Asynchronous Hierarchical Federated Learning

Federated Learning is a rapidly growing area of research and with various benefits and industry applications. Typical federated patterns have some intrinsic issues such as heavy server traffic, long periods of convergence, and unreliable accuracy. In this paper, we address these issues by proposing asynchronous hierarchical federated learning, in which the central server uses either the network topology or some clustering algorithm to assign clusters for workers (i.e., client devices). In each cluster, a special aggregator device is selected to enable hierarchical learning, leads to efficient communication between server and workers, so that the burden of the server can be significantly reduced. In addition, asynchronous federated learning schema is used to tolerate heterogeneity of the system and achieve fast convergence, i.e., the server aggregates the gradients from the workers weighted by a staleness parameter to update the global model, and regularized stochastic gradient descent is performed in workers, so that the instability of asynchronous learning can be alleviated. We evaluate the proposed algorithm on CIFAR-10 image classification task, the experimental results demonstrate the effectiveness of asynchronous hierarchical federated learning.

Sepsis Prediction with Temporal Convolutional Networks

We design and implement a temporal convolutional network model to predict sepsis onset. Our model is trained on data extracted from MIMIC III database, based on a retrospective analysis of patients admitted to intensive care unit who did not fall under the definition of sepsis at the time of admission. Benchmarked with several machine learning models, our model is superior on this binary classification task, demonstrates the prediction power of convolutional networks for temporal patterns, also shows the significant impact of having longer look back time on sepsis prediction.

MoCoViT: Mobile Convolutional Vision Transformer

Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile Convolutional Vision Transformer (MoCoViT), which improves in performance and efficiency by introducing transformer into mobile convolutional networks to leverage the benefits of both architectures. Different from recent works on vision transformer, the mobile transformer block in MoCoViT is carefully designed for mobile devices and is very lightweight, accomplished through two primary modifications: the Mobile Self-Attention (MoSA) module and the Mobile Feed Forward Network (MoFFN). MoSA simplifies the calculation of the attention map through Branch Sharing scheme while MoFFN serves as a mobile version of MLP in the transformer, further reducing the computation by a large margin. Comprehensive experiments verify that our proposed MoCoViT family outperform state-of-the-art portable CNNs and transformer neural architectures on various vision tasks. On ImageNet classification, it achieves 74.5% top-1 accuracy at 147M FLOPs, gaining 1.2% over MobileNetV3 with less computations. And on the COCO object detection task, MoCoViT outperforms GhostNet by 2.1 AP in RetinaNet framework.

TRT-ViT: TensorRT-oriented Vision Transformer

We revisit the existing excellent Transformers from the perspective of practical application. Most of them are not even as efficient as the basic ResNets series and deviate from the realistic deployment scenario. It may be due to the current criterion to measure computation efficiency, such as FLOPs or parameters is one-sided, sub-optimal, and hardware-insensitive. Thus, this paper directly treats the TensorRT latency on the specific hardware as an efficiency metric, which provides more comprehensive feedback involving computational capacity, memory cost, and bandwidth. Based on a series of controlled experiments, this work derives four practical guidelines for TensorRT-oriented and deployment-friendly network design, e.g., early CNN and late Transformer at stage-level, early Transformer and late CNN at block-level. Accordingly, a family of TensortRT-oriented Transformers is presented, abbreviated as TRT-ViT. Extensive experiments demonstrate that TRT-ViT significantly outperforms existing ConvNets and vision Transformers with respect to the latency/accuracy trade-off across diverse visual tasks, e.g., image classification, object detection and semantic segmentation. For example, at 82.7% ImageNet-1k top-1 accuracy, TRT-ViT is 2.7$\times$ faster than CSWin and 2.0$\times$ faster than Twins. On the MS-COCO object detection task, TRT-ViT achieves comparable performance with Twins, while the inference speed is increased by 2.8$\times$.

