Author name cluster

Lucian Popa

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

1 author row

AAAI Conference 2026 Conference Paper

Constraint-Guided Clustering for Identifying in-Vehicle Electronic Control Units from Voltage Data

Bogdan Groza
Patricia Iosif
Lucian Popa

Identifying in-vehicle electronic control units based on voltage characteristics has been the subject of extensive research in cybersecurity. However, the results reported so far generally depend on restricted datasets and supervised learning. In this work, we show that clustering, i.e., unsupervised learning, of voltage characteristics, is in fact more challenging when done on a larger pool of electronic control units as several out-of-the-box clustering methods and metrics will fail to determine the correct number of clusters when exerted over a large dataset. To overcome this issue, we propose a new methodology that takes advantage of domain-specific constraints, which guide the search toward the correct number of electronic control units in a car, or even in a larger pool of units from several cars. We introduce two new metrics: correctness, which measures the success ratio with respect to the constraints, and divergence, which measures the consistency of the clustering, and show that they provide a strong indication for the optimal number of clusters. In this specific context, both metrics prove to be more reliable than the widely used Silhouette score, Davies-Bouldin and Calinski-Harabas indexes. We successfully test our methodology on the largest dataset available today for in-vehicle voltage characteristics and discover new insights regarding the number of devices.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Activated LoRA: Fine-tuned LLMs for Intrinsics

Kristjan Greenewald
Luis Lastras
Thomas Parnell
Vraj Shah
Lucian Popa
Giulio Zizzo
Chulaka Gunasekara
Ambrish Rawat

Low-Rank Adaptation (LoRA) has emerged as a highly efficient framework for finetuning the weights of large foundation models, and has become the go-to method for data-driven customization of LLMs. Despite the promise of highly customized behaviors and capabilities, switching between relevant LoRAs in a multiturn setting is inefficient, as the key-value (KV) cache of the entire turn history must be recomputed with the LoRA weights before generation can begin. To address this problem, we propose Activated LoRA (aLoRA), an adapter architecture which modifies the LoRA framework to only adapt weights for the tokens in the sequence after the aLoRA is invoked. This change crucially allows aLoRA to accept the base model's KV cache of the input string, meaning that aLoRA can be instantly activated whenever needed in a chain without recomputing the prior keys and values. This enables building what we call intrinsics, i. e. specialized models invoked to perform well-defined operations on portions of an input chain or conversation that otherwise uses the base model by default. We train a set of aLoRA-based intrinsics models, demonstrating competitive accuracy with standard LoRA while significantly improving inference efficiency. We contributed our Activated LoRA implementation to the Huggingface PEFT library.

PDF Details

AAAI Conference 2024 Conference Paper

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

Yu Zhang
Yunyi Zhang
Yanzhen Shen
Yu Deng
Lucian Popa
Larisa Shwartz
ChengXiang Zhai
Jiawei Han

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering domains (e.g., software engineering and security) can be time-consuming and costly, without mentioning the domain gaps between training and inference data if the model needs to be applied to confidential datasets. In this paper, we study the task of seed-guided fine-grained entity typing in science and engineering domains, which takes the name and a few seed entities for each entity type as the only supervision and aims to classify new entity mentions into both seen and unseen types (i.e., those without seed entities). To solve this problem, we propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus using the contextualized representations of pre-trained language models. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types. Extensive experiments on two datasets covering four domains demonstrate the effectiveness of SEType in comparison with various baselines. Code and data are available at: https://github.com/yuzhimanhua/SEType.

PDF Details DOI

KR Conference 2023 Conference Paper

A Framework for Combining Entity Resolution and Query Answering in Knowledge Bases

Ronald Fagin
Phokion G. Kolaitis
Domenico Lembo
Lucian Popa
Federico Scafoglieri

We propose a new framework for combining entity resolution and query answering in knowledge bases (KBs) with tuple-generating dependencies (tgds) and equality-generating dependencies (egds) as rules. We define the semantics of the KB in terms of special instances that involve equivalence classes of entities and sets of values. Intuitively, the former collect all entities denoting the same real-world object, while the latter collect all alternative values for an attribute. This approach allows us to both resolve entities and bypass possible inconsistencies in the data. We then design a chase procedure that is tailored to this new framework and has the feature that it never fails; moreover, when the chase procedure terminates, it produces a universal solution, which in turn can be used to obtain the certain answers to conjunctive queries. We finally discuss challenges arising when the chase does not terminate.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning

Krishnateja Killamsetty
Guttu Sai Abhishek
Aakriti Lnu
Ganesh Ramakrishnan
Alexandre Evfimievski
Lucian Popa
Rishabh Iyer

Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter configuration, even with state-of-the-art (SOTA) hyper-parameter optimization (HPO) algorithms, can be time-consuming, requiring multiple training runs over the entire datasetfor different possible sets of hyper-parameters. Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us to find the optimal hyper-parameter configuration significantly faster. In this work, we propose AUTOMATA, a gradient-based subset selection framework for hyper-parameter tuning. We empirically evaluate the effectiveness of AUTOMATA in hyper-parameter tuning through several experiments on real-world datasets in the text, vision, and tabular domains. Our experiments show that using gradient-based data subsets for hyper-parameter tuning achieves significantly faster turnaround times and speedups of 3×-30× while achieving comparable performance to the hyper-parameters found using the entire dataset.

PDF Details

AAAI Conference 2021 System Paper

AutoText: An End-to-End AutoAI Framework for Text

Arunima Chaudhary
Alayt Issak
Kiran Kate
Yannis Katsis
Abel Valente
Dakuo Wang
Alexandre Evfimievski
Sairam Gurajada

Building models for natural language processing (NLP) tasks remains a daunting task for many, requiring significant technical expertise, efforts, and resources. In this demonstration, we present AutoText, an end-to-end AutoAI framework for text, to lower the barrier of entry in building NLP models. AutoText combines state-of-the-art AutoAI optimization techniques and learning algorithms for NLP tasks into a single extensible framework. Through its simple, yet powerful UI, non-AI experts (e. g. , domain experts) can quickly generate performant NLP models with support to both control (e. g. , via specifying constraints) and understand learned models.

PDF Details

AAAI Conference 2020 System Paper

PARTNER: Human-in-the-Loop Entity Name Understanding with Deep Learning

Kun Qian
Poornima Chozhiyath Raman
Yunyao Li
Lucian Popa

Entity name disambiguation is an important task for many text-based AI tasks. Entity names usually have internal semantic structures that are useful for resolving different variations of the same entity. We present, PARTNER, a deep learning-based interactive system for entity name understanding. Powered by effective active learning and weak supervision, PARTNER can learn deep learning-based models for identifying entity name structure with low human effort. PARTNER also allows the user to design complex normalization and variant generation functions without coding skills.

PDF Details

AAAI Conference 2019 Conference Paper

Knowledge Refinement via Rule Selection

Phokion G. Kolaitis
Lucian Popa
Kun Qian

In several different applications, including data transformation and entity resolution, rules are used to capture aspects of knowledge about the application at hand. Often, a large set of such rules is generated automatically or semi-automatically, and the challenge is to refine the encapsulated knowledge by selecting a subset of rules based on the expected operational behavior of the rules on available data. In this paper, we carry out a systematic complexity-theoretic investigation of the following rule selection problem: given a set of rules specified by Horn formulas, and a pair of an input database and an output database, find a subset of the rules that minimizes the total error, that is, the number of false positive and false negative errors arising from the selected rules. We first establish computational hardness results for the decision problems underlying this minimization problem, as well as upper and lower bounds for its approximability. We then investigate a bi-objective optimization version of the rule selection problem in which both the total error and the size of the selected rules are taken into account. We show that testing for membership in the Pareto front of this bi-objective optimization problem is DP-complete. Finally, we show that a similar DP-completeness result holds for a bi-level optimization version of the rule selection problem, where one minimizes first the total error and then the size.

PDF Details

TCS Journal 2005 Journal Article

Data exchange: semantics and query answering

Ronald Fagin
Phokion G. Kolaitis
Renée J. Miller
Lucian Popa

Data exchange is the problem of taking data structured under a source schema and creating an instance of a target schema that reflects the source data as accurately as possible. In this paper, we address foundational and algorithmic issues related to the semantics of data exchange and to the query answering problem in the context of data exchange. These issues arise because, given a source instance, there may be many target instances that satisfy the constraints of the data exchange problem. We give an algebraic specification that selects, among all solutions to the data exchange problem, a special class of solutions that we call universal. We show that a universal solution has no more and no less data than required for data exchange and that it represents the entire space of possible solutions. We then identify fairly general, yet practical, conditions that guarantee the existence of a universal solution and yield algorithms to compute a canonical universal solution efficiently. We adopt the notion of the “certain answers” in indefinite databases for the semantics for query answering in data exchange. We investigate the computational complexity of computing the certain answers in this context and also address other algorithmic issues that arise in data exchange. In particular, we study the problem of computing the certain answers of target queries by simply evaluating them on a canonical universal solution, and we explore the boundary of what queries can and cannot be answered this way, in a data exchange setting.

Details DOI