arXiv subjects

Dimitrios Skoutas

Publications and source records attributed to Dimitrios Skoutas.

14 recordsLinked to original sources

arXiv2026

Context-Enriched Natural Language Descriptions of Vessel Trajectories

We address the problem of transforming raw vessel trajectory data collected from AIS into structured and semantically enriched representations interpretable by humans and directly usable by machine reasoning systems. We propose a context-aware trajectory abstraction framework that segments noisy AIS sequences into distinct trips each consisting of clean, mobility-annotated episodes. Each episode is further enriched with multi-source contextual information, such as nearby geographic entities, offshore navigation features, and weather conditions. Crucially, such representations can support generation of controlled natural language descriptions using LLMs. We empirically examine the quality of such descriptions generated using several LLMs over AIS data along with open contextual features. By increasing semantic density and reducing spatiotemporal complexity, this abstraction can facilitate downstream analytics and enable integration with LLMs for higher-level maritime reasoning tasks.

cs.AI↗

arXiv2026

Data-Driven Trajectory Imputation for Vessel Mobility Analysis

Modeling vessel activity at sea is critical for a wide range of applications, including route planning, transportation logistics, maritime safety, and environmental monitoring. Over the past two decades, the Automatic Identification System (AIS) has enabled real-time monitoring of hundreds of thousands of vessels, generating huge amounts of data daily. One major challenge in using AIS data is the presence of large gaps in vessel trajectories, often caused by coverage limitations or intentional transmission interruptions. These gaps can significantly degrade data quality, resulting in inaccurate or incomplete analysis. State-of-the-art imputation approaches have mainly been devised to tackle gaps in vehicle trajectories, even when the underlying road network is not considered. But the motion patterns of sailing vessels differ substantially, e.g., smooth turns, maneuvering near ports, or navigating in adverse weather conditions. In this application paper, we propose HABIT, a lightweight, configurable H3 Aggregation-Based Imputation framework for vessel Trajectories. This data-driven framework provides a valuable means to impute missing trajectory segments by extracting, analyzing, and indexing motion patterns from historical AIS data. Our empirical study over AIS data across various timeframes, densities, and vessel types reveals that HABIT produces maritime trajectory imputations performing comparably to baseline methods in terms of accuracy, while performing better in terms of latency while accounting for vessel characteristics and their motion patterns.

cs.DB↗

arXiv2026

DistillER: Knowledge Distillation in Entity Resolution with Large Language Models

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate either in unsupervised settings and rely on very large and costly models, or in supervised settings and require ground-truth annotations, leaving a critical gap between time efficiency and effectiveness. To make LLM-powered ER more practical, we investigate Knowledge Distillation (KD) as a means to transfer knowledge from large, effective models (Teachers) to smaller, more efficient models (Students) without requiring gold labels. We introduce DistillER, the first framework that systematically bridges this gap across three dimensions: (i) Data Selection, where we study strategies for identifying informative subsets of data; (ii) Knowledge Elicitation, where we compare single- and multi-teacher settings across LLMs and smaller language models (SLMs); and (iii) Distillation Algorithms, where we evaluate supervised fine-tuning and reinforcement learning approaches. Our experiments reveal that supervised fine-tuning of Students on noisy labels generated by LLM Teachers consistently outperforms alternative KD strategies, while also enabling high-quality explanation generation. Finally, we benchmark DistillER against established supervised and unsupervised ER methods based on LLMs and SLMs, demonstrating significant improvements in both effectiveness and efficiency.

cs.DB↗

arXiv2026

Hippasus: Effective and Efficient Automatic Feature Augmentation for Machine Learning Tasks on Relational Data

ML models critically depend on feature quality, yet in real-world settings, useful features are often distributed across multiple relational tables rather than a single dataset. Feature augmentation addresses this problem by automatically discovering and joining additional tables to enrich a base table with predictive features. However, scaling feature augmentation to complex schemas with many tables and multi-hop relationships is challenging. It requires exploring a large space of join paths, executing costly joins, and selecting useful features from noisy results. Existing approaches suffer from either limited effectiveness or efficiency. Restricting exploration to simple joins limits predictive performance, while more expressive methods rely on expensive training data, lack scalability, or fail to fully exploit schema-level semantics. We present Hippasus, a cost-aware, LLM-augmented feature discovery framework over relational schemas that addresses these challenges. Hippasus combines lightweight statistical signals with adaptive semantic reasoning, invoking stronger (LLM-based) analysis only when necessary. It further introduces efficient multi-way join execution with cross-path feature consolidation, and a hybrid feature selection strategy that integrates statistical relevance with semantic refinement. Experiments on real-world datasets show that Hippasus improves feature augmentation accuracy by up to 26.8% over state-of-the-art methods, while achieving a favorable effectiveness-cost tradeoff.

