The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent work expects to get query-informed representations of documents. During training, it expands the document with a real query, while replacing the real query with a generated pseudo query at inference. This discrepancy between training and inference makes the dense retrieval model pay more attention to the query information but ignore the document when computing the document representation. As a result, it even performs worse than the vanilla dense retrieval model, since its performance depends heavily on the relevance between the generated queries and the real query. In this paper, we propose a curriculum sampling strategy, which also resorts to the pseudo query at training and gradually increases the relevance of the generated query to the real query. In this way, the retrieval model can learn to extend its attention from the document only to both the document and query, hence getting high-quality query-informed document representations. Experimental results on several passage retrieval datasets show that our approach outperforms the previous dense retrieval methods1.

Graph-based change point detection (CPD) play an irreplaceable role in discovering anomalous graphs in the time-varying network. While several techniques have been proposed to detect change points by identifying whether there is a significant difference between the target network and successive previous ones, they neglect the natural evolution of the network. In practice, real-world graphs such as social networks, traffic networks, and rating networks are constantly evolving over time. Considering this problem, we treat the problem as a prediction task and propose a novel CPD method for dynamic graphs via a latent evolution model. Our method focuses on learning the low-dimensional representations of networks and capturing the evolving patterns of these learned latent representations simultaneously. After having the evolving patterns, a prediction of the target network can be achieved. Then, we can detect the change points by comparing the prediction and the actual network by leveraging a trade-off strategy, which balances the importance between the prediction network and the normal graph pattern extracted from previous networks. Intensive experiments conducted on both synthetic and real-world datasets show the effectiveness and superiority of our model.

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model. Traditional knowledge distillation methods include response-based methods and feature-based methods. Response-based methods are used the most widely but suffer from lower upper limit of model performance, while feature-based methods have constraints on the vocabularies and tokenizers. In this paper, we propose a tokenizer-free method liberal feature-based distillation (LEAD). LEAD aligns the distribution between teacher model and student model, which is effective, extendable, portable and has no requirements on vocabularies, tokenizer, or model architecture. Extensive experiments show the effectiveness of LEAD on several widely-used benchmarks, including MS MARCO Passage, TREC Passage 19, TREC Passage 20, MS MARCO Document, TREC Document 19 and TREC Document 20.

The interplay between quantum physics and machine learning gives rise to the emergent frontier of quantum machine learning, where advanced quantum learning models may outperform their classical counterparts in solving certain challenging problems. However, quantum learning systems are vulnerable to adversarial attacks: adding tiny carefully-crafted perturbations on legitimate input samples can cause misclassifications. To address this issue, we propose a general scheme to protect quantum learning systems from adversarial attacks by randomly encoding the legitimate data samples through unitary or quantum error correction encoders. In particular, we rigorously prove that both global and local random unitary encoders lead to exponentially vanishing gradients (i.e. barren plateaus) for any variational quantum circuits that aim to add adversarial perturbations, independent of the input data and the inner structures of adversarial circuits and quantum classifiers. In addition, we prove a rigorous bound on the vulnerability of quantum classifiers under local unitary adversarial attacks. We show that random black-box quantum error correction encoders can protect quantum classifiers against local adversarial noises and their robustness increases as we concatenate error correction codes. To quantify the robustness enhancement, we adapt quantum differential privacy as a measure of the prediction stability for quantum classifiers. Our results establish versatile defense strategies for quantum classifiers against adversarial perturbations, which provide valuable guidance to enhance the reliability and security for both near-term and future quantum learning technologies.

The matrix-based R\'enyi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical inference and machine learning tasks. However, this information theoretical quantity is not robust against noise in the data, and is computationally prohibitive in large-scale applications. To address these issues, we propose a novel measure of information, termed low-rank matrix-based R\'enyi's entropy, based on low-rank representations of infinitely divisible kernel matrices. The proposed entropy functional inherits the specialty of of the original definition to directly quantify information from data, but enjoys additional advantages including robustness and effective calculation. Specifically, our low-rank variant is more sensitive to informative perturbations induced by changes in underlying distributions, while being insensitive to uninformative ones caused by noises. Moreover, low-rank R\'enyi's entropy can be efficiently approximated by random projection and Lanczos iteration techniques, reducing the overall complexity from $\mathcal{O}(n^3)$ to $\mathcal{O}(n^2 s)$ or even $\mathcal{O}(ns^2)$, where $n$ is the number of data samples and $s \ll n$. We conduct large-scale experiments to evaluate the effectiveness of this new information measure, demonstrating superior results compared to matrix-based R\'enyi's entropy in terms of both performance and computational efficiency.

