We introduce Principal Component Analysis guided Quantile Sampling (PCA QS), a novel sampling framework designed to preserve both the statistical and geometric structure of large scale datasets. Unlike conventional PCA, which reduces dimensionality at the cost of interpretability, PCA QS retains the original feature space while using leading principal components solely to guide a quantile based stratification scheme. This principled design ensures that sampling remains representative without distorting the underlying data semantics. We establish rigorous theoretical guarantees, deriving convergence rates for empirical quantiles, Kullback Leibler divergence, and Wasserstein distance, thus quantifying the distributional fidelity of PCA QS samples. Practical guidelines for selecting the number of principal components, quantile bins, and sampling rates are provided based on these results. Extensive empirical studies on both synthetic and real-world datasets show that PCA QS consistently outperforms simple random sampling, yielding better structure preservation and improved downstream model performance. Together, these contributions position PCA QS as a scalable, interpretable, and theoretically grounded solution for efficient data summarization in modern machine learning workflows.
This study critically distinguishes between AI Agents and Agentic AI, offering a structured conceptual taxonomy, application mapping, and challenge analysis to clarify their divergent design philosophies and capabilities. We begin by outlining the search strategy and foundational definitions, characterizing AI Agents as modular systems driven by Large Language Models (LLMs) and Large Image Models (LIMs) for narrow, task-specific automation. Generative AI is positioned as a precursor, with AI Agents advancing through tool integration, prompt engineering, and reasoning enhancements. In contrast, Agentic AI systems represent a paradigmatic shift marked by multi-agent collaboration, dynamic task decomposition, persistent memory, and orchestrated autonomy. Through a sequential evaluation of architectural evolution, operational mechanisms, interaction styles, and autonomy levels, we present a comparative analysis across both paradigms. Application domains such as customer support, scheduling, and data summarization are contrasted with Agentic AI deployments in research automation, robotic coordination, and medical decision support. We further examine unique challenges in each paradigm including hallucination, brittleness, emergent behavior, and coordination failure and propose targeted solutions such as ReAct loops, RAG, orchestration layers, and causal modeling. This work aims to provide a definitive roadmap for developing robust, scalable, and explainable AI agent and Agentic AI-driven systems. >AI Agents, Agent-driven, Vision-Language-Models, Agentic AI Decision Support System, Agentic-AI Applications
Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) finds meaningful patterns in spatial data by considering density and spatial proximity. As the clustering algorithm is inherently designed for static applications, so have recent studies focused on accelerating the algorithm for static applications using approximate or parallel methods. However, much less attention has been given to dynamic environments, where even a single point insertion or deletion can require recomputing the clustering hierarchy from scratch due to the need of maintaining the minimum spanning tree (MST) over a complete graph. This paper addresses the challenge of enhancing the clustering algorithm for dynamic data. We present an exact algorithm that maintains density information and updates the clustering hierarchy of HDBSCAN during point insertions and deletions. Considering the hardness of adapting the exact algorithm to dynamic data involving modern workloads, we propose an online-offline framework. The online component efficiently summarizes dynamic data using a tree structure, called Bubble-tree, while the offline step performs the static clustering. Experimental results demonstrate that the data summarization adapts well to fully dynamic environments, providing compression quality on par with existing techniques while significantly improving runtime performance of the clustering algorithm in dynamic data workloads.
Data summarization tasks are often modeled as $k$-clustering problems, where the goal is to choose $k$ data points, called cluster centers, that best represent the dataset by minimizing a clustering objective. A popular objective is to minimize the maximum distance between any data point and its nearest center, which is formalized as the $k$-center problem. While in some applications all data points can be chosen as centers, in the general setting, centers must be chosen from a predefined subset of points, referred as facilities or suppliers; this is known as the $k$-supplier problem. In this work, we focus on fair data summarization modeled as the fair $k$-supplier problem, where data consists of several groups, and a minimum number of centers must be selected from each group while minimizing the $k$-supplier objective. The groups can be disjoint or overlapping, leading to two distinct problem variants each with different computational complexity. We present $3$-approximation algorithms for both variants, improving the previously known factor of $5$. For disjoint groups, our algorithm runs in polynomial time, while for overlapping groups, we present a fixed-parameter tractable algorithm, where the exponential runtime depends only on the number of groups and centers. We show that these approximation factors match the theoretical lower bounds, assuming standard complexity theory conjectures. Finally, using an open-source implementation, we demonstrate the scalability of our algorithms on large synthetic datasets and assess the price of fairness on real-world data, comparing solution quality with and without fairness constraints.
Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distribution between training and testing sets. However, given that urban systems are usually dynamic, multi-sourced with imbalanced data distributions, current specific task-specific models fail to generalize to new urban conditions and adapt to new domains without explicitly modeling interdependencies across various dimensions and types of urban data. To this end, we argue that there is an essential to propose a Continuous Multi-task Spatio-Temporal learning framework (CMuST) to empower collective urban intelligence, which reforms the urban spatiotemporal learning from single-domain to cooperatively multi-dimensional and multi-task learning. Specifically, CMuST proposes a new multi-dimensional spatiotemporal interaction network (MSTI) to allow cross-interactions between context and main observations as well as self-interactions within spatial and temporal aspects to be exposed, which is also the core for capturing task-level commonality and personalization. To ensure continuous task learning, a novel Rolling Adaptation training scheme (RoAda) is devised, which not only preserves task uniqueness by constructing data summarization-driven task prompts, but also harnesses correlated patterns among tasks by iterative model behavior modeling. We further establish a benchmark of three cities for multi-task spatiotemporal learning, and empirically demonstrate the superiority of CMuST via extensive evaluations on these datasets. The impressive improvements on both few-shot streaming data and new domain tasks against existing SOAT methods are achieved. Code is available at https://github.com/DILab-USTCSZ/CMuST.
Submodular optimization with bandit feedback has recently been studied in a variety of contexts. In a number of real-world applications such as diversified recommender systems and data summarization, the submodular function exhibits additional linear structure. We consider developing approximation algorithms for the maximization of a submodular objective function $f:2^U\to\mathbb{R}_{\geq 0}$, where $f=\sum_{i=1}^dw_iF_{i}$. It is assumed that we have value oracle access to the functions $F_i$, but the coefficients $w_i$ are unknown, and $f$ can only be accessed via noisy queries. We develop algorithms for this setting inspired by adaptive allocation algorithms in the best-arm identification for linear bandit, with approximation guarantees arbitrarily close to the setting where we have value oracle access to $f$. Finally, we empirically demonstrate that our algorithms make vast improvements in terms of sample efficiency compared to algorithms that do not exploit the linear structure of $f$ on instances of move recommendation.
We introduce a novel subset selection problem called min-distance diversification with monotone submodular utility ($\textsf{MDMS}$), which has a wide variety of applications in machine learning, e.g., data sampling and feature selection. Given a set of points in a metric space, the goal of $\textsf{MDMS}$ is to maximize an objective function combining a monotone submodular utility term and a min-distance diversity term between any pair of selected points, subject to a cardinality constraint. We propose the $\texttt{GIST}$ algorithm, which achieves a $\frac{1}{2}$-approximation guarantee for $\textsf{MDMS}$ by approximating a series of maximum independent set problems with a bicriteria greedy algorithm. We also prove that it is NP-hard to approximate to within a factor of $0.5584$. Finally, we demonstrate that $\texttt{GIST}$ outperforms existing benchmarks for on a real-world image classification task that studies single-shot subset selection for ImageNet.
This paper introduces a federated learning framework tailored for online combinatorial optimization with bandit feedback. In this setting, agents select subsets of arms, observe noisy rewards for these subsets without accessing individual arm information, and can cooperate and share information at specific intervals. Our framework transforms any offline resilient single-agent $(\alpha-\epsilon)$-approximation algorithm, having a complexity of $\tilde{\mathcal{O}}(\frac{\psi}{\epsilon^\beta})$, where the logarithm is omitted, for some function $\psi$ and constant $\beta$, into an online multi-agent algorithm with $m$ communicating agents and an $\alpha$-regret of no more than $\tilde{\mathcal{O}}(m^{-\frac{1}{3+\beta}} \psi^\frac{1}{3+\beta} T^\frac{2+\beta}{3+\beta})$. This approach not only eliminates the $\epsilon$ approximation error but also ensures sublinear growth with respect to the time horizon $T$ and demonstrates a linear speedup with an increasing number of communicating agents. Additionally, the algorithm is notably communication-efficient, requiring only a sublinear number of communication rounds, quantified as $\tilde{\mathcal{O}}\left(\psi T^\frac{\beta}{\beta+1}\right)$. Furthermore, the framework has been successfully applied to online stochastic submodular maximization using various offline algorithms, yielding the first results for both single-agent and multi-agent settings and recovering specialized single-agent theoretical guarantees. We empirically validate our approach to a stochastic data summarization problem, illustrating the effectiveness of the proposed framework, even in single-agent scenarios.
