually adapt and behave competitively, and can match the B+-tree in read performance.

In this demo, we realize data indexes that can morph from being write-optimized at times to being read-optimized at other times nonstop with zero-down time during the workload transitioning. These data indexes are useful for HTAP systems (Hybrid Transactional and Analytical Processing Systems), where transactional workloads are write-heavy while analytical workloads are read-heavy. Traditional indexes, e.g., B+-tree and LSM-Tree, although optimized for one kind of workload, cannot perform equally well under all workloads. To migrate from the write-optimized LSM-Tree to a read-optimized B+-tree is costly and mandates some system down time to reorganize data. We design adaptive indexes that can dynamically morph from a pure LSM-tree to a pure buffered B-tree back and forth, and has interesting states in-between. There are two challenges: allowing concurrent operations and avoiding system down time. This demo benchmarks the proposed AHA-Tree index under dynamic workloads and shows how the index evolves from one state to another without blocking.

RoboCup Soccer Simulation 2D (SS2D) research is hampered by the complexity of existing Cpp-based codes like Helios, Cyrus, and Gliders, which also suffer from limited integration with modern machine learning frameworks. This development paper introduces a transformative solution a gRPC-based, language-agnostic framework that seamlessly integrates with the high-performance Helios base code. This approach not only facilitates the use of diverse programming languages including CSharp, JavaScript, and Python but also maintains the computational efficiency critical for real time decision making in SS2D. By breaking down language barriers, our framework significantly enhances collaborative potential and flexibility, empowering researchers to innovate without the overhead of mastering or developing extensive base codes. We invite the global research community to leverage and contribute to the Cross Language Soccer (CLS) framework, which is openly available under the MIT License, to drive forward the capabilities of multi-agent systems in soccer simulations.

In the Soccer Simulation 2D environment, accurate observation is crucial for effective decision making. However, challenges such as partial observation and noisy data can hinder performance. To address these issues, we propose a denoising algorithm that leverages predictive modeling and intersection analysis to enhance the accuracy of observations. Our approach aims to mitigate the impact of noise and partial data, leading to improved gameplay performance. This paper presents the framework, implementation, and preliminary results of our algorithm, demonstrating its potential in refining observations in Soccer Simulation 2D. Cyrus 2D Team is using a combination of Helios, Gliders, and Cyrus base codes.

The idea of generalized indices is one of the success stories of database systems research. It has found its way to implementation in common database systems. GiST (Generalized Search Tree) and SP-GiST (Space-Partitioned Generalized Search Tree) are two widely-used generalized indices that are typically used for multidimensional data. Currently, the generalized indices GiST and SP-GiST represent one database object using one index entry, e.g., a bounding box for each spatio-temporal object. However, when dealing with complex objects, e.g., moving object trajectories, a single entry per object is inadequate for creating efficient indices. Previous research has highlighted that splitting trajectories into multiple bounding boxes prior to indexing can enhance query performance as it leads to a higher index filter. In this paper, we introduce MGiST and MSP-GiST, the multi-entry generalized search tree counterparts of GiST and SP-GiST, respectively, that are designed to enable the partitioning of objects into multiple entries during insertion. The methods for decomposing a complex object into multiple sub-objects differ from one data type to another, and may depend on some domain-specific parameters. Thus, MGiST and MSP-GiST are designed to allow for pluggable modules that aid in optimizing the split of an object into multiple sub-objects. We demonstrate the usefulness of MGiST and MSP-GiST using a trajectory indexing scenario, where we realize several trajectory indexes using MGiST and MSP-GiST and instantiate these search trees with trajectory-specific splitting algorithms. We create and test the performance of several multi-entry versions of widely-used spatial index structures, e.g., R-Tree, Quad-Tree, and KD-Tree. We conduct evaluations using both synthetic and real-world data, and observe up to an order of magnitude enhancement in performance of point, range, and KNN queries.

Graph Neural Networks (GNNs) have advanced spatiotemporal forecasting by leveraging relational inductive biases among sensors (or any other measuring scheme) represented as nodes in a graph. However, current methods often rely on Recurrent Neural Networks (RNNs), leading to increased runtimes and memory use. Moreover, these methods typically operate within 1-hop neighborhoods, exacerbating the reduction of the receptive field. Causal Graph Processes (CGPs) offer an alternative, using graph filters instead of MLP layers to reduce parameters and minimize memory consumption. This paper introduces the Causal Graph Process Neural Network (CGProNet), a non-linear model combining CGPs and GNNs for spatiotemporal forecasting. CGProNet employs higher-order graph filters, optimizing the model with fewer parameters, reducing memory usage, and improving runtime efficiency. We present a comprehensive theoretical and experimental stability analysis, highlighting key aspects of CGProNet. Experiments on synthetic and real data demonstrate CGProNet's superior efficiency, minimizing memory and time requirements while maintaining competitive forecasting performance., Comment: 21 pages, 4 figures

