Related papers: An Efficient NAS-based Approach for Handling Imbal…

Graph is a prevalent data structure employed to represent the relationships between entities, frequently serving as a tool to depict and simulate numerous systems, such as molecules and social networks. However, real-world graphs usually…

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to…

One-shot Neural architecture search (One-shot NAS) has been proposed as a time-efficient approach to obtain optimal subnet architectures and weights under different complexity cases by training only once. However, the subnet performance…

Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search for each deployment specification of hardware or objective.…

The integration of communication networks and the Internet of Things (IoT) in Industrial Control Systems (ICSs) increases their vulnerability towards cyber-attacks, causing devastating outcomes. Traditional Intrusion Detection Systems…

Computing at the edge is increasingly important since a massive amount of data is generated. This poses challenges in transporting all that data to the remote data centers and cloud, where they can be processed and analyzed. On the other…

Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to…

With the rapid growth of memory and computing power, datasets are becoming increasingly complex and imbalanced. This is especially severe in the context of clinical data, where there may be one rare event for many cases in the majority…

Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain. Recent worksin neural architecture search (NAS), especially one-shot NAS, can aidtransfer learning by establishing sufficient…

Despite significant advancements in deep classification techniques and in-lab automatic optical inspection models for long-tailed or highly imbalanced data, applying these approaches to real-world IC defect classification tasks remains…

Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge. A major challenge of CIL arises when applying to real-world data characterized by non-uniform…

Classification data sets with skewed class proportions are called imbalanced. Class imbalance is a problem since most machine learning classification algorithms are built with an assumption of equal representation of all classes in the…

Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balanced and class-limited benchmarks, such as Microsoft COCO…

Methods in long-tail learning focus on improving performance for data-poor (rare) classes; however, performance for such classes remains much lower than performance for more data-rich (frequent) classes. Analyzing the predictions of…

Deep neural networks have recently drawn considerable attention to build and evaluate artificial learning models for perceptual tasks. Here, we present a study on the performance of the deep learning models to deal with global optimization…

Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms. Current studies on deep learning mainly focus on data sets with balanced class labels or unbalanced data, but with massive…

Mixed-integer programming (MIP) is a powerful paradigm for modeling and solving various important combinatorial optimization problems. Recently, learning-based approaches have shown a potential to speed up MIP solving via offline training…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints including latency, compute, energy consumption, etc. Neural…