Most studies on machine learning in sensing systems focus on low-level perception tasks that process raw sensory data within a short time window. However, many practical applications, such as human routine modeling and occupancy tracking, require high-level reasoning abilities to comprehend concepts and make inferences based on long-term sensor traces. Existing machine learning-based approaches for handling such complex tasks struggle to generalize due to the limited training samples and the high dimensionality of sensor traces, necessitating the integration of human knowledge for designing first-principle models or logic reasoning methods. We pose a fundamental question: Can we harness the reasoning capabilities and world knowledge of Large Language Models (LLMs) to recognize complex events from long-term spatiotemporal sensor traces? To answer this question, we design an effective prompting framework for LLMs on high-level reasoning tasks, which can handle traces from the raw sensor data as well as the low-level perception results. We also design two strategies to enhance performance with long sensor traces, including summarization before reasoning and selective inclusion of historical traces. Our framework can be implemented in an edge-cloud setup, running small LLMs on the edge for data summarization and performing high-level reasoning on the cloud for privacy preservation. The results show that LLMSense can achieve over 80\% accuracy on two high-level reasoning tasks such as dementia diagnosis with behavior traces and occupancy tracking with environmental sensor traces. This paper provides a few insights and guidelines for leveraging LLM for high-level reasoning on sensor traces and highlights several directions for future work.
We describe a parallel approximation algorithm for maximizing monotone submodular functions subject to hereditary constraints on distributed memory multiprocessors. Our work is motivated by the need to solve submodular optimization problems on massive data sets, for practical contexts such as data summarization, machine learning, and graph sparsification. Our work builds on the randomized distributed RandGreedi algorithm, proposed by Barbosa, Ene, Nguyen, and Ward (2015). This algorithm computes a distributed solution by randomly partitioning the data among all the processors and then employing \emph{a single} accumulation step in which all processors send their partial solutions to one processor. However, for large problems, the accumulation step exceeds the memory available on a processor, and the processor that performs the accumulation becomes a computational bottleneck. Hence we propose a generalization of the RandGreedi algorithm that employs multiple accumulation steps to reduce the memory required. We analyze the approximation ratio and the time complexity of the algorithm (in the BSP model). We evaluate the new GreedyML algorithm on three classes of problems, and report results from large-scale data sets with millions of elements. The results show that the GreedyML algorithm can solve problems where the sequential Greedy and distributed RandGreedi algorithms fail due to memory constraints. For certain computationally intensive problems, the GreedyML algorithm is faster than the RandGreedi algorithm. The observed approximation quality of the solutions computed by the GreedyML algorithm closely matches those obtained by the RandGreedi algorithm on these problems.
In this work, we propose a novel dimensionality reduction technique, DiffRed, which first projects the data matrix, A, along first $k_1$ principal components and the residual matrix $A^{*}$ (left after subtracting its $k_1$-rank approximation) along $k_2$ Gaussian random vectors. We evaluate M1, the distortion of mean-squared pair-wise distance, and Stress, the normalized value of RMS of distortion of the pairwise distances. We rigorously prove that DiffRed achieves a general upper bound of $O\left(\sqrt{\frac{1-p}{k_2}}\right)$ on Stress and $O\left(\frac{(1-p)}{\sqrt{k_2*\rho(A^{*})}}\right)$ on M1 where $p$ is the fraction of variance explained by the first $k_1$ principal components and $\rho(A^{*})$ is the stable rank of $A^{*}$. These bounds are tighter than the currently known results for Random maps. Our extensive experiments on a variety of real-world datasets demonstrate that DiffRed achieves near zero M1 and much lower values of Stress as compared to the well-known dimensionality reduction techniques. In particular, DiffRed can map a 6 million dimensional dataset to 10 dimensions with 54% lower Stress than PCA.