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by few other works. We also demonstrate that model pre-training and sparse scaling using Mixture-of-Experts bring large gains to translation performance. The mined data and models are freely available.

Three-phase PWM voltage-source rectifier (VSR) systems have been widely used in various energy conversion systems, where current sensors are the key component for state monitoring and system control. The current sensor faults may bring hidden danger or damage to the whole system; therefore, this paper proposed a random forest (RF) and current fault texture feature-based method for current sensor fault diagnosis in three-phase PWM VSR systems. First, the three-phase alternating currents (ACs) of the three-phase PWM VSR are collected to extract the current fault texture features, and no additional hardware sensors are needed to avoid causing additional unstable factors. Then, the current fault texture features are adopted to train the random forest current sensor fault detection and diagnosis (CSFDD) classifier, which is a data-driven CSFDD classifier. Finally, the effectiveness of the proposed method is verified by simulation experiments. The result shows that the current sensor faults can be detected and located successfully and that it can effectively provide fault locations for maintenance personnel to keep the stable operation of the whole system.

知识蒸馏是将知识从强大的教师转移到有效的学生模型的有效方法。理想情况下，我们希望老师越好，学生越好。但是，这种期望并不总是成真。通常，由于教师和学生之间的不可忽略的差距，更好的教师模型通过蒸馏导致不良学生。为了弥合差距，我们提出了一种渐进式蒸馏方法，以进行致密检索。产品由教师渐进式蒸馏和数据进行渐进的蒸馏组成，以逐步改善学生。我们对五个广泛使用的基准，MARCO通道，TREC Passage 19，TREC文档19，MARCO文档和自然问题进行了广泛的实验，其中POD在蒸馏方法中实现了密集检索的最新方法。代码和模型将发布。

神经网络实施的标准方法具有强大的功能近似功能，但在其预测中学习元表示和理性概率不确定性的能力受到限制。另一方面，高斯流程采用贝叶斯学习计划来估计这种不确定性，但受其效率和近似能力的限制。神经过程家族（NPF）打算通过利用神经网络来提供元学习预测性不确定性来提供两全其美的世界。近年来，这种潜力为家庭带来了重大的研究活动。因此，需要对NPF模型进行全面调查，以组织和联系其动机，方法论和实验。本文打算解决这一差距，同时更深入地研究有关家庭成员的制定，研究主题和应用程序。我们阐明了它们的潜力，即在一个雨伞下带来其他深度学习领域的最新进展。然后，我们提供了对家庭的严格分类法，并从经验上证明了它们对在1-D，2-D和3-D输入域上运行的数据生成功能进行建模的功能。最后，我们通过讨论有关有希望的方向的观点，这些方向可以推动该领域的研究进展。我们的实验代码将在https://github.com/srvcodes/neural-processes-survey上提供。

从观察数据中恢复基本的定向无环形结构（DAG），由于DAG受限的优化问题的组合性质，因此极具挑战性。最近，通过将DAG约束将DAG的限制定义为平滑的平等性，通常基于邻接矩阵上的多项式，将DAG学习作为连续优化问题。现有方法将非常小的系数放在高阶多项式术语上以进行稳定，因为它们认为由于数字爆炸而导致高阶项上的大系数有害。相反，我们发现，高阶术语上的大系数对DAG学习有益，当邻接矩阵的光谱辐射小时，高阶术语的较大系数可以比小尺寸近似于小的限制。同行。基于此，我们提出了一种具有有效截短的矩阵功率迭代的新型DAG学习方法，以近似于基于几何序列的DAG约束。从经验上讲，我们的DAG学习方法在各种环境中的表现优于先前的最新方法，在结构锤距离上通常以3倍或以上的倍数。