对卷积神经网络（CNN）的知识蒸馏（KD）进行了广泛的研究，以提高小型模型的性能。最近，Vision Transformer（VIT）在许多计算机视觉任务上取得了巨大的成功，而VIT的KD也需要实现。但是，除了基于输出logit的KD之外，由于巨大的结构间隙，其他基于特征的CNN基于特征的KD方法不能直接应用于VIT。在本文中，我们探讨了对VIT的基于特征的蒸馏方式。根据VIT中特征地图的性质，我们设计了一系列受控的实验，并为VIT特征蒸馏提供了三个实用指南。我们的一些发现甚至与CNN时代的实践相反。根据三个准则，我们提出了基于功能的方法Vitkd，从而为学生带来一致且相当大的改进。在ImagEnet-1K上，我们将DEIT微型从74.42％提高到76.06％，Deit-Small从80.55％提高到81.95％，而Deit-Base则从81.76％升至83.46％。此外，Vitkd和基于Logit的KD方法是互补的，可以直接使用。这种组合可以进一步提高学生的表现。具体而言，学生DEIT微小，小和基础分别达到77.78％，83.59％和85.41％。该代码可在https://github.com/yzd-v/cls_kd上找到。

最近，对于长期时间序列预测（LTSF）任务，基于变压器的解决方案激增。尽管过去几年的表现正在增长，但我们质疑这项研究中这一研究的有效性。具体而言，可以说，变形金刚是最成功的解决方案，是在长序列中提取元素之间的语义相关性。但是，在时间序列建模中，我们要在一组连续点的有序集中提取时间关系。在采用位置编码和使用令牌将子系列嵌入变压器中的同时，有助于保留某些订购信息，但\ emph {置换不变}的自我注意力专注机制的性质不可避免地会导致时间信息损失。为了验证我们的主张，我们介绍了一组名为LTSF线性的令人尴尬的简单单层线性模型，以进行比较。在九个现实生活数据集上的实验结果表明，LTSF线性在所有情况下都超过现有的基于变压器的LTSF模型，并且通常要大幅度较大。此外，我们进行了全面的经验研究，以探索LTSF模型各种设计元素对其时间关系提取能力的影响。我们希望这一令人惊讶的发现为LTSF任务打开了新的研究方向。我们还主张重新审视基于变压器解决方案对其他时间序列分析任务（例如，异常检测）的有效性。代码可在：\ url {https://github.com/cure-lab/ltsf-linear}中获得。

本文提出了一个简单的基线框架，用于基于视频的2D/3D人姿势估计，该估计可以比现有作品实现10倍提高效率，而无需任何性能降级，名为Deciwatch。与当前在视频中估算每个帧的解决方案不同，Deciwatch引入了一个简单而有效的样品探测框架框架，该框架只能通过人类动作的连续性和轻巧的姿势表示，仅观看稀疏采样的框架。具体而言，DeciWatch均匀地示例少于10％的视频帧以进行详细估计，以有效的变压器体系结构来确定估计的2D/3D姿势，然后使用另一个基于变压器的网络准确地恢复其余帧。通过四个数据集的三个基于视频的人姿势估计和身体网格恢复任务的全面实验结果验证了Deciwatch的效率和有效性。代码可在https://github.com/cure-lab/deciwatch上找到。

在分析人类运动视频时，来自现有姿势估计器的输出抖动是高度不平衡的。大多数帧只遭受轻微的傻瓜，而在那些具有遮挡或图像质量差的框架中发生了重要的困难。这种复杂的姿势通常持续存在于视频中，导致估计结果差和大型抖动的连续帧。现有的基于时间卷积网络，经常性神经网络或低通滤波器的现有姿态平滑解决方案不能处理这种长期抖动问题，而不考虑抖动视频段内的显着和持久的错误。通过上述观察，我们提出了一种新颖的即插即用细化网络，即光滑网络，可以附加到任何现有的姿势估计，以提高其时间平滑度，同时提高其每个帧精度。特别是，SmoothNet是一个简单而有效的数据驱动的全连接网络，具有大的接收领域，有效地减轻了长期抖动与不可靠的估计结果的影响。我们在十二个骨干网络上进行广泛的实验，跨越2D和3D姿势估算，身体恢复和下游任务。我们的结果表明，所提出的光滑网络始终如一地优于现有的解决方案，尤其是具有高误差和长期抖动的夹子。

Increasing research interests focus on sequential recommender systems, aiming to model dynamic sequence representation precisely. However, the most commonly used loss function in state-of-the-art sequential recommendation models has essential limitations. To name a few, Bayesian Personalized Ranking (BPR) loss suffers the vanishing gradient problem from numerous negative sampling and predictionbiases; Binary Cross-Entropy (BCE) loss subjects to negative sampling numbers, thereby it is likely to ignore valuable negative examples and reduce the training efficiency; Cross-Entropy (CE) loss only focuses on the last timestamp of the training sequence, which causes low utilization of sequence information and results in inferior user sequence representation. To avoid these limitations, in this paper, we propose to calculate Cumulative Cross-Entropy (CCE) loss over the sequence. CCE is simple and direct, which enjoys the virtues of painless deployment, no negative sampling, and effective and efficient training. We conduct extensive experiments on five benchmark datasets to demonstrate the effectiveness and efficiency of CCE. The results show that employing CCE loss on three state-of-the-art models GRU4Rec, SASRec, and S3-Rec can reach 125.63%, 69.90%, and 33.24% average improvement of full ranking NDCG@5, respectively. Using CCE, the performance curve of the models on the test data increases rapidly with the wall clock time, and is superior to that of other loss functions in almost the whole process of model training.