The rise of the Internet and the exponential increase in data have made manual data summarization and analysis a challenging task. Instagram social network is a prominent social network widely utilized in Iran for information sharing and communication across various age groups. The inherent structure of Instagram, characterized by its text-rich content and graph-like data representation, enables the utilization of text and graph processing techniques for data analysis purposes. The degree distributions of these networks exhibit scale-free characteristics, indicating non-random growth patterns. Recently, word co-occurrence has gained attention from researchers across multiple disciplines due to its simplicity and practicality. Keyword extraction is a crucial task in natural language processing. In this study, we demonstrated that high-precision extraction of keywords from Instagram posts in the Persian language can be achieved using unsupervised word co-occurrence methods without resorting to conventional techniques such as clustering or pre-trained models. After graph visualization and community detection, it was observed that the top topics covered by news agencies are represented by these graphs. This approach is generalizable to new and diverse datasets and can provide acceptable outputs for new data. To the author's knowledge, this method has not been employed in the Persian language before on Instagram social network. The new crawled data has been publicly released on GitHub for exploration by other researchers. By employing this method, it is possible to use other graph-based algorithms, such as community detections. The results help us to identify the key role of different news agencies in information diffusion among the public, identify hidden communities, and discover latent patterns among a massive amount of data.
Maximizing submodular functions has been increasingly used in many applications of machine learning, such as data summarization, recommendation systems, and feature selection. Moreover, there has been a growing interest in both submodular maximization and dynamic algorithms. In 2020, Monemizadeh and Lattanzi, Mitrovic, Norouzi{-}Fard, Tarnawski, and Zadimoghaddam initiated developing dynamic algorithms for the monotone submodular maximization problem under the cardinality constraint $k$. Recently, there have been some improvements on the topic made by Banihashem, Biabani, Goudarzi, Hajiaghayi, Jabbarzade, and Monemizadeh. In 2022, Chen and Peng studied the complexity of this problem and raised an important open question: "Can we extend [fully dynamic] results (algorithm or hardness) to non-monotone submodular maximization?". We affirmatively answer their question by demonstrating a reduction from maximizing a non-monotone submodular function under the cardinality constraint $k$ to maximizing a monotone submodular function under the same constraint. Through this reduction, we obtain the first dynamic algorithms to solve the non-monotone submodular maximization problem under the cardinality constraint $k$. Our algorithms maintain an $(8+\epsilon)$-approximate of the solution and use expected amortized $O(\epsilon^{-3}k^3\log^3(n)\log(k))$ or $O(\epsilon^{-1}k^2\log^3(k))$ oracle queries per update, respectively. Furthermore, we showcase the benefits of our dynamic algorithm for video summarization and max-cut problems on several real-world data sets.
In the era of burgeoning data generation, managing and storing large-scale time-varying datasets poses significant challenges. With the rise of supercomputing capabilities, the volume of data produced has soared, intensifying storage and I/O overheads. To address this issue, we propose a dynamic spatio-temporal data summarization technique that identifies informative features in key timesteps and fuses less informative ones. This approach minimizes storage requirements while preserving data dynamics. Unlike existing methods, our method retains both raw and summarized timesteps, ensuring a comprehensive view of information changes over time. We utilize information-theoretic measures to guide the fusion process, resulting in a visual representation that captures essential data patterns. We demonstrate the versatility of our technique across diverse datasets, encompassing particle-based flow simulations, security and surveillance applications, and biological cell interactions within the immune system. Our research significantly contributes to the realm of data management, introducing enhanced efficiency and deeper insights across diverse multidisciplinary domains. We provide a streamlined approach for handling massive datasets that can be applied to in situ analysis as well as post hoc analysis. This not only addresses the escalating challenges of data storage and I/O overheads but also unlocks the potential for informed decision-making. Our method empowers researchers and experts to explore essential temporal dynamics while minimizing storage requirements, thereby fostering a more effective and intuitive understanding of complex data behaviors.
