This Research Topic is hosted by the organizing chairs of the “International Workshop on Resource-Efficient Learning for Knowledge Discovery”

Modern machine learning techniques, particularly deep learning, have demonstrated remarkable efficacy across numerous knowledge discovery and data mining applications. However, the advancement of many of these methods is often hindered by resource constraints, such as limited labelled data (data-level), small model size requirements in real-world computing platforms (model-level), and efficient mapping of computations to heterogeneous target hardware (system-level). Addressing these factors is crucial for deploying models effectively and efficiently across a broad spectrum of real-world systems, including large-scale social network analysis, recommendation systems, and real-time anomaly detection. Therefore, there is a critical need to develop efficient learning techniques to tackle the challenges posed by resource limitations, whether from data, model/algorithm, or system/hardware perspectives. The goal is to create a new collection of articles on this special topic to address the challenges that arise when modern machine learning techniques (e.g., deep learning) encounter resource limitations (e.g., scarce labelled data, constrained computing devices, low power/energy budget).

This Research Topic will focus on machine learning techniques for knowledge discovery and data science applications, emphasizing efficient learning from three angles: data, algorithm/model, and system/hardware. The topics of interest will include:

• Data-efficient learning: Self-supervised/unsupervised learning, semi/weakly-supervised learning, few-shot learning, and their applications to various data modalities (e.g., graph, user behaviour, text, web, image, time series) and data science problems (e.g., social media, healthcare, recommendation, finance, multimedia)

• Algorithm/model-efficient learning: Neural network pruning, quantization, acceleration, sparse learning, neural network compression, knowledge distillation, neural architecture search, and their applications on various data science problems.

• System/hardware-efficient learning: Neural network-hardware co-design, real-time and energy-efficient learning system design, hardware accelerators for machine learning, and their applications on various data science problems.

• Joint-efficient learning: Any kind of joint-efficient learning algorithms/methods (e.g., data-model joint learning, algorithm-hardware joint learning) and their application on various data science problems.

Are you interested in contributing a manuscript to this Research Topic?

Resource-Efficient Learning for Knowledge Discovery