More Like this

1. QFlow: A Learning Approach to High QoE Video Streaming at the Wireless Edge

   https://doi.org/10.1109/TNET.2021.3106675  

   Bhattacharyya, Rajarshi ; Bura, Archana ; Rengarajan, Desik ; Rumuly, Mason ; Xia, Bainan ; Shakkottai, Srinivas ; Kalathil, Dileep ; Mok, Ricky K. ; Dhamdhere, Amogh ( January 2021 , IEEE/ACM Transactions on Networking)

   null (Ed.)

   The predominant use of wireless access networks is for media streaming applications. However, current access networks treat all packets identically, and lack the agility to determine which clients are most in need of service at a given time. Software reconfigurability of networking devices has seen wide adoption, and this in turn implies that agile control policies can be now instantiated on access networks. Exploiting such reconfigurability requires the design of a system that can enable a configuration, measure the impact on the application performance (Quality of Experience), and adaptively select a new configuration. Effectively, this feedback loop is a Markov Decision Process whose parameters are unknown. The goal of this work is to develop QFlow, a platform that instantiates this feedback loop, and instantiate a variety of control policies over it. We use the popular application of video streaming over YouTube as our use case. Our context is priority queueing, with the action space being that of determining which clients should be assigned to each queue at each decision period. We first develop policies based on model-based and model-free reinforcement learning. We then design an auction-based system under which clients place bids for priority service, as well as a more structured index-based policy. Through experiments, we show how these learning-based policies on QFlow are able to select the right clients for prioritization in a high-load scenario to outperform the best known solutions with over 25% improvement in QoE, and a perfect QoE score of 5 over 85% of the time. 

   more » « less
2. An Upper Limit to Youth Psychotherapy Benefit? A Meta-Analytic Copula Approach to Psychotherapy Outcomes

   https://doi.org/10.1177/2167702619858424  

   Jones, Payton_J ; Mair, Patrick ; Kuppens, Sofie ; Weisz, John_R ( August 2019 , Clinical Psychological Science)

   Across 50 years of research, extensive efforts have been made to improve the effectiveness of psychotherapies for children and adolescents. Yet recent evidence shows no significant improvement in youth psychotherapy outcomes. In other words, efforts to improve the general quality of therapy models do not appear to have translated directly into improved outcomes. We used multilevel meta-analytic data from 502 randomized controlled trials to generate a bivariate copula model predicting effect size as therapy quality approaches infinity. Our results suggest that even with a therapy of perfect quality, achieved effect sizes may be modest. If therapy quality and therapy outcome share a correlation of .20 (a somewhat optimistic assumption given the evidence we review), a therapy of perfect quality would produce an effect size of Hedges’s g = 0.83. We suggest that youth psychotherapy researchers complement their efforts to improve psychotherapy quality by investigating additional strategies for improving outcomes.

    

   more » « less
3. Text Generation to Aid Depression Detection: A Comparative Study of Conditional Sequence Generative Adversarial Networks

   https://doi.org/10.1109/BigData55660.2022.10020224  

   Tlachac, ML ; Gerych, Walter ; Agrawal, Kratika ; Litterer, Benjamin ; Jurovich, Nicholas ; Thatigotla, Saitheeraj ; Thadajarassiri, Jidapa ; Rundensteiner, Elke A. ( December 2022 , 2022 IEEE International Conference on Big Data (Big Data))

   Corpuses of unstructured textual data, such as text messages between individuals, are often predictive of medical issues such as depression. The text data usually used in healthcare applications has high value and great variety, but is typically small in volume. Generating labeled unstructured text data is important to improve models by augmenting these small datasets, as well as to facilitate anonymization. While methods for labeled data generation exist, not all of them generalize well to small datasets. In this work, we thus perform a much needed systematic comparison of conditional text generation models that are promising for small datasets due to their unified architectures. We identify and implement a family of nine conditional sequence generative adversarial networks for text generation, which we collectively refer to as cSeqGAN models. These models are characterized along two orthogonal design dimensions: weighting strategies and feedback mechanisms. We conduct a comparative study evaluating the generation ability of the nine cSeqGAN models on three diverse text datasets with depression and sentiment labels. To assess the quality and realism of the generated text, we use standard machine learning metrics as well as human assessment via a user study. While the unconditioned models produced predictive text, the cSeqGAN models produced more realistic text. Our comparative study lays a solid foundation and provides important insights for further text generation research, particularly for the small datasets common within the healthcare domain. 

   more » « less
4. Maximizing Global Model Appeal in Federated Learning

   Cho, Yae Jee ; Jhunjhunwala, Divyansh ; Li, Tian ; Smith, Virginia ; Joshi, Gauri ( March 2024 , Transactions on machine learning research)

   Bellet, Aurelien (Ed.)

   Federated learning (FL) aims to collaboratively train a global model using local data from a network of clients. To warrant collaborative training, each federated client may expect the resulting global model to satisfy some individual requirement, such as achieving a certain loss threshold on their local data. However, in real FL scenarios, the global model may not satisfy the requirements of all clients in the network due to the data heterogeneity across clients. In this work, we explore the problem of global model appeal in FL, which we define as the total number of clients that find that the global model satisfies their individual requirements. We discover that global models trained using traditional FL approaches can result in a significant number of clients unsatisfied with the model based on their local requirements. As a consequence, we show that global model appeal can directly impact how clients participate in training and how the model performs on new clients at inference time. Our work proposes MaxFL, which maximizes the number of clients that find the global model appealing. MaxFL achieves a 22-40% and 18-50% improvement in the test accuracy of training clients and (unseen) test clients respectively, compared to a wide range of FL approaches that tackle data heterogeneity, aim to incentivize clients, and learn personalized/fair models. 

   more » « less
5. What drives our behaviors in buildings? A review on occupant interactions with building systems from the lens of behavioral theories

   https://doi.org/10.1016/j.buildenv.2020.106928  

   Arsalan Heydarian, Claire McIlvennie ( July 2020 , Building and environment)

   Occupant behavior has a significant impact on building systems’ operations and efficiency. As a result, several innovative approaches have been introduced to quantify the dynamics of occupants within indoor environments, such as interactions with different building systems and the impact of various feedback and interventions to reduce the building energy consumption. To achieve this, researchers have highlighted the importance of reducing energy consumption without impacting occupant comfort. As a result, there is an increasing body of research evaluating how different theories of behavior across a variety of disciplines can explain occupant interactions with building systems. Future progress in this area calls for an in-depth understanding of behavioral theories in explaining occupant interactions with different building systems. In this paper, we have used a structured literature review approach to investigate how different psychological, sociological, and economic theories have been applied to explain occupant interactions with heating and cooling (HVAC systems), opening windows and ventilation, lighting and shading, electronic appliances, domestic hot water, as well as energy conservation behaviors. Throughout the paper, we identify the most common theories and methodologies applied within the existing research, general findings related to how occupants interact with different building systems, as well as a number of identified gaps within the literature. Finally, we provide a discussion on directions for future research studies in this area under each building system. 

   more » « less