Congestion control (CC) is the key to achieving ultra-low latency, high bandwidth and network stability in high-speed networks. From years of experience operating large-scale and high-speed RDMA networks, we find the existing high-speed CC schemes have inherent limitations for reaching these goals. In this paper, we present HPCC (High Precision Congestion Control), a new high-speed CC mechanism which achieves the three goals simultaneously. HPCC leverages in-network telemetry (INT) to obtain precise link load information and controls traffic precisely. By addressing challenges such as delayed INT information during congestion and overreaction to INT information, HPCC can quickly converge to utilize free bandwidth while avoiding congestion, and can maintain near-zero in-network queues for ultra-low latency. HPCC is also fair and easy to deploy in hardware. We implement HPCC with commodity programmable NICs and switches. In our evaluation, compared to DCQCN and TIMELY, HPCC shortens flow completion times by up to 95%, causing little congestion even under large-scale incasts. CCS CONCEPTS• Networks → Transport protocols; Data center networks;

This paper proposes, simulates and experimentally demonstrate an optical interconnect architecture for large-scale computing systems. The proposed architecture, H-LION (Hierarchical Lightwave Optical Interconnect Network), leverages wavelength routing in arrayed waveguide grating routers (AWGRs), and computing nodes (or servers) with embedded routers and wavelength-specific optical I/Os. Within the racks and clusters, the interconnect topology is hierarchical all-to-all exploiting passive AWGRs. For the inter cluster communication, the proposed architecture exploits a flat and distributed Thin-CLOS topology based on AWGR-based optical switches. H-LION can scale beyond 100,000 nodes while guaranteeing up to 1.83× saving in number of inter-rack cables, and up to 1.5× saving in number of inter-rack switches, when comparing to a legacy 3-tier Fat Tree network. Network simulation results show a system-wide network throughput reaching as high as 90% of the total possible capacity in case of synthetic traffic with uniform random distribution. Experiments show 97% intra-cluster throughput for uniform random traffic, and error-free inter-cluster communication at 10 Gb/s.

Dental caries has been a common health issue throughout the world, which can even lead to dental pulp and root apical inflammation eventually. Timely and effective treatment of dental caries is vital for patients to reduce pain. Traditional caries disease diagnosis methods like naked-eye detection and panoramic radiograph examinations rely on experienced doctors, which may cause misdiagnosis and high time-consuming. To this end, we propose a novel deep learning architecture called CariesNet to delineate different caries degrees from panoramic radiographs. We firstly collect a high-quality panoramic radiograph dataset with 3127 well-delineated caries lesions, including shallow caries, moderate caries, and deep caries. Then we construct CariesNet as a U-shape network with the additional full-scale axial attention module to segment these three caries types from the oral panoramic images. Moreover, we test the segmentation performance between CariesNet and other baseline methods. Experiments show that our method can achieve a mean 93.64% Dice coefficient and 93.61% accuracy in the segmentation of three different levels of caries.

Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog policy. In this paper, we propose GALAXY, a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning. Specifically, we introduce a dialog act prediction task for policy optimization during pre-training and employ a consistency regularization term to refine the learned representation with the help of unlabeled dialogs. We also implement a gating mechanism to weigh suitable unlabeled dialog samples. Empirical results show that GALAXY substantially improves the performance of task-oriented dialog systems, and achieves new state-of-the-art results on benchmark datasets: In-Car, MultiWOZ2.0 and MultiWOZ2.1, improving their end-to-end combined scores by 2.5, 5.3 and 5.5 points, respectively. We also show that GALAXY has a stronger few-shot ability than existing models under various low-resource settings. For reproducibility, we release the code and data at https://github.com/siat-nlp/GALAXY.