cs.DB↗

arXiv2024

MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs

Predicting future values in multivariate time series is vital across various domains. This work explores the use of large language models (LLMs) for this task. However, LLMs typically handle one-dimensional data. We introduce MultiCast, a zero-shot LLM-based approach for multivariate time series forecasting. It allows LLMs to receive multivariate time series as input, through three novel token multiplexing solutions that effectively reduce dimensionality while preserving key repetitive patterns. Additionally, a quantization scheme helps LLMs to better learn these patterns, while significantly reducing token use for practical applications. We showcase the performance of our approach in terms of RMSE and execution time against state-of-the-art approaches on three real-world datasets.

cs.LG↗

arXiv2023

Accelerating Spatio-Textual Queries with Learned Indices

Efficiently computing spatio-textual queries has become increasingly important in various applications that need to quickly retrieve geolocated entities associated with textual information, such as in location-based services and social networks. To accelerate such queries, several works have proposed combining spatial and textual indices into hybrid index structures. Recently, the novel idea of replacing traditional indices with ML models has attracted a lot of attention. This includes works on learned spatial indices, where the main challenge is to address the lack of a total ordering among objects in a multidimensional space. In this work, we investigate how to extend this novel type of index design to the case of spatio-textual data. We study different design choices, based on either loose or tight coupling between the spatial and textual part, as well as a hybrid index that combines a traditional and a learned component. We also perform an experimental evaluation using several real-world datasets to assess the potential benefits of using a learned index for evaluating spatio-textual queries.

cs.DS↗

arXiv2023

Atrapos: Real-time Evaluation of Metapath Query Workloads

Heterogeneous information networks (HINs) represent different types of entities and relationships between them. Exploring, analysing, and extracting knowledge from such networks relies on metapath queries that identify pairs of entities connected by relationships of diverse semantics. While the real-time evaluation of metapath query workloads on large, web-scale HINs is highly demanding in computational cost, current approaches do not exploit interrelationships among the queries. In this paper, we present ATRAPOS, a new approach for the real-time evaluation of metapath query workloads that leverages a combination of efficient sparse matrix multiplication and intermediate result caching. ATRAPOS selects intermediate results to cache and reuse by detecting frequent sub-metapaths among workload queries in real time, using a tailor-made data structure, the Overlap Tree, and an associated caching policy. Our experimental study on real data shows that ATRAPOS accelerates exploratory data analysis and mining on HINs, outperforming off-the-shelf caching approaches and state-of-the-art research prototypes in all examined scenarios. -- Note that this version of our work is more extended than the one presented in TheWebConf 2023 (doi: 10.1145/3543507.3583322)

cs.DB↗

arXiv2023

Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]

Many recent works on Entity Resolution (ER) leverage Deep Learning techniques involving language models to improve effectiveness. This is applied to both main steps of ER, i.e., blocking and matching. Several pre-trained embeddings have been tested, with the most popular ones being fastText and variants of the BERT model. However, there is no detailed analysis of their pros and cons. To cover this gap, we perform a thorough experimental analysis of 12 popular language models over 17 established benchmark datasets. First, we assess their vectorization overhead for converting all input entities into dense embeddings vectors. Second, we investigate their blocking performance, performing a detailed scalability analysis, and comparing them with the state-of-the-art deep learning-based blocking method. Third, we conclude with their relative performance for both supervised and unsupervised matching. Our experimental results provide novel insights into the strengths and weaknesses of the main language models, facilitating researchers and practitioners to select the most suitable ones in practice.

cs.DB↗

arXiv2021

Local Pair and Bundle Discovery over Co-Evolving Time Series

Time series exploration and mining has many applications across several industrial and scientific domains. In this paper, we consider the problem of detecting locally similar pairs and groups, called bundles, over co-evolving time series. These are pairs or groups of subsequences whose values do not differ by more than ε for at least delta consecutive timestamps, thus indicating common local patterns and trends. We first present a baseline algorithm that performs a sweep line scan across all timestamps to identify matches. Then, we propose a filter-verification technique that only examines candidate matches at judiciously chosen checkpoints across time. Specifically, we introduce two block scanning algorithms for discovering local pairs and bundles respectively, which leverage the potential of checkpoints to aggressively prune the search space. We experimentally evaluate our methods against real-world and synthetic datasets, demonstrating a speed-up in execution time by an order of magnitude over the baseline. This paper has been published in the 16th International Symposium on Spatial and Temporal Databases (SSTD19).

