Search Results

Stochastic Network Optimization (SNO) concerns scheduling in stochastic queueing systems and has been widely studied in network theory. Classical SNO algorithms require network conditions to be stationary w.r.t. time, which fails to capture the non-...

We introduce S-BDT: a novel (ε,δ)-differentially private distributed gradient boosted decision tree (GBDT) learner that improves the protection of single training data points (privacy) while achieving meaningful learning goals, such as accuracy or ...

Educational live streaming has become a complement to in-person teaching. While synchronous instructor-learner communication is useful, the technology-mediated nature of live streaming can obscure many interaction cues (e.g., learners' facial expressions ...

We present MIRACLE, a system for online, interpretable visual concept and video action recognition. Through a chat interface, users query the recognition system with an uploaded image or video. For images, MIRACLE returns concept predictions from its ...

The rapid evolution of multimedia and computer vision technologies requires adaptive visual model deployment strategies to effectively handle diverse tasks and varying environments. This work introduces AxiomVision, a novel framework that can guarantee ...

Online Continual Learning (OCL) aims at learning a model through a sequence of single-pass data, usually encountering the challenges of catastrophic forgetting both between different learning stages and within a stage. Currently, existing OCL methods ...

In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning based paradigm is ...

Bottleneck identification is a challenging task in network analysis, especially when the network is not fully specified. To address this task, we develop a unified online learning framework based on combinatorial semi-bandits that performs bottleneck ...

In the field of education, the commonly used one-size-fits-all gamification approach is unlikely to optimize student learning due to individual differences, raising the question of how gamification could be further enhanced to improve student learning. ...

World models for online learning in complex environments are increasingly essential, particularly in partially observable scenarios. Within this domain, biologically inspired models of temporal memory have emerged as a promising class of models. ...

Recommender systems have been widely used in e-commerce, and re-ranking models are playing an increasingly significant role in the domain, which leverages the inter-item influence and determines the final recommendation lists. Online learning methods ...

Customers can access hundreds of reviews for a single product in online marketplaces. Buyers often use reviews from other customers that share their type---such as height for clothing or skin type for skincare products---to estimate their values, which ...

The experience of distance learning during COVID-19 has become invaluable for continuing lifelong learning process under the war conditions in Ukraine. That experience was especially helpful for the survival of universities relocated from the ...

Electroencephalogram (EEG)-based Brain-Computer Interfaces (BCIs) have garnered significant interest across various domains, including rehabilitation and robotics. Despite advancements in neural network-based EEG decoding, maintaining performance across ...

Distance learning is one of the technology-wise challenges in the education field. Remote learning provides the advantage of encouraging anyone to join from worldwide. In order to make education sustainable, understanding students' concentration in ...

Hierarchical Inference (HI) has emerged as a promising approach for efficient distributed inference between end devices deployed with small pre-trained Deep Learning (DL) models and edge/cloud servers running large DL models. Under HI, a device uses the ...

Scheduling in multi-channel wireless communication system presents formidable challenges in effectively allocating resources. To address these challenges, we investigate a multi-resource restless matching bandit (MR-RMB) model for heterogeneous resource ...

This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before generating an outcome. Each agent can only control its own action and learn ...

Instructors in computer science classes often need to decide between having students use real programming tools to provide practical experience and presenting them with simpler educational interfaces to reduce their cognitive load. Our work ...$\mathrm{}$$\mathrm{}$

Pathology is a fundamental discipline of basic medicine, and pathological diagnosis is the "golden standard" in clinical medicine, serving as the basis for clinical doctors to formulate treatment plans. Pathological knowledge can be divided into explicit ...