Filters








314 Hits in 7.1 sec

Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks [article]

Gabriel de Souza Pereira Moreira, Dietmar Jannach, Adilson Marques da Cunha
2019 arXiv   pre-print
Our results confirm the benefits of considering additional types of information, including article popularity and recency, in the proposed way, resulting in significantly higher recommendation accuracy  ...  reader's context, or the recency or popularity of an article.  ...  Acknowledgements We would like to thank Globo.com for sharing a dataset to make this investigation possible, and to CI&T for providing support and an R&D environment for this research.  ... 
arXiv:1904.10367v1 fatcat:sa66nqhy3nhxnkqvno4ttp3oie

Deep learning-based edge caching for multi-cluster heterogeneous networks

Jiachen Yang, Jipeng Zhang, Chaofan Ma, Huihui Wang, Juping Zhang, Gan Zheng
2019 Neural computing & applications (Print)  
More specifically, we propose the multilayer real-time predictive analytics based on historical temporal information (frequency, recency, betweenness) and spatial information (dynamic clustering, similarity  ...  Mobile opportunistic caching at the edges is expected to be an effective solution for bringing content closer and improve the quality of service for mobile users.  ...  are both necessary to address multi-user data communications in dynamic fragmented and sparse topologies.  ... 
doi:10.1007/s00521-019-04040-z fatcat:knxtp5xe4jfyzk5cfx67oj4qje

WADE

Zhe Wang, Shuchang Shan, Ting Cao, Junli Gu, Yi Xu, Shuai Mu, Yuan Xie, Daniel A. Jiménez
2013 ACM Transactions on Architecture and Code Optimization (TACO)  
However, most prior work focuses on optimization techniques for NVM-based main memory itself, with little attention paid to cache management policies for the Last-Level Cache (LLC).  ...  It yields a geometric mean speedup of 5.1% for single-thread applications and 7.6% for multicore workloads.  ...  The insight of the technique is that frequent writeback data is also highly reused dirty data in the LLC.  ... 
doi:10.1145/2555289.2555307 fatcat:apfkp5ba2rfsfc5w7beq3ctaeq

WADE

Zhe Wang, Shuchang Shan, Ting Cao, Junli Gu, Yi Xu, Shuai Mu, Yuan Xie, Daniel A. Jiménez
2013 ACM Transactions on Architecture and Code Optimization (TACO)  
However, most prior work focuses on optimization techniques for NVM-based main memory itself, with little attention paid to cache management policies for the Last-Level Cache (LLC).  ...  It yields a geometric mean speedup of 5.1% for single-thread applications and 7.6% for multicore workloads.  ...  The insight of the technique is that frequent writeback data is also highly reused dirty data in the LLC.  ... 
doi:10.1145/2541228.2555307 fatcat:pwjaffpvqzgozog57ncdktgdjm

Time Series Prediction Using Deep Learning Methods in Healthcare

Mohammad Amin Morid, Olivia R. Liu Sheng, Joseph Dunbar
2022 ACM Transactions on Management Information Systems  
inclusion, attention mechanisms, interpretation, incorporation of medical ontologies, learning strategies, and scalability.  ...  The high-dimensional nature of healthcare data necessitates labor-intensive and time-consuming processes when selecting an appropriate set of features for each new task.  ...  Combining our findings, a sequence representation with a pretrained embedding layer is highly recommended for learning tasks on EHR data, while a matrix representation seems to be more effective for AC  ... 
doi:10.1145/3531326 fatcat:w2mml2pc2fdnpazjkpi2hqpvgq

An overview on the exploitation of time in collaborative filtering

João Vinagre, Alípio Mário Jorge, João Gama
2015 Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery  
Classic Collaborative Filtering (CF) algorithms rely on the assumption that data are static and we usually disregard the temporal effects in natural user-generated data.  ...  These temporal effects include user preference drifts and shifts, seasonal effects, new users and items entering the system -and old ones leaving -, user and item activity rate fluctuations and other similar  ...  The distribution of the metrics naturally follows the type of data: precision, recall, F1, DCG and MAP for positive-only data, and RMSE and MAE for ratings.  ... 
doi:10.1002/widm.1160 fatcat:eobngsqsrfer5nrkfznkcvqqqe

Measuring, modelling and Integrating Time-varying Video Quality in End-to-End Multimedia Service Delivery: A Review and Open Challenges

Chaminda T.E.R. Hewage, Arslan Ahmad, Thanuja Mallikarachchi, Nabajeet Barman, Maria G. Martini
2022 IEEE Access  
for global quality measurements, and Continuous Time-Varying Quality (CTVQ) models; 2) Future Challenges and Directions -we investigate ten major research challenges and future directions based on the  ...  state-of-the-art for QoE modelling, QoE-aware encoding/decoding and QoE monitoring/management of multimedia streaming in next-generation networks.  ...  The QoE management in 6G and beyond networks using network enabling technologies promises network programmability, scalability, agility, distributive computing, dynamic resource optimization and automation  ... 
doi:10.1109/access.2022.3180491 fatcat:4mcyfjfd2zhrzl7qytj7vwkwsm

Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference [article]