cs.DS↗

arXiv2021

Local Similarity Search on Geolocated Time Series Using Hybrid Indexing

Geolocated time series, i.e., time series associated with certain locations, abound in many modern applications. In this paper, we consider hybrid queries for retrieving geolocated time series based on filters that combine spatial distance and time series similarity. For the latter, unlike existing work, we allow filtering based on local similarity, which is computed based on subsequences rather than the entire length of each series, thus allowing the discovery of more fine-grained trends and patterns. To efficiently support such queries, we first leverage the state-of-the-art BTSR-tree index, which utilizes bounds over both the locations and the shapes of time series to prune the search space. Moreover, we propose optimizations that check at specific timestamps to identify candidate time series that may exceed the required local similarity threshold. To further increase pruning power, we introduce the SBTSR-tree index, an extension to BTSR-tree, which additionally segments the time series temporally, allowing the construction of tighter bounds. Our experimental results on several real-world datasets demonstrate that SBTSR-tree can provide answers much faster for all examined query types. This paper has been published in the 27th International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2019).

cs.DB↗

arXiv2021

Twin Subsequence Search in Time Series

We address the problem of subsequence search in time series using Chebyshev distance, to which we refer as twin subsequence search. We first show how existing time series indices can be extended to perform twin subsequence search. Then, we introduce TS-Index, a novel index tailored to this problem. Our experimental evaluation compares these approaches against real time series datasets, and demonstrates that TS-Index can retrieve twin subsequences much faster under various query conditions. This paper has been published in the 24th International Conference on Extending Database Technology (EDBT 2021).

cs.DS↗

arXiv2021

INODE: Building an End-to-End Data Exploration System in Practice [Extended Vision]

A full-fledged data exploration system must combine different access modalities with a powerful concept of guiding the user in the exploration process, by being reactive and anticipative both for data discovery and for data linking. Such systems are a real opportunity for our community to cater to users with different domain and data science expertise. We introduce INODE -- an end-to-end data exploration system -- that leverages, on the one hand, Machine Learning and, on the other hand, semantics for the purpose of Data Management (DM). Our vision is to develop a classic unified, comprehensive platform that provides extensive access to open datasets, and we demonstrate it in three significant use cases in the fields of Cancer Biomarker Reearch, Research and Innovation Policy Making, and Astrophysics. INODE offers sustainable services in (a) data modeling and linking, (b) integrated query processing using natural language, (c) guidance, and (d) data exploration through visualization, thus facilitating the user in discovering new insights. We demonstrate that our system is uniquely accessible to a wide range of users from larger scientific communities to the public. Finally, we briefly illustrate how this work paves the way for new research opportunities in DM.

cs.LG↗

arXiv2020

A Survey of Blocking and Filtering Techniques for Entity Resolution

Efficiency techniques are an integral part of Entity Resolution, since its infancy. In this survey, we organized the bulk of works in the field into Blocking, Filtering and hybrid techniques, facilitating their understanding and use. We also provided an in-dept coverage of each category, further classifying the corresponding works into novel sub-categories. Lately, the efficiency techniques have received more attention, due to the rise of Big Data. This includes large volumes of semi-structured data, which pose challenges not only to the scalability of efficiency techniques, but also to their core assumptions: the requirement of Blocking for schema knowledge and of Filtering for high similarity thresholds. The former led to the introduction of schema-agnostic Blocking in conjunction with Block Processing techniques, while the latter led to more relaxed criteria of similarity. Our survey covers these new fields in detail, putting in context all relevant works.

cs.DB↗

arXiv2014

A Buffer-aided Successive Opportunistic Relay Selection Scheme with Power Adaptation and Inter-Relay Interference Cancellation for Cooperative Diversity Systems

In this paper we consider a simple cooperative network consisting of a source, a destination and a cluster of decode-and-forward half-duplex relays. At each time-slot, the source and (possibly) one of the relays transmit a packet to another relay and the destination, respectively, resulting in inter-relay interference (IRI). In this work, with the aid of buffers at the relays, we mitigate the detrimental effect of IRI through interference cancellation. More specifically, we propose the min-power scheme that minimizes the total energy expenditure per time slot under an IRI cancellation scheme. Apart from minimizing the energy expenditure, the min-power selection scheme, also provides better throughput and lower outage probability than existing works in the literature. It is the first time that interference cancellation is combined with buffer-aided relays and power adaptation to mitigate the IRI and minimize the energy expenditure. The new relay selection policy is analyzed in terms of outage probability and diversity, by modeling the evolution of the relay buffers as a Markov Chain (MC). We construct the state transition matrix of the MC, and hence obtain the steady state with which we can characterize the outage probability. The proposed scheme outperforms relevant state-of-the-art relay selection schemes in terms of throughput, diversity and energy efficiency, as demonstrated via examples.

cs.IT↗