In recent years, deep learning has rapidly advanced in its capacity to model diverse data and tackle a wide range of applications. For instance, Large Language Models (LLMs) and graph neural networks (GNNs) have attracted considerable research attention due to their significant contributions to real-world problem-solving. The methodological advancements in LLMs and GNNs have led to promising results in areas such as social networks, question answering, search engines, recommendations, and content analysis. However, existing deep learning techniques often rely on the assumption of ample data and substantial computing resources during model training. This assumption can be impractical, especially given the high costs of data labeling and the large sizes of foundational models, particularly in resource-constrained settings like academic labs. Therefore, it is both challenging and crucial to explore these techniques in resource-constrained environments. Addressing these challenges is essential for the effective and efficient deployment of models in various real-world web systems and applications. Consequently, these fundamental issues have attracted increasing research interest in resource-efficient learning. The proposed international workshop on "Resource-Efficient Learning for the Web (RelWeb 2025)" will provide a great venue for academic researchers and industrial practitioners to share challenges, solutions, and future opportunities of resource-efficient learning.

The goal of this workshop is to create a venue to tackle the challenges that arise when modern machine learning techniques (e.g., deep learning) encounter resource limitations (e.g., scarce labeled data, constrained computing devices, low power/energy budget). The workshop will center on deep learning techniques utilized in data and web science applications, with a focus on efficient learning from three angles: data, model, and system/hardware. Specifically, the topics of this workshop include:

The workshop will be a half-day session comprising several invited talks from distinguished researchers in the field, spotlight lightning talks and a poster session where contributing paper presenters can discuss their work. Attendance is open to all registered participants.

Workshop papers must be written in English, in double-column format, and must adhere to the ACM template and formatting, at least 4 pages in length. (The same format as the main conference papers: https://www2025.thewebconf.org/research-tracks). Word users may use the Word Interim Template. Papers will be peer-reviewed and selected for spotlight and/or poster presentation. We also welcome recent and ongoing research studies submissions. We will also select the best paper award. Paper Submission site: https://cmt3.research.microsoft.com/RelWeb2025/Submission/Index