Samir Das

Bryan Bo Cao, Abhinav Sharma, Manavjeet Singh et al.

Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep Neural Networks (DNNs) used in video-based applications (e.g. object detection) exerts pressure on memory-constrained edge devices. Model merging is proposed to reduce the DNNs' memory footprint by keeping only one copy of merged layers' weights in memory. In existing model merging techniques, (i) only architecturally identical layers can be shared; (ii) requires computationally expensive retraining in the cloud; (iii) assumes the availability of ground truth for retraining. The re-evaluation of a merged model's performance, however, requires a validation dataset with ground truth, typically runs at the cloud. Common metrics to guide the selection of shared layers include the size or computational cost of shared layers or representation size. We propose a new model merging scheme by sharing representations (i.e., outputs of layers) at the edge, guided by representation similarity S. We show that S is extremely highly correlated with merged model's accuracy with Pearson Correlation Coefficient |r| > 0.94 than other metrics, demonstrating that representation similarity can serve as a strong validation accuracy indicator without ground truth. We present our preliminary results of the newly proposed model merging scheme with identified challenges, demonstrating a promising research future direction.

Vasudevan Nagendra, Abhishek Pokala, Arani Bhattacharya et al.

Proactive detection of network configuration bugs is important to ensure its proper functioning and reduce cost of network administrator. In this research, we propose to build the control plane verification engine MAVERICK that detects the bugs in the network control plane i.e., network device configurations and control plane states. MAVERICK automatically infers signatures for the control plane configurations (e.g., ACLs, route-maps, route-policies and so on) and states that allows administrators to automatically detect bugs with minimal human intervention. MAVERICK achieves this by effectively leveraging any structural deviation i.e., outliers in the network configurations that is organized as simple or complexly nested key-value pairs. The outliers that are calculated using signature-based outlier detection mechanism are further characterized for its severity and ranked or re-prioritized according to their criticality. We consider a wide set of heuristics and domain expertise factors for effectively to reduce both false positives and false negatives.Our evaluation on four medium to large-scale enterprise networks show that MAVERICK can automatically detect the bugs present in the network with approximately 75% accuracy. Further-more, With minimal administrator input i.e., with a few minutes of signature re-tuning, MAVERICK allows the administrators to effectively detect approximately 94 - 100% of the bugs present in the network, thereby ranking down less severe bugs and removing false positives.

Tristan Glatard, Gregory Kiar, Tristan Aumentado-Armstrong et al.

We present Boutiques, a system to automatically publish, integrate and execute applications across computational platforms. Boutiques applications are installed through software containers described in a rich and flexible JSON language. A set of core tools facilitate the construction, validation, import, execution, and publishing of applications. Boutiques is currently supported by several distinct virtual research platforms, and it has been used to describe dozens of applications in the neuroinformatics domain. We expect Boutiques to improve the quality of application integration in computational platforms, to reduce redundancy of effort, to contribute to computational reproducibility, and to foster Open Science.