众所周知，深度学习模型容易受到对抗性例子的影响。现有对对抗训练的研究已在这一挑战中取得了长足的进步。作为一个典型的特征，他们经常认为班级分布总体平衡。但是，在广泛的应用中，长尾数据集无处不在，其中头等级实例的数量大于尾巴类。在这种情况下，AUC比准确度更合理，因为它对课堂分布不敏感。在此激励的情况下，我们提出了一项早期试验，以探索对抗性训练方法以优化AUC。主要的挑战在于，积极和负面的例子与目标函数紧密结合。作为直接结果，如果没有数据集进行全面扫描，就无法生成对抗示例。为了解决此问题，基于凹入的正则化方案，我们将AUC优化问题重新制定为鞍点问题，该问题将成为实例函数。这导致端到端培训方案。此外，我们提供了提出的算法的收敛保证。我们的分析与现有研究不同，因为该算法被要求通过计算Min-Max问题的梯度来产生对抗性示例。最后，广泛的实验结果表明，在三个长尾数据集中，我们的算法的性能和鲁棒性。

ROC曲线（AUC）下的面积是机器学习的关键指标，它评估了所有可能的真实正率（TPR）和假阳性率（FPRS）的平均性能。基于以下知识：熟练的分类器应同时拥抱高的TPR和低FPR，我们转向研究一个更通用的变体，称为双向部分AUC（TPAUC），其中只有$ \ Mathsf {Tpr} \ ge ge ge ge \ alpha，\ mathsf {fpr} \ le \ beta $包含在该区域中。此外，最近的工作表明，TPAUC与现有的部分AUC指标基本上不一致，在该指标中，只有FPR范围受到限制，为寻求解决方案以利用高TPAUC开辟了一个新问题。在此激励的情况下，我们在本文中提出了优化该新指标的第一个试验。本课程的关键挑战在于难以通过端到端随机训练进行基于梯度的优化，即使有适当的替代损失选择。为了解决这个问题，我们提出了一个通用框架来构建替代优化问题，该问题支持有效的端到端培训，并深入学习。此外，我们的理论分析表明：1）替代问题的目标函数将在轻度条件下实现原始问题的上限，2）优化替代问题会导致TPAUC的良好概括性能，并且具有很高的可能性。最后，对几个基准数据集的实证研究表达了我们框架的功效。

最近提出的协作度量学习（CML）范式由于其简单性和有效性引起了人们对推荐系统（RS）领域的广泛兴趣。通常，CML的现有文献在很大程度上取决于\ textit {负抽样}策略，以减轻成对计算的耗时负担。但是，在这项工作中，通过进行理论分析，我们发现负抽样会导致对概括误差的偏差估计。具体而言，我们表明，基于抽样的CML将在概括性结合中引入一个偏差项，该术语是由per-use \ textit {total方差}（TV）量化的，在负面采样和地面真相分布引起的分布之间。这表明，即使有足够大的训练数据，优化基于采样的CML损耗函数也不能确保小概括误差。此外，我们表明偏见术语将消失，而无需负面抽样策略。在此激励的情况下，我们提出了一种有效的替代方案，而没有对CML进行负面采样的cml，name \ textit {无抽样协作度量学习}（SFCML），以消除实际意义上的采样偏见。最后，超过七个基准数据集的全面实验表达了所提出的算法的优势。

Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions. For instance, OT is a popular loss function that quantifies the discrepancy between an empirical distribution and a parametric model. Recently, an entropic penalty term and the celebrated Sinkhorn algorithm have been commonly used to approximate the original OT in a computationally efficient way. However, since the Sinkhorn algorithm runs a projection associated with the Kullback-Leibler divergence, it is often vulnerable to outliers. To overcome this problem, we propose regularizing OT with the \beta-potential term associated with the so-called $\beta$-divergence, which was developed in robust statistics. Our theoretical analysis reveals that the $\beta$-potential can prevent the mass from being transported to outliers. We experimentally demonstrate that the transport matrix computed with our algorithm helps estimate a probability distribution robustly even in the presence of outliers. In addition, our proposed method can successfully detect outliers from a contaminated dataset

