Related papers: An Adaptive Hotspot-Aware Index for Oscillating Wr…

Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant…

Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably…

Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a…

Anomaly detection to recognize unusual events in large scale systems in a time sensitive manner is critical in many industries, eg. bank fraud, enterprise systems, medical alerts, etc. Large-scale systems often grow in size and complexity…

Low-rank adaptation (LoRA) has shifted the paradigm of adapting pre-trained Vision Transformers (ViT), achieving great efficiency by updating only a subset of tailored parameters to approximate weight updates. However, the multi-head design…

The recent proposal of learned index structures opens up a new perspective on how traditional range indexes can be optimized. However, the current learned indexes assume the data distribution is relatively static and the access pattern is…

We introduce HTAD, a novel model for diagnosis prediction using Electronic Health Records (EHR) represented as Heterogeneous Information Networks. Recent studies on modeling EHR have shown success in automatically learning representations…

Multi-task learning (MTL) aims to enhance the performance and efficiency of machine learning models by simultaneously training them on multiple tasks. However, MTL research faces two challenges: 1) effectively modeling the relationships…

Humans have the ability to adapt the type of information they use, the procedure they employ, and the amount of time they spend when solving problems. However, most standard neural networks have a fixed function type and computation budget…

Hierarchical reinforcement learning (HRL) helps address large-scale and sparse reward issues in reinforcement learning. In HRL, the policy model has an inner representation structured in levels. With this structure, the reinforcement…

Heterogeneous information networks (HINs) represent different types of entities and relationships between them. Exploring, analysing, and extracting knowledge from such networks relies on metapath queries that identify pairs of entities…

With the emergence of heterogeneous hardware paving the way for the post-Moore era, it is of high importance to adapt the runtime scheduling to the platform's heterogeneity. To enhance adaptive and responsive scheduling, we introduce a…

Although many updatable learned indexes have been proposed in recent years, whether they can outperform traditional approaches on disk remains unknown. In this study, we revisit and implement four state-of-the-art updatable learned indexes…

Multi-task learning (MTL) aims at improving the generalization performance of several related tasks by leveraging useful information contained in them. However, in industrial scenarios, interpretability is always demanded, and the data of…

With the rapid advancement of mobile networks and the widespread use of mobile devices, spatial crowdsourcing, which involves assigning location-based tasks to mobile workers, has gained significant attention. However, most existing…

Data streams are ubiquitous in modern business and society. In practice, data streams may evolve over time and cannot be stored indefinitely. Effective and transparent machine learning on data streams is thus often challenging. Hoeffding…

Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation…

Discussions about the choice of a tree hash mode of operation for a standardization have recently been undertaken. It appears that a single tree mode cannot address adequately all possible uses and specifications of a system. In this paper,…

To meet the demands of wireless sensor networks (WSNs) where data are usually aggregated at a single source prior to transmitting to any distant user, there is a need to establish a tree structure inside to aggregate data. In this paper, an…

The growth of compute-intensive AI tasks highlights the need to mitigate the processing costs and improve performance and energy efficiency. This necessitates the integration of intelligent agents as architectural adaptation supervisors…