Related papers: The StoreGate: a Data Model for the Atlas Software…
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data,…
In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data…
The POOL project is the common persistency framework for the LHC experiments to store petabytes of experiment data and metadata in a distributed and grid enabled way. POOL is a hybrid event store consisting of a data streaming layer and a…
We describe the LHCb detector simulation application (Gauss) based on the Geant4 toolkit. The application is built using the Gaudi software framework, which is used for all event-processing applications in the LHCb experiment. The existence…
We introduce bindings that enable the convenient, efficient, and reliable use of software modules of CGAL (Computational Geometry Algorithm Library), which are written in C++, from within code written in Python. There are different tools…
A working implementation of nested transactions has been produced for LOCUS, an integrated distributed operating system which provides a high degree of network transparency. Several aspects of our mechanism are novel. First, the mechanism…
Transfer learning is a crucial technique for handling a small amount of data that is potentially related to other abundant data. However, most of the existing methods are focused on classification tasks using images and language datasets.…
One of the purposes of Big Data systems is to support analysis of data gathered from heterogeneous data sources. Since data warehouses have been used for several decades to achieve the same goal, they could be leveraged also to provide…
Feature selection, dimension selection, and embedding compression are fundamental techniques for improving efficiency and generalization in deep recommender systems. Although conceptually related, these problems are typically studied in…
Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…
Traditionally, HENP computing facilities have been open facilities that are accessed in many different ways by users that are both internal and external to the facility. However, the need to protect the facility from cybersecurity threats…
Flexible and performant Persistency Service is a necessary component of any HEP Software Framework. The building of a modular, non-intrusive and performant persistency component have been shown to be very difficult task. In the past, it was…
Matrix completion is a classic problem underlying recommender systems. It is traditionally tackled with matrix factorization. Recently, deep learning based methods, especially graph neural networks, have made impressive progress on this…
Data analytics applications transform raw input data into analytics-specific data structures before performing analytics. Unfortunately, such data ingestion step is often more expensive than analytics. In addition, various types of NVRAM…
Machine learning architectures, including transformers and recurrent neural networks (RNNs) have revolutionized forecasting in applications ranging from text processing to extreme weather. Notably, advanced network architectures, tuned for…
The agent harness, the system layer comprising prompts, tools, memory, and orchestration logic that surrounds the model, has emerged as the central engineering abstraction for LLMbased agents. Yet harness design remains ad hoc, with no…
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.…
Data sharing is essential in the numerical simulations research. We introduce a data repository, DataVault, that is designed for data sharing, search and analysis. A comparative study of existing repositories is performed to analyze…
Real world graphs are often dynamic and evolve over time. It is crucial for storing and querying graph evolution in graph databases. However, existing works either suffer from high storage overhead or lack efficient temporal query support,…
As continuous learning based video analytics continue to evolve, the role of efficient edge servers in efficiently managing vast and dynamic datasets is becoming increasingly crucial. Unlike their compute architecture, storage and archival…