The UI INDEX is a resource center for the Interventions community. Central to the UI INDEX is a curated searchable database of the translational interventions literature as well as searchable resources for journals that publish Interventions work, highly cited work and program information regarding work funded by the National Institutes of Health. Participants will learn about the content and usage of these tools. 


UI Index: A Tool Providing a Searchable Interface for Literature on Broadening Participation in Science

Many companies make use of customer service chats to help the customer and try to solve their problem. However, customer service data is confidential and as such, cannot easily be shared in the research community. This also implies that these
data are rarely labeled, making it difficult to take advantage of it with machine learning methods. In this paper we present the first work on a customer’s problem status prediction and identification of problematic conversations. Given very small
subsets of labeled textual conversations and unlabeled ones, we propose a semi-supervised framework dedicated to customer service data leveraging speaker role information to adapt the model to the domain and the task using a two-step process. Our framework, Task-Adaptive Fine-tuning, goes from predicting customer satisfaction to identifying the status of the customer’s problem, with the latter being the main objective of the multi-task setting. It outperforms recent inductive semi-supervised approaches on this novel task while only considering a relatively low number of parameters to train on during the final target task. We believe it can not only serve models dedicated to customer service but also to any other application making use of confidential conversational data where labeled sets are rare. Source code is available at https://github.com/gguibon/taft

An Adaptive Layer to Leverage both Domain and Task Specific Information from Scarce Data

The conversational recommender system (CRS) aims to provide high-quality recommendations through interactive dialogues. However, previous CRS models have no effective mechanisms for task planning and topic elaboration, and thus they hardly maintain coherence in multi-task recommendation dialogues. Inspired by recent advances in prompt-based learning, we propose a novel contextual prompting framework for dialogue management, which optimizes prompts based on context, topics, and user profiles. Specifically, we develop a topic controller to sequentially plan the subtasks, and a prompt search module to construct context-aware prompts. We further adopt external knowledge to enrich user profiles and make knowledge-aware recommendations. Incorporating these techniques, we propose a conversational recommender system with contextual prompting, namely CP-Rec. Experimental results demonstrate that it achieves state-of-the-art recommendation accuracy and generates more coherent and informative conversations.

CP-Rec: Contextual Prompting for Conversational Recommender Systems

AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes

The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification.

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

Energy efficiency is considered a significant concern in the deployment and operation of data center networks. In this work, to address the energy consumption problem in data center networks, we propose an energy-efficient routing approach that considers that the network devices work based on traffic demand. Our approach monitors the traffic demand to improve the energy efficiency in SD-DCN networks. The simulation results reflect the enhancement of the proposed approach to optimize the end-to-end delay, throughput, and energy savings.

Energy-Aware Routing in SDN Enabled Data Center Network

"Augmented Reality (AR) and Virtual Reality (VR) games are some of the emerging use cases of 5G in the area of ultra-Reliable and Low Latency Communications (uRLLC). A multiplayer AR/VR game broadly consists of compute-intensive tasks which convert the raw data generated from sensory sources such as wearables, smartphones, etc., to action data such as location, orientation, intention, etc., and services that process the action data. Services generate a common response to all
players by taking action data as input. The total response time must be as low as 20 milliseconds for a good user experience and to prevent motion sickness. While considering these aspects, the multiplayer game must be scalable, and users should be able to move. Multi-access edge computing (MEC) helps to improve performance by partially/fully offloading such tasks from mobile devices and latency-sensitive services from the cloud to a server at the edge called the MEC host. We propose, for the first time, an online mobility-aware heuristic in a Multi-access Edge Computing Network (MEN) to reduce the response time, specifically the Game Frame Time (GFT), consistently, for an improved Quality of Experience (QoE), for such games. This is done by jointly offloading tasks and placing services, and migrating both whenever required. Additionally, for improved response, the network is partitioned into regions, and a service instance is placed on a MEC host, called the Region Coordinator (RC), in each region, in a decentralized manner. When a new player joins, an old player leaves, or old players move, the number of players and their mobility patterns change in a particular region. This may require allocating or moving tasks from one MEC host to another and migrating services to a new RC. While tasks and services are migrated, the associated state and data must be moved to the destination MEC host. Our experiments demonstrate that the standard deviation for
the mean GFT is 0 ms in the best case and 9.26 ms in the worst case, providing a uniform user experience, even when mobility is as high as 50% (it means 50% of the players are moving). When there is mobility, the GFT increases by 28.29% in the best
case and 37.18% in the worst case, compared to a no-mobility scenario. We also demonstrate that, given computing power, there is a tradeoff between responsiveness and GFT."

Mobility-aware Multi-Access Edge Computing for Multiplayer Augmented and Virtual Reality Gaming

Firewalls for IoT devices can be enforced at the gateway router or at the cloud. Utilizing a fog based architecture, firewalls can also be enforced at the fog layer. Depending on where the firewall is running, varying delays and overhead will be experienced by IoT devices. Some IoT devices are sensitive to the incurred delays. So choosing the most suitable platform to enforce a firewall for each individual device considering the delay sensitivity of the device is important. This presentation  gives an overview of a delay-aware IoT firewall enforcing mechanism using fog-cloud architecture. The presentation includes the system architecture, methodology, workflow of dynamic assignment of different devices to different platforms, the idea of delay monitoring and load-balancing, and future work.