Processing multidomain data defined on multiple graphs holds significant potential in various practical applications in computer science. However, current methods are mostly limited to discrete graph filtering operations. Tensorial partial differential equations on graphs (TPDEGs) provide a principled framework for modeling structured data across multiple interacting graphs, addressing the limitations of the existing discrete methodologies. In this paper, we introduce Continuous Product Graph Neural Networks (CITRUS) that emerge as a natural solution to the TPDEG. CITRUS leverages the separability of continuous heat kernels from Cartesian graph products to efficiently implement graph spectral decomposition. We conduct thorough theoretical analyses of the stability and over-smoothing properties of CITRUS in response to domain-specific graph perturbations and graph spectra effects on the performance. We evaluate CITRUS on well-known traffic and weather spatiotemporal forecasting datasets, demonstrating superior performance over existing approaches. The implementation codes are available at https://github.com/ArefEinizade2/CITRUS., Comment: 20 pages, 5 figures

Randomized smoothing has shown promising certified robustness against adversaries in classification tasks. Despite such success with only zeroth-order access to base models, randomized smoothing has not been extended to a general form of regression. By defining robustness in regression tasks flexibly through probabilities, we demonstrate how to establish upper bounds on input data point perturbation (using the $\ell_2$ norm) for a user-specified probability of observing valid outputs. Furthermore, we showcase the asymptotic property of a basic averaging function in scenarios where the regression model operates without any constraint. We then derive a certified upper bound of the input perturbations when dealing with a family of regression models where the outputs are bounded. Our simulations verify the validity of the theoretical results and reveal the advantages and limitations of simple smoothing functions, i.e., averaging, in regression tasks. The code is publicly available at \url{https://github.com/arekavandi/Certified_Robust_Regression}.

Processing, managing, and analyzing dynamic graphs are the cornerstone in multiple application domains including fraud detection, recommendation system, graph neural network training, etc. This demo presents GTX, a latch-free write-optimized transactional graph data system that supports high throughput read-write transactions while maintaining competitive graph analytics. GTX has a unique latch-free graph storage and a transaction and concurrency control protocol for dynamic power-law graphs. GTX leverages atomic operations to eliminate latches, proposes a delta-based multi-version storage, and designs a hybrid transaction commit protocol to reduce interference between concurrent operations. To further improve its throughput, we design a delta-chains index to support efficient edge lookups. GTX manages concurrency control at delta-chain level, and provides adaptive concurrency according to the workload. Real-world graph access and updates exhibit temporal localities and hotspots. Unlike other transactional graph systems that experience significant performance degradation, GTX is the only system that can adapt to temporal localities and hotspots in graph updates and maintain million-transactions-per-second throughput. GTX is prototyped as a graph library and is evaluated using a graph library evaluation tool using real and synthetic datasets., Comment: 4 pages 2 figures for VLDB 2024 DEMO

This paper introduces GTX, a standalone main-memory write-optimized graph data system that specializes in structural and graph property updates while enabling concurrent reads and graph analytics through ACID transactions. Recent graph systems target concurrent read and write support while guaranteeing transaction semantics. However, their performance suffers from updates with real-world temporal locality over the same vertices and edges due to vertex-centric lock contentions. GTX has an adaptive delta-chain locking protocol on top of a carefully designed latch-free graph storage. It eliminates vertex-level locking contention, and adapts to real-life workloads while maintaining sequential access to the graph's adjacency lists storage. GTX's transactions further support cache-friendly block level concurrency control, and cooperative group commit and garbage collection. This combination of features ensures high update throughput and provides low-latency graph analytics. Based on experimental evaluation, in addition to not sacrificing the performance of read-heavy analytical workloads, and having competitive performance similar to state-of-the-art systems, GTX has high read-write transaction throughput. For write-heavy transactional workloads, GTX achieves up to 11x better transaction throughput than the best-performing state-of-the-art system., Comment: technical report for our main paper GTX: A Write-Optimized Latch-free Graph Data System with Transactional Support

Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic image detectors are unable to detect synthetic videos. We demonstrate that this is because synthetic video generators introduce substantially different traces than those left by image generators. Despite this, we show that synthetic video traces can be learned, and used to perform reliable synthetic video detection or generator source attribution even after H.264 re-compression. Furthermore, we demonstrate that while detecting videos from new generators through zero-shot transferability is challenging, accurate detection of videos from a new generator can be achieved through few-shot learning., Comment: To be published in CVPRW24

As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new techniques can vastly differ from those learned during training, and access to data for these new generators is often limited. To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors. E3 enables the accurate detection of images from newly emerged generators using minimal training data. Our approach does this by first employing transfer learning to develop a suite of expert embedders, each specializing in the forensic traces of a specific generator. Then, all embeddings are jointly analyzed by an Expert Knowledge Fusion Network to produce accurate and reliable detection decisions. Our experiments demonstrate that E3 outperforms existing continual learning methods, including those developed specifically for synthetic image detection., Comment: 11 pages, 4 figures, To be published in CVPRWMF24