The problem of non-monotone $k$-submodular maximization under a knapsack constraint ($\kSMK$) over the ground set size $n$ has been raised in many applications in machine learning, such as data summarization, information propagation, etc. However, existing algorithms for the problem are facing questioning of how to overcome the non-monotone case and how to fast return a good solution in case of the big size of data. This paper introduces two deterministic approximation algorithms for the problem that competitively improve the query complexity of existing algorithms. Our first algorithm, $\LAA$, returns an approximation ratio of $1/19$ within $O(nk)$ query complexity. The second one, $\RLA$, improves the approximation ratio to $1/5-\epsilon$ in $O(nk)$ queries, where $\epsilon$ is an input parameter. Our algorithms are the first ones that provide constant approximation ratios within only $O(nk)$ query complexity for the non-monotone objective. They, therefore, need fewer the number of queries than state-of-the-the-art ones by a factor of $\Omega(\log n)$. Besides the theoretical analysis, we have evaluated our proposed ones with several experiments in some instances: Influence Maximization and Sensor Placement for the problem. The results confirm that our algorithms ensure theoretical quality as the cutting-edge techniques and significantly reduce the number of queries.
The objective of a two-stage submodular maximization problem is to reduce the ground set using provided training functions that are submodular, with the aim of ensuring that optimizing new objective functions over the reduced ground set yields results comparable to those obtained over the original ground set. This problem has applications in various domains including data summarization. Existing studies often assume the monotonicity of the objective function, whereas our work pioneers the extension of this research to accommodate non-monotone submodular functions. We have introduced the first constant-factor approximation algorithms for this more general case.
Data summarization is the process of generating interpretable and representative subsets from a dataset. Existing time series summarization approaches often search for recurring subsequences using a set of manually devised similarity functions to summarize the data. However, such approaches are fraught with limitations stemming from an exhaustive search coupled with a heuristic definition of series similarity. Such approaches affect the diversity and comprehensiveness of the generated data summaries. To mitigate these limitations, we introduce an approach to time series summarization, called Time-to-Pattern (T2P), which aims to find a set of diverse patterns that together encode the most salient information, following the notion of minimum description length. T2P is implemented as a deep generative model that learns informative embeddings of the discrete time series on a latent space specifically designed to be interpretable. Our synthetic and real-world experiments reveal that T2P discovers informative patterns, even in noisy and complex settings. Furthermore, our results also showcase the improved performance of T2P over previous work in pattern diversity and processing scalability, which conclusively demonstrate the algorithm's effectiveness for time series summarization.
Despite recent advances in synthetic data generation, the scientific community still lacks a unified consensus on its usefulness. It is commonly believed that synthetic data can be used for both data exchange and boosting machine learning (ML) training. Privacy-preserving synthetic data generation can accelerate data exchange for downstream tasks, but there is not enough evidence to show how or why synthetic data can boost ML training. In this study, we benchmarked ML performance using synthetic tabular data for four use cases: data sharing, data augmentation, class balancing, and data summarization. We observed marginal improvements for the balancing use case on some datasets. However, we conclude that there is not enough evidence to claim that synthetic tabular data is useful for ML training.
Automatic chart to text summarization is an effective tool for the visually impaired people along with providing precise insights of tabular data in natural language to the user. A large and well-structured dataset is always a key part for data driven models. In this paper, we propose ChartSumm: a large-scale benchmark dataset consisting of a total of 84,363 charts along with their metadata and descriptions covering a wide range of topics and chart types to generate short and long summaries. Extensive experiments with strong baseline models show that even though these models generate fluent and informative summaries by achieving decent scores in various automatic evaluation metrics, they often face issues like suffering from hallucination, missing out important data points, in addition to incorrect explanation of complex trends in the charts. We also investigated the potential of expanding ChartSumm to other languages using automated translation tools. These make our dataset a challenging benchmark for future research.
Submodular function optimization has numerous applications in machine learning and data analysis, including data summarization which aims to identify a concise and diverse set of data points from a large dataset. It is important to implement fairness-aware algorithms when dealing with data items that may contain sensitive attributes like race or gender, to prevent biases that could lead to unequal representation of different groups. With this in mind, we investigate the problem of maximizing a monotone submodular function while meeting group fairness constraints. Unlike previous studies in this area, we allow for randomized solutions, with the objective being to calculate a distribution over feasible sets such that the expected number of items selected from each group is subject to constraints in the form of upper and lower thresholds, ensuring that the representation of each group remains balanced in the long term. Here a set is considered feasible if its size does not exceed a constant value of $b$. Our research includes the development of a series of approximation algorithms for this problem.