Enforcing delay-aware fog-cloud based IoT firewall (Work In Progress)

Cloud-based services are a current approach for developing large-scale applications with advantages such as flexibility, access to on-demand resources, and business agility. The overall application functionality results from complex interactions of many decoupled services, each having its operational specificity. Due to this complexity, the manual configuration of these systems is very arduous, error-prone and likely to impair the quality of service, leading to malfunctioning services, lowering availability and accruing costs. Identifying the optimal solution to simultaneously optimize availability and costs, whilst meeting service-level objectives remains a challenge for professionals developing solutions using cloud services. This paper proposes a mathematical formulation of a bi-objective problem to identify the optimal set of solutions for the system configuration. Empirical evaluation of the proposed approach in a case study of a real industrial scenario results in an R-Squared of 0.85, an MSE of 0.021 and an optimization accuracy of 0.928. These methods can help practitioners to keep services at an optimum configuration enabling autonomic service operation, whilst improving availability and cost.

Bi-objective optimization of availability and cost for cloud services

Detecting causality or the happens before relation
between events in an asynchronous distributed system is a
fundamental building block for distributed applications. To the
best of our knowledge, this problem has not been examined in a
system with Byzantine processes. We prove the following results
for an asynchronous system with Byzantine processes. (1) We
prove that it is impossible to determine causality between events
in the presence of even a single Byzantine process when processes
communicate by unicasting. (2) We also prove a similar impossibility
result when processes communicate by broadcasting.
(3) We also prove a similar impossibility result when processes
communicate by multicasting. (4) In an execution where there
exists a causal path between two events passing through only
correct processes, the impossibility result for unicasts remains. (5)
However, when processes communicate by broadcasting and there
exists a causal path between two events passing through only
correct processes, it is possible to detect causality between such
a pair of events. (6) In an execution where processes communicate
by multicasting and there exists a causal path between two
events passing through only correct processes, we prove that the
impossibility result for multicasts remains.

Detecting Causality in the Presence of Byzantine Processes: There is No Holy Grail

Gossip-based dissemination protocols are important building blocks of large-scale distributed systems as they may impact both the systems' efficiency and fault tolerance. There exist many flavors of gossip dissemination protocols. IDA-Gossip is one of the gossip dissemination protocols proposed in the context of blockchains to efficiently disseminate large messages. It relies on multi-chunk gossip dissemination, erasure coding, and Merkle hash trees. However, despite its claimed efficiency, there is no in-depth analysis of this protocol to understand its behavior under different conditions (e.g., with injected faults). In this work, we evaluate the behavior of IDA-Gossip by relying on extensive experiments and simulations. Specifically, we evaluate IDA-Gossip both in terms of performance and resilience to faults by varying its configuration parameters and the number of faulty nodes, respectively. This study results in several takeaways. First, IDA-Gossip provides excellent dissemination latency compared to classic gossip. Second, it provides excellent coverage even with 40 percent of faulty nodes in the system. Finally, the use of erasure coding provides an important advantage to IDA-Gossip compared to classic multi-chunk gossip dissemination protocols.

In-depth analysis of the IDA-Gossip protocol

Nowadays, tourists turn to digital platforms to discover new places to explore. CROSS City is a smart tourism mobile application that enhances the user experience of tourists visiting points of interest in a route by rewarding them in the end, if they actually visited all locations. From a technical standpoint, the user location is certified resorting to strategies that take advantage of both the diversity of the existing Wi-Fi network infrastructure throughout the city, as well as the presence of other users at the same site using Bluetooth. This work developed a new, peer-to-peer location certification strategy and added gamification elements to encourage users to keep the wireless radios turned on and use the app more. This work was evaluated both in laboratory experiments and with users in a real-world scenario which demonstrated that the new Bluetooth peer-based strategy is both feasible and resistant to collusion attacks.

Underline digital video library

UI Index: A Tool Providing a Searchable Interface for Literature on Broadening Participation in Science

An Adaptive Layer to Leverage both Domain and Task Specific Information from Scarce Data

CP-Rec: Contextual Prompting for Conversational Recommender Systems

AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

Energy-Aware Routing in SDN Enabled Data Center Network

Mobility-aware Multi-Access Edge Computing for Multiplayer Augmented and Virtual Reality Gaming

Enforcing delay-aware fog-cloud based IoT firewall (Work In Progress)

Bi-objective optimization of availability and cost for cloud services

Detecting Causality in the Presence of Byzantine Processes: There is No Holy Grail

In-depth analysis of the IDA-Gossip protocol

Bluetooth Peer-to-Peer Location Certification with a Gamified Mobile Application

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES