Robi Polikar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Robi Polikar has a total of 304 co-authors. Here are the top co-authors by number of shared publications:
Gregory Ditzler
Department of Electrical & Computer Engineering, University of Arizona, Tucson, Arizona USA
20 shared publicationsGail Rosen
Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 USA
13 shared publications- Gail L. Rosen
Drexel University
12 shared publications Shreekanth Mandayam
10 shared publicationsL. Udpa
8 shared publicationsS. Mandayam
8 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 89-134
Evaluating Genomic Language Models: Experimental Validation, Multi-Omics Integration, and Ethical-Legal Challenges
- 2 July 2026
- Published by Springer Nature
- p. 89-134
Evaluating Genomic Language Models: Experimental Validation, Multi-Omics Integration, and Ethical-Legal Challenges
- Open Access
Improving genomic language model reliability under distribution shift
Transformer-based Genomic Language Models (GLMs) have achieved strong performance across diverse genomic prediction tasks. However, their tendency toward overconfident predictions—particularly on noisy or unfamiliar data—limits reliability. In genomics, where unknown species and novel variants are common, developing models robust to distribution shift is crucial for dependable predictions. Here, we analyze the impact of several common and novel uncertainty quantification (UQ) methods in the context of GLMs, evaluating their performance across diverse downstream genomic and metagenomic prediction tasks. Comparing model behavior on both in-distribution (ID) and out-of-distribution (OOD) data, we show that temperature scaling and epistemic neural networks are capable of improving classification reliability across multiple GLM architectures and domains. The software is available at: https://github.com/EESI/glm-epinet-pyt
Open AccessImproving genomic language model reliability under distribution shift
Transformer-based Genomic Language Models (GLMs) have achieved strong performance across diverse genomic prediction tasks. However, their tendency toward overconfident predictions—particularly on noisy or unfamiliar data—limits reliability. In genomics, where unknown species and novel variants are common, developing models robust to distribution shift is crucial for dependable predictions. Here, we analyze the impact of several common and novel uncertainty quantification (UQ) methods in the context of GLMs, evaluating their performance across diverse downstream genomic and metagenomic prediction tasks. Comparing model behavior on both in-distribution (ID) and out-of-distribution (OOD) data, we show that temperature scaling and epistemic neural networks are capable of improving classification reliability across multiple GLM architectures and domains. The software is available at: https://github.com/EESI/glm-epinet-pyt
- Open Access
- 11 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Translating the Language of Life
- 11 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessTranslating the Language of Life
- Open Access
- 11 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Large Language Models for Molecular Biology (LLMBio): Editorial
- 11 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessLarge Language Models for Molecular Biology (LLMBio): Editorial
- Open Access
- 19 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (1)
The Naïve Bayes classifier++ for metagenomic taxonomic classification—query evaluation
Motivation: This study examines the query performance of the NBC++ (Incremental Naive Bayes Classifier) program for variations in canonicality, k-mer size, databases, and input sample data size. We demonstrate that both NBC++ and Kraken2 are influenced by database depth, with macro measures improving as depth increases. However, fully capturing the diversity of life, especially viruses, remains a challenge. Results: NBC++ can competitively profile the superkingdom content of metagenomic samples using a small training database. NBC++ spends less time training and can use a fraction of the memory than Kraken2 but at the cost of long querying time. Major NBC++ enhancements include accommodating canonical k-mer storage (leading to significant storage savings) and adaptable and optimized memory allocation that accelerates query analysis and enables the software to be run on nearly any system. Additionally, the output now includes log-likelihood values for each training genome, providing users with valuable confidence information. Availability and implementation: Source code and Dockerfile are available at http://github.com/EESI/Naive_Bayes.
- 19 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (1)
Open AccessThe Naïve Bayes classifier++ for metagenomic taxonomic classification—query evaluation
Motivation: This study examines the query performance of the NBC++ (Incremental Naive Bayes Classifier) program for variations in canonicality, k-mer size, databases, and input sample data size. We demonstrate that both NBC++ and Kraken2 are influenced by database depth, with macro measures improving as depth increases. However, fully capturing the diversity of life, especially viruses, remains a challenge. Results: NBC++ can competitively profile the superkingdom content of metagenomic samples using a small training database. NBC++ spends less time training and can use a fraction of the memory than Kraken2 but at the cost of long querying time. Major NBC++ enhancements include accommodating canonical k-mer storage (leading to significant storage savings) and adaptable and optimized memory allocation that accelerates query analysis and enables the software to be run on nearly any system. Additionally, the output now includes log-likelihood values for each training genome, providing users with valuable confidence information. Availability and implementation: Source code and Dockerfile are available at http://github.com/EESI/Naive_Bayes.
- Open Access
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 126108-126121
Adversary Aware Continual Learning
Continual learning approaches are useful to help a model learn new information or new tasks sequentially, while also retaining the previously acquired information. However, such approaches are known to be extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific task or class at test time. In this work, we propose a novel defensive framework to counter such an attack and use the attacker’s primary strength – hiding the backdoor pattern by making it imperceptible to humans – against itself. To do so we train the model to learn a random perceptible pattern as decoy data during training with the deliberate intent to overpower the attacker’s imperceptible pattern. We demonstrate the effectiveness of the proposed defensive mechanism through various commonly used replay-based (both generative and exact replay-based) continual learning algorithms using continual learning benchmark variants of CIFAR-10, CIFAR-100, and MNIST datasets. We show that the proposed defensive framework considerably improves the robustness of continual learning algorithms without having any knowledge of the attacker’s target task, attacker’s target class, shape, size, and location of the attacker’s backdoor pattern. Moreover, our defensive framework does not depend on the underlying continual learning algorithm and does not rely on detecting the attack samples (to subsequently remove them from further consideration), but instead attempts to correctly classify even the attack samples and thus ensuring robustness in continual learning models. We refer to the proposed defensive framework as adversary aware continual learning (AACL).
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 126108-126121
Open AccessAdversary Aware Continual Learning
Continual learning approaches are useful to help a model learn new information or new tasks sequentially, while also retaining the previously acquired information. However, such approaches are known to be extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific task or class at test time. In this work, we propose a novel defensive framework to counter such an attack and use the attacker’s primary strength – hiding the backdoor pattern by making it imperceptible to humans – against itself. To do so we train the model to learn a random perceptible pattern as decoy data during training with the deliberate intent to overpower the attacker’s imperceptible pattern. We demonstrate the effectiveness of the proposed defensive mechanism through various commonly used replay-based (both generative and exact replay-based) continual learning algorithms using continual learning benchmark variants of CIFAR-10, CIFAR-100, and MNIST datasets. We show that the proposed defensive framework considerably improves the robustness of continual learning algorithms without having any knowledge of the attacker’s target task, attacker’s target class, shape, size, and location of the attacker’s backdoor pattern. Moreover, our defensive framework does not depend on the underlying continual learning algorithm and does not rely on detecting the attack samples (to subsequently remove them from further consideration), but instead attempts to correctly classify even the attack samples and thus ensuring robustness in continual learning models. We refer to the proposed defensive framework as adversary aware continual learning (AACL).
- Open Access
The Naïve Bayes Classifier++ for Metagenomic Taxonomic Classification – Query Evaluation
This study examines the query performance of the NBC++ (Incremental Naive Bayes Classifier) program for variations in canonicality, kmer size, databases, and input sample data size. NBC++ can successfully assess a wide range of superkingdoms using a small training database. We demonstrate that NBC++ and Kraken2 are affected by database depth with macro measures increasing with depth but that the full diversity of life, especially viruses, is still a challenge for these classifiers. NBC++ spends less time training but at the cost of long querying time. The major enhancements are to accommodate canonical k mer storage (with major storage savings), adaptable and optimized memory allocation that quickens the query analysis and allows the classifier to be run on almost any system, and enables output of the log-likelihood values against each training genome which provides users with valualbe confidence information.
Open AccessThe Naïve Bayes Classifier++ for Metagenomic Taxonomic Classification – Query Evaluation
This study examines the query performance of the NBC++ (Incremental Naive Bayes Classifier) program for variations in canonicality, kmer size, databases, and input sample data size. NBC++ can successfully assess a wide range of superkingdoms using a small training database. We demonstrate that NBC++ and Kraken2 are affected by database depth with macro measures increasing with depth but that the full diversity of life, especially viruses, is still a challenge for these classifiers. NBC++ spends less time training but at the cost of long querying time. The major enhancements are to accommodate canonical k mer storage (with major storage savings), adaptable and optimized memory allocation that quickens the query analysis and allows the classifier to be run on almost any system, and enables output of the log-likelihood values against each training genome which provides users with valualbe confidence information.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1132-1138
Semi-Supervised and Incremental Sequence Analysis for Taxonomic Classification
Metagenomic analysis is vital in determining what organisms are present in a microbial sample and why they are present. In this study, we explore the utility of MMseqs2, a bioinformatics pipeline, for taxonomic classification in metagenomics, focusing on 16S rRNA gene sequences. We evaluate the algorithm's performance in full dataset as well as batch-by-batch incremental processing, and more importantly, we add the capability of semi-supervised classification to this otherwise clustering only algorithm. Incremental updating is important because it allows seamless integration and processing of new data, whereas semi-supervised classification allows taxonomic identification of previously unknown organisms. We also evaluate the different clustering modes offered by MMseqs2, and compare MMseqs2 to our previously developed semi-supervised incremental algorithm SSI-VSEARCH. We show that MMseqs2's built-in clusterupdate function works well, and our semi-supervised classification capability adds new functionality to this bioinformatics processing pipeline.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1132-1138
Semi-Supervised and Incremental Sequence Analysis for Taxonomic Classification
Metagenomic analysis is vital in determining what organisms are present in a microbial sample and why they are present. In this study, we explore the utility of MMseqs2, a bioinformatics pipeline, for taxonomic classification in metagenomics, focusing on 16S rRNA gene sequences. We evaluate the algorithm's performance in full dataset as well as batch-by-batch incremental processing, and more importantly, we add the capability of semi-supervised classification to this otherwise clustering only algorithm. Incremental updating is important because it allows seamless integration and processing of new data, whereas semi-supervised classification allows taxonomic identification of previously unknown organisms. We also evaluate the different clustering modes offered by MMseqs2, and compare MMseqs2 to our previously developed semi-supervised incremental algorithm SSI-VSEARCH. We show that MMseqs2's built-in clusterupdate function works well, and our semi-supervised classification capability adds new functionality to this bioinformatics processing pipeline.
