Domain Large Language Models, Model Compression, Efficient Fine-Tuning

Task Literature Survey

Work Surveys joint compression and fine-tuning methods for LLMs, including pruning, quantization, knowledge distillation, low-rank approximation, PEFT, and alignment tuning, while organizing representative toolchains and open challenges for efficient deployment under memory, latency, and hardware constraints

Reference Survey on Joint Compression and Fine-Tuning of Large Language Models: Methods, Toolchains, and Open Challenges under Resource Constraints, Neurocomputing, 2026

Domain Continual Learning, Edge AI, Machine Learning Systems

Task Prompt-based Continual Learning under resource-constrained edge environments

Work Proposes a prompt-based continual learning framework that reduces training-time memory and computation

Reference Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge, CVPR, 2026

Domain Time Series Classification, Time-Sensitive Machine Learning

Task Time Series Classification with real-time constraint

Work Proposes a computationally efficient CNN architecture that aggregates features from all layers

Reference Efficient Cheap All-Layer Aggregation Network for Time-Sensitive Time Series Classification, Knowledge-Based Systems, 2026

Domain Continual Learning, Machine Learning Operation

Task Literature Survey

Work Reviews replay-based continual learning methods and conducts empirical validation on feasibility in diverse edge devices using a representative method

Reference Survey on Replay-Based Continual Learning and Empirical Validation on Feasibility in Diverse Edge Devices Using a Representative Method, Mathematics, 2025

Domain Data Preprocessing, Missing Value Imputation

Task Impute missing values in the given dataset

Work Neural network-based missing value imputation scheme using the chain strategy

Reference ChainImputer: A Neural Network-Based Iterative Imputation Method Using Cumulative Features, Symmetry, 2025

Domain Data Preprocessing, Multilabel Feature Selection

Task Essential feature subset identification relevant to multiple labels simultaneously

Work Memetic multilabel feature selection method incorporating the pruning of features and labels into the refinement process

Reference Memetic multilabel feature selection using pruned refinement process, Journal of Big Data, 2024

Domain Data Preprocessing, Unsupervised Feature Selection

Task Essential feature subset identification without the class label

Work Unsupervised feature selection method based on the information entropy approximation of the feature subset

Reference Unsupervised Feature Selection towards Pattern Discrimination Power, UAI, 2024

Domain Machine Learning, Continual Learning, Replay-based Class-Incremental Learning

Task Learn new classes continuously from a consistent data stream while retaining the knowledge of old classes to prevent catastrophic forgetting

Work Solution for mitigating representation shifts by incorporating asymmetric mixup training into the replay method

Reference MixER: Mixup-based Experience Replay for Online Class-Incremental Learning, IEEE Access, 2024

Domain Data Preprocessing, Multilabel Feature Selection

Task Essential feature subset identification relevant to multiple labels simultaneously

Work Memetic multilabel feature selection method incorporating the pruning of features and labels into the refinement process

Reference Memetic multilabel feature selection using pruned refinement process, Journal of Big Data, 2024

Domain Machine Learning Operation, Neural Network Design, Neural Architecture Search

Task Automated identification of optimal neural network for human activity recognition in mobile devices

Work Propose an efficient neural architecture search method based on a latency lookup table for human activity recognition

Reference Efficient Human Activity Recognition Using Lookup Table-Based Neural Architecture Search for Mobile Devices, IEEE Access, 2023

Domain Machine Learning Operation, Neural Network Design, Neural Architecture Search

Task Implement a machine learning operation platform for non-expert users

Work Devise a platform including multi-objective neural architecture search considering hardware specification

Reference Development of Integrated Development Framework that supports Automatic Neural Network Generation and Deployment optimized for Runtime Environment, Government Project, 2022-2025

Domain Data Preprocessing, Multilabel Feature Selection, All-Relevant Feature Selection

Task Identify all the features relevant to the given multiple labels

Work All-relevant multilabel feature selection method incorporating high-order interaction among labels

Reference Multilabel All-relevant Feature Selection using Lower Bounds of Conditional Mutual Information, Expert Systems with Applications, 2023

Domain Machine Learning Operation, Neural Network Design, Neural Architecture Search

Task Automated identification of optimal neural network for image classification

Work Propose a search method of group structure of group convolution in convolutional neural network

Reference Achieving an Optimal Group Structure in a Neural Architecture Search, Electronics Letters, 2022

Domain Data Preprocessing, Multilabel Feature Selection, Metaheuristic Search

Task Identify an optimal feature subset relevant to the given multiple labels

Work Memetic multilabel feature selection method based on novel communication process with hybridized filter

Reference Effective Memetic Algorithm for Feature Selection using Hybridization-based Communication, Expert Systems with Applications, 2022

Domain Machine Learning, Multilabel Learning, Multilabel Classification

Task Assign relevant labels to the input pattern

Work Generalize the standard naïve Bayes classifier to consider the dependencies among labels

Reference Multilabel Naive Bayes Classification Considering Label Dependence, Pattern Recognition Letters, 2020

Domain Data Preprocessing, Multilabel Feature Selection, Low-Order Approximation, Information Entropy

Task Identify an optimal feature subset relevant to the given multiple labels

Work Generalize a criterion derivation framework according to the degree of approximation

Reference Generalized Information-theoretic Criterion for Multi-label Feature Selection, IEEE Access, 2019

Domain Data Preprocessing, Multilabel Feature Selection, Metaheuristic Search

Task Identify an optimal feature subset relevant to the given multiple labels

Work Memetic multilabel feature selection method incorporating a filter specialized in text categorization

Reference Memetic Feature Selection for Multilabel Text Categorization using Label Frequency Difference, Information Sciences, 2019

Domain Data Preprocessing, Multilabel Feature Selection, Robustness, Large Label Set

Task Identify an optimal feature subset relevant to the given multiple labels

Work Propose a criterion for multilabel feature selection specialized in a large label set

Reference SCLS: Multi-label Feature Selection based on Scalable Criterion for Large Label Set, Pattern Recognition, 2017

Domain Data Preprocessing, Multilabel Feature Selection, Efficiency

Task Identify an optimal feature subset relevant to the given multiple labels

Work Propose an efficient multilabel feature selection considering dependencies among promising labels

Reference Fast Multi-label Feature Selection based on Information-theoretic Feature Ranking, Pattern Recognition, 2015

Domain Data Preprocessing, Multilabel Feature Selection, Metaheuristic Search

Task Identify an optimal feature subset relevant to the given multiple labels

Work Memetic multilabel feature selection method based on a multilabel feature filter with adaptive strength

Reference Memetic Feature Selection Algorithm for Multi-label Classification, Information Sciences, 2015

Domain Data Preprocessing, Multilabel Feature Selection, Label Dependency, Interaction Information

Task Identify an optimal feature subset relevant to the given multiple labels

Work Propose a multilabel feature selection considering the label dependency using the interaction information

Reference Mutual Information-based Multi-label Feature Selection using Interaction Information, Expert Systems with Applications, 2015

Domain Data Preprocessing, Multilabel Feature Selection, Label Dependency, Multivariate Mutual Information

Task Identify an optimal feature subset relevant to the given multiple labels

Work Propose a multilabel feature selection considering the label dependency using the multivariate mutual information

Reference Feature Selection for Multi-label Classification using Multivariate Mutual Information, Pattern Recognition Letters, 2013