Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2024
Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks
Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS), Volume 8, Issue 3Article No.: 31, Pages 1–48https://doi.org/10.1145/3700413Stochastic 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-...
S-BDT: Distributed Differentially Private Boosted Decision Trees
CCS '24: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications SecurityPages 288–302https://doi.org/10.1145/3658644.3690301We 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 ...
- research-articleNovember 2024
EduLive: Re-Creating Cues for Instructor-Learners Interaction in Educational Live Streams with Learners' Transcript-Based Annotations
Proceedings of the ACM on Human-Computer Interaction (PACMHCI), Volume 8, Issue CSCW2Article No.: 421, Pages 1–33https://doi.org/10.1145/3686960Educational 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 ...
- abstractOctober 2024
MIRACLE: An Online, Explainable Multimodal Interactive Concept Learning System
- Ansel Blume,
- Khanh Duy Nguyen,
- Zhenhailong Wang,
- Yangyi Chen,
- Michal Shlapentokh-Rothman,
- Xiaomeng Jin,
- Jeonghwan Kim,
- Zhen Zhu,
- Jiateng Liu,
- Kuan-Hao Huang,
- Mankeerat Sidhu,
- Xuanming Zhang,
- Vivian Liu,
- Raunak Sinha,
- Te-Lin Wu,
- Abhay Zala,
- Elias Stengel-Eskin,
- Da Yin,
- Yao Xiao,
- Utkarsh Mall,
- Zhou Yu,
- Kai-Wei Chang,
- Camille Cobb,
- Karrie Karahalios,
- Lydia Chilton,
- Mohit Bansal,
- Nanyun Peng,
- Carl Vondrick,
- Derek Hoiem,
- Heng Ji
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 11252–11254https://doi.org/10.1145/3664647.3684993We 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 ...
- research-articleOctober 2024
AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 7229–7238https://doi.org/10.1145/3664647.3681269The 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 ...
-
- research-articleOctober 2024
Progressive Prototype Evolving for Dual-Forgetting Mitigation in Non-Exemplar Online Continual Learning
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 2477–2486https://doi.org/10.1145/3664647.3681234Online 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 ...
- research-articleOctober 2024
PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 8691–8700https://doi.org/10.1145/3664647.3681176In 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 ...
- short-paperOctober 2024
A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 3782–3786https://doi.org/10.1145/3627673.3679867Bottleneck 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 ...
- research-articleOctober 2024
Investigating the Implementation and Effects of Personalized Gamification in Education
CHI PLAY Companion '24: Companion Proceedings of the 2024 Annual Symposium on Computer-Human Interaction in PlayPages 454–457https://doi.org/10.1145/3665463.3678846In 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. ...
- ArticleOctober 2024
Soft Adaptive Segments for Bio-Inspired Temporal Memory
Hybrid Artificial Intelligent SystemsPages 202–213https://doi.org/10.1007/978-3-031-74183-8_17AbstractWorld 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. ...
- short-paperOctober 2024
Do Not Wait: Learning Re-Ranking Model Without User Feedback At Serving Time in E-Commerce
RecSys '24: Proceedings of the 18th ACM Conference on Recommender SystemsPages 896–901https://doi.org/10.1145/3640457.3688165Recommender 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 ...
- research-articleOctober 2024
Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty
ACM SIGecom Exchanges (SIGECOM), Volume 22, Issue 1Pages 74–82https://doi.org/10.1145/3699824.3699830Customers 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 ...
- ArticleOctober 2024
Distance Teaching of Mathematical and Computer Disciplines During the War in Ukraine
Creative Mathematical Sciences CommunicationPages 205–214https://doi.org/10.1007/978-3-031-73257-7_17AbstractThe 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 ...
- short-paperOctober 2024
On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface
ISWC '24: Proceedings of the 2024 ACM International Symposium on Wearable ComputersPages 9–16https://doi.org/10.1145/3675095.3676607Electroencephalogram (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 ...
- posterOctober 2024
Concentration Estimation in Online Video Lecture Using Multimodal Sensors
UbiComp '24: Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous ComputingPages 71–75https://doi.org/10.1145/3675094.3677587Distance 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 ...
- research-articleOctober 2024
Regret Bounds for Online Learning for Hierarchical Inference
MobiHoc '24: Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile ComputingPages 281–290https://doi.org/10.1145/3641512.3686392Hierarchical 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 ...
- research-articleOctober 2024
Deep Index Policy for Multi-Resource Restless Matching Bandit and Its Application in Multi-Channel Scheduling
MobiHoc '24: Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile ComputingPages 71–80https://doi.org/10.1145/3641512.3686381Scheduling 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 ...
- research-articleOctober 2024
Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback
MobiHoc '24: Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile ComputingPages 41–50https://doi.org/10.1145/3641512.3686369This 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 ...
- research-articleDecember 2024
Research on Development of Pathological Knowledge Management Platform
WSSE '24: Proceedings of the 2024 The 6th World Symposium on Software Engineering (WSSE)Pages 79–84https://doi.org/10.1145/3698062.3698073Pathology 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 ...