- 4 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1119-1126
Semi-supervised and Incremental VSEARCH for Metagenomic Classification
DNA Sequencing of microbial communities from en-vironmental samples generates large volumes of data, which can be analyzed using various bioinformatics pipelines. Unsupervised clustering algorithms are usually an early and critical step in an analysis pipeline, since much of such data are unlabeled, unstructured, or novel. However, curated reference databases that provide taxonomic label information are also increasing and growing, which can help in the classification of sequences, and not just clustering. In this contribution, we report on our progress in developing a semi-supervised approach for genomic clustering algorithms, such as U/VSEARCH. The primary contribution of this approach is the ability to recognize previously seen or unseen novel sequences using an incremental approach: for sequences whose examples were previously seen by the algorithm, the algorithm can predict a correct label. For previously unseen novel sequences, the algorithm assigns a temporary label and then updates that label with a permanent one if/when such a label is established in a future reference database. The incremental learning aspect of the proposed approach provides the additional benefit and capability to process the data continuously as new datasets become available. This functionality is notable as most sequence data processing platforms are static in nature, designed to run on a single batch of data, whose only other remedy to process additional data is to combine the new and old data and rerun the entire analysis. We report our promising preliminary results on an extended 16S rRNA database.
- 4 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1119-1126
Semi-supervised and Incremental VSEARCH for Metagenomic Classification
DNA Sequencing of microbial communities from en-vironmental samples generates large volumes of data, which can be analyzed using various bioinformatics pipelines. Unsupervised clustering algorithms are usually an early and critical step in an analysis pipeline, since much of such data are unlabeled, unstructured, or novel. However, curated reference databases that provide taxonomic label information are also increasing and growing, which can help in the classification of sequences, and not just clustering. In this contribution, we report on our progress in developing a semi-supervised approach for genomic clustering algorithms, such as U/VSEARCH. The primary contribution of this approach is the ability to recognize previously seen or unseen novel sequences using an incremental approach: for sequences whose examples were previously seen by the algorithm, the algorithm can predict a correct label. For previously unseen novel sequences, the algorithm assigns a temporary label and then updates that label with a permanent one if/when such a label is established in a future reference database. The incremental learning aspect of the proposed approach provides the additional benefit and capability to process the data continuously as new datasets become available. This functionality is notable as most sequence data processing platforms are static in nature, designed to run on a single batch of data, whose only other remedy to process additional data is to combine the new and old data and rerun the entire analysis. We report our promising preliminary results on an extended 16S rRNA database.
- Open Access
- 20 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Beyond Instance-Dependent Noise: Generalizing Noisy Label Modeling to Multiple Labeler Dependence
Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic; however, these models assume a single generative process for label noise across the entire dataset, which does not accurately capture the real-world labeling dynamics observed in modern dataset collection. We propose a new model of label noise, which we call “labeler-dependent noise (LDN).” LDN extends and generalizes instance-dependent noise to multiple labelers, based on the observation that modern datasets are typically constructed via distributed data gathering and labeling methods. Furthermore, inspired by recent research in social learning theory, we introduce a modular learning framework under our proposed labeler-dependent noise model called “labeler-aware learning”, in which each labeler is estimated and compared against the others during the learning process. Our experimental results demonstrate how previous state-of-the-art approaches for learning from noisy labels are unable to handle the general model of label noise, while our labeler-aware learning framework remains robust even when large fractions of labelers are spammers.
- 20 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessBeyond Instance-Dependent Noise: Generalizing Noisy Label Modeling to Multiple Labeler Dependence
Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic; however, these models assume a single generative process for label noise across the entire dataset, which does not accurately capture the real-world labeling dynamics observed in modern dataset collection. We propose a new model of label noise, which we call “labeler-dependent noise (LDN).” LDN extends and generalizes instance-dependent noise to multiple labelers, based on the observation that modern datasets are typically constructed via distributed data gathering and labeling methods. Furthermore, inspired by recent research in social learning theory, we introduce a modular learning framework under our proposed labeler-dependent noise model called “labeler-aware learning”, in which each labeler is estimated and compared against the others during the learning process. Our experimental results demonstrate how previous state-of-the-art approaches for learning from noisy labels are unable to handle the general model of label noise, while our labeler-aware learning framework remains robust even when large fractions of labelers are spammers.