William Held, Dan Iter, Dan Jurafsky
2021 arXiv   pre-print
Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora.  ...  We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters  ...  Luu of Sunshine Products for logistics assistance, and to the anonymous reviewers and the Stanford NLP group for their helpful feedback.  ... 
arXiv:2110.05362v1 fatcat:oc5o6e3j7ncf3jwnuc4fio3424

USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity [article]

Amila Silva, Shanika Karunasekera, Christopher Leckie, Ling Luo
2019 arXiv   pre-print
Building spatiotemporal activity models for people's activities in urban spaces is important for understanding the ever-increasing complexity of urban dynamics.  ...  State-of-the-art methods for this task embed different modalities (location, time, and text) of GTSM records into a single embedding space.  ...  Answering such questions is challenging due to the highly complex spatiotemporal dynamics in cities.  ... 
arXiv:1910.10335v1 fatcat:qkcof354dbcmjbg6y6cbgf4mnu

The Future Internet of Things: Secure, Efficient, and Model-Based

Joshua E. Siegel, Sumeet Kumar, Sanjay E. Sarma
2018 IEEE Internet of Things Journal  
A solution jointly addressing security, efficiency, privacy, and scalability is needed to support continued expansion.  ...  Finally, we consider future opportunities for this architecture to reduce technical, economic, and sentiment barriers to the adoption of the IoT.  ...  As applications join and leave the system, the sampling rate is dynamically recalculated to ensure scalability and efficiency.  ... 
doi:10.1109/jiot.2017.2755620 fatcat:ucsemja72nglbfods6ani6epgq

CHAMELEON: A Deep Learning Meta-Architecture for News Recommender Systems [Phd. Thesis] [article]

Gabriel de Souza Pereira Moreira
2019 arXiv   pre-print
News RS are aimed to personalize users experiences and help them discover relevant articles from a large and dynamic search space.  ...  A method is proposed for a realistic temporal offline evaluation of such task, replaying the stream of user clicks and fresh articles being continuously published in a news portal.  ...  The Article Content Embeddings are L2-normalized, so that each embedding has zero mean and unit size. The dynamic features for novelty and recency were normalized based on a sliding CHAPTER 5.  ... 
arXiv:2001.04831v1 fatcat:x2k3u26i4jebzjlesswnncfepq

Energy efficient GPU transactional memory via space-time optimizations

Wilson W. L. Fung, Tor M. Aamodt
2013 Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture - MICRO-46  
One major, non-trivial effort/risk is to expose the available parallelism in the application as 1000s of concurrent threads without introducing data races or deadlocks via fine-grained data synchronization  ...  However, employing GPUs for applications with irregular parallelism tends to be a risky process, involving significant effort from the programmer.  ...  ACKNOWLEDGEMENTS We thank Henry Wong, Andrew Boktor and the anonymous reviewers for their valuable comments.  ... 
doi:10.1145/2540708.2540743 dblp:conf/micro/FungA13 fatcat:l6qqlhuntzdydleecyvjldd3zy

Static Type Analysis by Abstract Interpretation of Python Programs

Raphaël Monat, Abdelraouf Ouadjaout, Antoine Miné, Tobias Pape, Robert Hirschfeld
2020 European Conference on Object-Oriented Programming  
Python is an increasingly popular dynamic programming language, particularly used in the scientific community and well-known for its powerful and permissive high-level syntax.  ...  We present a flow- and context-sensitive analysis with special domains to support containers (such as lists) and infer type equalities (allowing it to express parametric polymorphism).  ...  Acknowledgements We thank the anonymous reviewers for their valuable comments and feedback. Cons ist en t * Comple te  ... 
doi:10.4230/lipics.ecoop.2020.17 dblp:conf/ecoop/MonatOM19 fatcat:c6bujhm42na6paexk5sukwqa7q

A Deep Probabilistic Model for Customer Lifetime Value Prediction [article]

Xiaojing Wang, Tianqi Liu, Jingang Miao
2019 arXiv   pre-print
This modeling approach allows us to capture the churn probability and account for the heavy-tailedness nature of LTV at the same time.  ...  For model evaluation, we recommend the normalized Gini coefficient to quantify model discrimination and decile charts to assess model calibration.  ...  ACKNOWLEDGMENTS The authors thank Jim Koehler, Tim Au, Georg Goerg, Dustin Tseng, Yael Grossman Levy, Henry Tappen for useful discussions, and Google Ads engineering and product team for their support.  ... 
arXiv:1912.07753v1 fatcat:yffxg677mzhk7hym7pvnvdlasq

Arbitrage of forecasting experts

Vitor Cerqueira, Luís Torgo, Fábio Pinto, Carlos Soares
2018 Machine Learning  
We present an approach for retrieving out-of-bag predictions that significantly improves its data efficiency.  ...  Its generalised interest is related to the uncertainty and complex evolving structure of time series.  ...  -006961", and by National Funds through the FCT-Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) as part of Project UID/EEA/50014/2013; Project "NORTE-01-0145-FEDER  ... 
doi:10.1007/s10994-018-05774-y fatcat:gkxfqujjzrf43cmqyhnfncjc2m
« Previous Showing results 1 — 15 out of 314 results