Related papers: Salt-based autopeering for DLT-networks
We study a mismatch between the deep learning recommendation models' flat architecture, common distributed training paradigm and hierarchical data center topology. To address the associated inefficiencies, we propose Disaggregated…
We propose a flexible Semi-Automatic Labeling Tool (SALT) for general LiDAR point clouds with cross-scene adaptability and 4D consistency. Unlike recent approaches that rely on camera distillation, SALT operates directly on raw LiDAR data,…
Link prediction (LP) is an important problem in network science and machine learning research. The state-of-the-art LP methods are usually evaluated in a uniform setup, ignoring several factors associated with the data and application…
Analyzing data owned by several parties while achieving a good trade-off between utility and privacy is a key challenge in federated learning and analytics. In this work, we introduce a novel relaxation of local differential privacy (LDP)…
Modern network analysis often involves multi-layer network data in which the nodes are aligned, and the edges on each layer represent one of the multiple relations among the nodes. Current literature on multi-layer network data is mostly…
Infrastructure sharing is a widely discussed and implemented approach and is successfully adopted in telecommunications networks today. In practice, it is implemented through prior negotiated Service Level Agreements (SLAs) between the…
We consider the problem of reasoning about networked and layered control systems using assume-guarantee specifications. As these systems are formed by the interconnection of components that operate under various clocks, we introduce a new…
We propose a new approach, termed Hybrid DLT, to address a broad range of industrial use cases where certain properties of both private and public DLTs are valuable, while other properties may be unnecessary or detrimental. The Hybrid DLT…
Long-Tailed (LT) recognition has been widely studied to tackle the challenge of imbalanced data distributions in real-world applications. However, the design of neural architectures for LT settings has received limited attention, despite…
Delay Tolerant Networks (DTNs) are critical for emergency communication in highly dynamic and challenging scenarios characterized by intermittent connectivity, frequent disruptions, and unpredictable node mobility. While some protocols are…
Distributed Hash Tables (DHTs) are pivotal in numerous high-impact key-value applications built on distributed networked systems, offering a decentralized architecture that avoids single points of failure and improves data availability.…
Traditional public distributed ledgers have not been able to scale-out well and work efficiently. Sharding is deemed as a promising way to solve this problem. By partitioning all nodes into small committees and letting them work in…
The design of the forthcoming fifth generation (5G) system shall meet the severe requirement of managing an always increasing amount of traffic generated by both humans and machines, while guaranteeing data security. Among the enabling…
Distributed peer-to-peer systems are widely popular due to their decentralized nature, which ensures that no peer is critical for the functionality of the system. However, fully decentralized solutions are usually much harder to design, and…
Due to extreme chemical, thermal, and radiation environments, existing molten salt property databases lack the necessary experimental thermal properties of reactor-relevant salt compositions. Meanwhile, simulating these properties directly…
In Federated Learning (FL), common privacy-enhancing techniques, such as secure aggregation and distributed differential privacy, rely on the critical assumption of an honest majority among participants to withstand various attacks. In…
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly…
Differentiable solvers for the linear assignment problem (LAP) have attracted much research attention in recent years, which are usually embedded into learning frameworks as components. However, previous algorithms, with or without learning…
Decentralized machine learning (DML) supports collaborative training in large-scale networks with no central server. It is sensitive to the quality and reliability of inter-device communications that result in time-varying and stochastic…
Large-scale transformer models have become the de-facto architectures for various machine learning applications, e.g., CV and NLP. However, those large models also introduce prohibitive training costs. To mitigate this issue, we propose a…