Accurate Fruit Localisation for Robotic Harvesting using High Resolution LiDAR-Camera Fusion

Accurate depth-sensing plays a crucial role in securing a high success rate of robotic harvesting in natural orchard environments. Solid-state LiDAR (SSL), a recently introduced LiDAR technique, can perceive high-resolution geometric information of the scenes, which can be potential utilised to receive accurate depth information. Meanwhile, the fusion of the sensory information from LiDAR and camera can significantly enhance the sensing ability of the harvesting robots. This work introduces a LiDAR-camera fusion-based visual sensing and perception strategy to perform accurate fruit localisation for a harvesting robot in the apple orchards. Two SOTA extrinsic calibration methods, target-based and targetless-based, are applied and evaluated to obtain the accurate extrinsic matrix between the LiDAR and camera. With the extrinsic calibration, the point clouds and color images are fused to perform fruit localisation using a one-stage instance segmentation network. Experimental shows that LiDAR-camera achieves better quality on visual sensing in the natural environments. Meanwhile, introducing the LiDAR-camera fusion largely improves the accuracy and robustness of the fruit localisation. Specifically, the standard deviations of fruit localisation by using LiDAR-camera at 0.5 m, 1.2 m, and 1.8 m are 0.245, 0.227, and 0.275 cm respectively. These measurement error is only one one fifth of that from Realsense D455. Lastly, we have attached our visualised point cloud to demonstrate the highly accurate sensing method.

Network Topology Optimization via Deep Reinforcement Learning

Topology impacts important network performance metrics, including link utilization, throughput and latency, and is of central importance to network operators. However, due to the combinatorial nature of network topology, it is extremely difficult to obtain an optimal solution, especially since topology planning in networks also often comes with management-specific constraints. As a result, local optimization with hand-tuned heuristic methods from human experts are often adopted in practice. Yet, heuristic methods cannot cover the global topology design space while taking into account constraints, and cannot guarantee to find good solutions. In this paper, we propose a novel deep reinforcement learning (DRL) algorithm, called Advantage Actor Critic-Graph Searching (A2C-GS), for network topology optimization. A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search. A2C-GS can efficiently search over large topology space and output topology with satisfying performance. We conduct a case study based on a real network scenario, and our experimental results demonstrate the superior performance of A2C-GS in terms of both efficiency and performance.

SepViT: Separable Vision Transformer

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, they often require enormous amount of computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. To address these issues, we draw lessons from depthwise separable convolution and imitate its ideology to design the Separable Vision Transformer, abbreviated as SepViT. SepViT helps to carry out the information interaction within and among the windows via a depthwise separable self-attention. The novel window token embedding and grouped self-attention are employed to model the attention relationship among windows with negligible computational cost and capture a long-range visual dependencies of multiple windows, respectively. Extensive experiments on various benchmark tasks demonstrate SepViT can achieve state-of-the-art results in terms of trade-off between accuracy and latency. Among them, SepViT achieves 84.0% top-1 accuracy on ImageNet-1K classification while decreasing the latency by 40%, compared to the ones with similar accuracy (e.g., CSWin, PVTV2). As for the downstream vision tasks, SepViT with fewer FLOPs can achieve 50.4% mIoU on ADE20K semantic segmentation task, 47.5 AP on the RetinaNet-based COCO detection task, 48.7 box AP and 43.9 mask AP on Mask R-CNN-based COCO detection and segmentation tasks.

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and translates natural source sentences in inference. The source discrepancy between training and inference hinders the translation performance of UNMT models. By carefully designing experiments, we identify two representative characteristics of the data gap in source: (1) style gap (i.e., translated vs. natural text style) that leads to poor generalization capability; (2) content gap that induces the model to produce hallucination content biased towards the target language. To narrow the data gap, we propose an online self-training approach, which simultaneously uses the pseudo parallel data {natural source, translated target} to mimic the inference scenario. Experimental results on several widely-used language pairs show that our approach outperforms two strong baselines (XLM and MASS) by remedying the style and content gaps.

Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation

In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the discrepancies between Seq2Seq pretraining and NMT finetuning limit the translation quality (i.e., domain discrepancy) and induce the over-estimation issue (i.e., objective discrepancy). Based on these observations, we further propose simple and effective strategies, named in-domain pretraining and input adaptation to remedy the domain and objective discrepancies, respectively. Experimental results on several language pairs show that our approach can consistently improve both translation performance and model robustness upon Seq2Seq pretraining.