相关论文: ProvLet: A Provenance Management Service for Long …
Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…
Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen…
In the world of science new technology have opened up the possibility to rely on advanced computational methods and models to conduct and produce scientific research. An important aspect of scientific and business workflows is provenance -…
In recent years, cyber attacks have become increasingly sophisticated and persistent. Detection and investigation based on the provenance graph can effectively mitigate cyber intrusion. However, in the long time span of defenses, the sheer…
Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the problem of identifying rare examples within a corpus of…
Whole-system data provenance provides deep insight into the processing of data on a system, including detecting data integrity attacks. The downside to systems that collect whole-system data provenance is the sheer volume of data that is…
Output-length prediction is important for efficient LLM serving, as it directly affects batching, memory reservation, and scheduling. For prompt-only length prediction, most existing methods use a one-shot sampled length as the label,…
Chest X-rays (CXRs) often display various diseases with disparate class frequencies, leading to a long-tailed, multi-label data distribution. In response to this challenge, we explore the Pruned MIMIC-CXR-LT dataset, a curated collection…
As an important type of cloud data, digital provenance is arousing increasing attention on improving system performance. Currently, provenance has been employed to provide cues regarding access control and to estimate data quality. However,…
Medical image classification has been widely adopted in medical image analysis. However, due to the difficulty of collecting and labeling data in the medical area, medical image datasets are usually highly-imbalanced. To address this…
Provenance has been thought of a mechanism to verify a workflow and to provide workflow reproducibility. This provenance of scientific workflows has been effectively carried out in Grid based scientific workflow systems. However, recent…
Providing an appropriate level of accessibility to and tracking of data or process elements in large volumes of medical data, is an essential requirement in the Big Data era. Researchers require systems that provide traceability of…
Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth analyses of these data are critical for hypothesis validation,…
Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common…
Long-term data-driven studies have become indispensable in many areas of science. Often, the data formats, structures and semantics of data change over time, the data sets evolve. Therefore, studies over several decades in particular have…
We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…
Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten synthesis procedures into text or ordered steps. We introduce MatProcBench, a…
Ensuring reproducibility of research is an integral part of good scientific practice. One way to support this is through provenance: information about research workflows from data gathering to researchers' sensemaking processes leading to…
Prompts to large language models (LLMs) have evolved beyond simple user questions. For LLMs to solve complex problems, today's practices are to include domain-specific instructions, illustration of tool usages, and/or long context such as…
Production Lines and Conveying Systems are the staple of modern manufacturing processes. Manufacturing efficiency is directly related to the efficiency of the means of production and conveying. Modelling in the industrial context has always…