In the era of Internet of Things (IoT), network-wide anomaly detection is a crucial part of monitoring IoT networks due to the inherent security vulnerabilities of most IoT devices. Principal Components Analysis (PCA) has been proposed to separate network traffics into two disjoint subspaces corresponding to normal and malicious behaviors for anomaly detection. However, the privacy concerns and limitations of devices' computing resources compromise the practical effectiveness of PCA. We propose a federated PCA-based Grassmannian optimization framework that coordinates IoT devices to aggregate a joint profile of normal network behaviors for anomaly detection. First, we introduce a privacy-preserving federated PCA framework to simultaneously capture the profile of various IoT devices' traffic. Then, we investigate the alternating direction method of multipliers gradient-based learning on the Grassmann manifold to guarantee fast training and the absence of detecting latency using limited computational resources. Empirical results on the NSL-KDD dataset demonstrate that our method outperforms baseline approaches. Finally, we show that the Grassmann manifold algorithm is highly adapted for IoT anomaly detection, which permits drastically reducing the analysis time of the system. To the best of our knowledge, this is the first federated PCA algorithm for anomaly detection meeting the requirements of IoT networks.

In this paper, we propose a novel architecture, the Enhanced Interactive Transformer (EIT), to address the issue of head degradation in self-attention mechanisms. Our approach replaces the traditional multi-head self-attention mechanism with the Enhanced Multi-Head Attention (EMHA) mechanism, which relaxes the one-to-one mapping constraint among queries and keys, allowing each query to attend to multiple keys. Furthermore, we introduce two interaction models, Inner-Subspace Interaction and Cross-Subspace Interaction, to fully utilize the many-to-many mapping capabilities of EMHA. Extensive experiments on a wide range of tasks (e.g. machine translation, abstractive summarization, grammar correction, language modelling and brain disease automatic diagnosis) show its superiority with a very modest increase in model size.

Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task. Typically, transferability is either measured experimentally or inferred through task relatedness, which is often defined without a clear operational meaning. In this paper, we present a novel metric, H-score, an easily-computable evaluation function that estimates the performance of transferred representations from one task to another in classification problems using statistical and information theoretic principles. Experiments on real image data show that our metric is not only consistent with the empirical transferability measurement, but also useful to practitioners in applications such as source model selection and task transfer curriculum learning.

Summary quality assessment metrics have two categories: reference-based and reference-free. Reference-based metrics are theoretically more accurate but are limited by the availability and quality of the human-written references, which are both difficulty to ensure. This inspires the development of reference-free metrics, which are independent from human-written references, in the past few years. However, existing reference-free metrics cannot be both zero-shot and accurate. In this paper, we propose a zero-shot but accurate reference-free approach in a sneaky way: feeding documents, based upon which summaries generated, as references into reference-based metrics. Experimental results show that this zero-shot approach can give us the best-performing reference-free metrics on nearly all aspects on several recently-released datasets, even beating reference-free metrics specifically trained for this task sometimes. We further investigate what reference-based metrics can benefit from such repurposing and whether our additional tweaks help.

The quality of knowledge retrieval is crucial in knowledge-intensive conversations. Two common strategies to improve the retrieval quality are finetuning the retriever or generating a self-contained query, while they encounter heavy burdens on expensive computation and elaborate annotations. In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. Without extra supervision, the end-to-end joint training of QKConv explores multiple candidate queries and utilizes corresponding selected knowledge to yield the target response. To evaluate the effectiveness of the proposed method, we conducted comprehensive experiments on conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results demonstrate that QKConv achieves state-of-the-art performance compared to unsupervised methods and competitive performance compared to supervised methods.

In this paper, we carry out numerical analysis to prove convergence of a novel sample-wise back-propagation method for training a class of stochastic neural networks (SNNs). The structure of the SNN is formulated as discretization of a stochastic differential equation (SDE). A stochastic optimal control framework is introduced to model the training procedure, and a sample-wise approximation scheme for the adjoint backward SDE is applied to improve the efficiency of the stochastic optimal control solver, which is equivalent to the back-propagation for training the SNN. The convergence analysis is derived with and without convexity assumption for optimization of the SNN parameters. Especially, our analysis indicates that the number of SNN training steps should be proportional to the square of the number of layers in the convex optimization case. Numerical experiments are carried out to validate the analysis results, and the performance of the sample-wise back-propagation method for training SNNs is examined by benchmark machine learning examples.