The utilization of large-scale distributed renewable energy promotes the development of the multi-microgrid (MMG), which raises the need of developing an effective energy management method to minimize economic costs and keep self energy-sufficiency. The multi-agent deep reinforcement learning (MADRL) has been widely used for the energy management problem because of its real-time scheduling ability. However, its training requires massive energy operation data of microgrids (MGs), while gathering these data from different MGs would threaten their privacy and data security. Therefore, this paper tackles this practical yet challenging issue by proposing a federated multi-agent deep reinforcement learning (F-MADRL) algorithm via the physics-informed reward. In this algorithm, the federated learning (FL) mechanism is introduced to train the F-MADRL algorithm thus ensures the privacy and the security of data. In addition, a decentralized MMG model is built, and the energy of each participated MG is managed by an agent, which aims to minimize economic costs and keep self energy-sufficiency according to the physics-informed reward. At first, MGs individually execute the self-training based on local energy operation data to train their local agent models. Then, these local models are periodically uploaded to a server and their parameters are aggregated to build a global agent, which will be broadcasted to MGs and replace their local agents. In this way, the experience of each MG agent can be shared and the energy operation data is not explicitly transmitted, thus protecting the privacy and ensuring data security. Finally, experiments are conducted on Oak Ridge national laboratory distributed energy control communication lab microgrid (ORNL-MG) test system, and the comparisons are carried out to verify the effectiveness of introducing the FL mechanism and the outperformance of our proposed F-MADRL.

This paper presents a safety-critical locomotion control framework for quadrupedal robots. Our goal is to enable quadrupedal robots to safely navigate in cluttered environments. To tackle this, we introduce exponential Discrete Control Barrier Functions (exponential DCBFs) with duality-based obstacle avoidance constraints into a Nonlinear Model Predictive Control (NMPC) with Whole-Body Control (WBC) framework for quadrupedal locomotion control. This enables us to use polytopes to describe the shapes of the robot and obstacles for collision avoidance while doing locomotion control of quadrupedal robots. Compared to most prior work, especially using CBFs, that utilize spherical and conservative approximation for obstacle avoidance, this work demonstrates a quadrupedal robot autonomously and safely navigating through very tight spaces in the real world. (Our open-source code is available at github.com/HybridRobotics/quadruped_nmpc_dcbf_duality, and the video is available at youtu.be/p1gSQjwXm1Q.)

Three-dimensional (3D) ultrasound imaging technique has been applied for scoliosis assessment, but current assessment method only uses coronal projection image and cannot illustrate the 3D deformity and vertebra rotation. The vertebra detection is essential to reveal 3D spine information, but the detection task is challenging due to complex data and limited annotations. We propose VertMatch, a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner. The first step is to detect the possible positions of structures on transverse slice globally, and then the local patches are cropped based on detected positions. The second step is to distinguish whether the patches contain real vertebral structures and screen the predicted positions from the first step. VertMatch develops three novel components for semi-supervised learning: for position detection in the first step, (1) anatomical prior is used to screen pseudo labels generated from confidence threshold method; (2) multi-slice consistency is used to utilize more unlabeled data by inputting multiple adjacent slices; (3) for patch identification in the second step, the categories are rebalanced in each batch to solve imbalance problem. Experimental results demonstrate that VertMatch can detect vertebra accurately in ultrasound volume and outperforms state-of-the-art methods. VertMatch is also validated in clinical application on forty ultrasound scans, and it can be a promising approach for 3D assessment of scoliosis.

Free-text rationales (FTRs) follow how humans communicate by explaining reasoning processes via natural language. A number of recent works have studied how to improve language model (LM) generalization by using FTRs to teach LMs the correct reasoning processes behind correct task outputs. These prior works aim to learn from FTRs by appending them to the LM input or target output, but this may introduce an input distribution shift or conflict with the task objective, respectively. We propose KNIFE, which distills FTR knowledge from an FTR-augmented teacher LM (takes both task input and FTR) to a student LM (takes only task input), which is used for inference. Crucially, the teacher LM's forward computation has a bottleneck stage in which all of its FTR states are masked out, which pushes knowledge from the FTR states into the task input/output states. Then, FTR knowledge is distilled to the student LM by training its task input/output states to align with the teacher LM's. On two question answering datasets, we show that KNIFE significantly outperforms existing FTR learning methods, in both fully-supervised and low-resource settings.

Time series anomaly detection strives to uncover potential abnormal behaviors and patterns from temporal data, and has fundamental significance in diverse application scenarios. Constructing an effective detection model usually requires adequate training data stored in a centralized manner, however, this requirement sometimes could not be satisfied in realistic scenarios. As a prevailing approach to address the above problem, federated learning has demonstrated its power to cooperate with the distributed data available while protecting the privacy of data providers. However, it is still unclear that how existing time series anomaly detection algorithms perform with decentralized data storage and privacy protection through federated learning. To study this, we conduct a federated time series anomaly detection benchmark, named FedTADBench, which involves five representative time series anomaly detection algorithms and four popular federated learning methods. We would like to answer the following questions: (1)How is the performance of time series anomaly detection algorithms when meeting federated learning? (2) Which federated learning method is the most appropriate one for time series anomaly detection? (3) How do federated time series anomaly detection approaches perform on different partitions of data in clients? Numbers of results as well as corresponding analysis are provided from extensive experiments with various settings. The source code of our benchmark is publicly available at https://github.com/fanxingliu2020/FedTADBench.