基于内容的图像检索（CIR）旨在通过同时理解示例图像和互补文本的组成来搜索目标图像，这可能会影响各种各样的现实世界应用，例如互联网搜索和时尚检索。在这种情况下，输入图像是搜索的直观上下文和背景，而相应的语言明确请求有关如何修改查询图像的特定特征以获取预期目标图像的新特征。此任务具有挑战性，因为它需要通过合并跨粒度语义更新来学习和理解复合图像文本表示。在本文中，我们通过小说\下划线{\ textbf {b}}来解决此任务\ textbf {s}} ition（\ textbf {boss}）带有混合反事实训练框架，通过从两个先前被忽视的角度研究它，从而为CIR任务提供了新的启示：\ emph {隐式自下而上的自下而上的sisitiol语言表示}和sisiol语言表示}和\ emph {显式晶状体构造的明显细粒度对应}。一方面，我们利用了从底部本地特征到顶部全局语义的跨模式嵌入的隐式相互作用和组成，从而保留和转换视觉表示在多个连续步骤中以语言语义为条件的视觉表示，以进行有效的目标图像搜索。另一方面，我们设计了一种混合反事实培训策略，可以减少模型对类似查询的歧义。

图形神经网络（GNN）由于其独特的能力扩展了机器学习（ML）方法，因此引起了极大的关注，该应用程序广泛定义为具有非结构化数据，尤其是图形。与其他机器学习（ML）方式相比，由于源自图类型的不规则性和异质性，图形神经网络（GNN）的加速度更具挑战性。但是，现有的努力主要集中在处理图形的不规则性上，并且没有研究其异质性。为此，我们提出了H-GCN，PL（可编程逻辑）和AIE（AI引擎）的混合加速器，以利用Xilinx Versal自适应计算加速度平台（ACAPS）的新兴异质性（ACAPS）来实现高表现GNN的确定。特别是，H-GCN根据其固有的异质性将每个图分为三个子图，并分别使用PL和AIE处理它们。为了进一步提高性能，我们探索了AIE的稀疏支持，并开发了一种有效的密度感知方法，以自动将稀疏矩阵矩阵乘法（SPMM）的瓷砖自动映射到收缩张量数阵列上。与最先进的GCN加速器相比，H-GCN平均达到1.1〜2.3倍的速度。

虽然注释大量的数据以满足复杂的学习模型，但对于许多现实世界中的应用程序可能会过于良好。主动学习（AL）和半监督学习（SSL）是两个有效但经常被隔离的方法，可以减轻渴望数据的问题。最近的一些研究探索了将AL和SSL相结合以更好地探测未标记数据的潜力。但是，几乎所有这些当代的SSL-AL作品都采用了简单的组合策略，忽略了SSL和AL的固有关系。此外，在处理大规模，高维数据集时，其他方法则遭受高计算成本。通过标记数据的行业实践的激励，我们提出了一种基于创新的基于不一致的虚拟对抗性积极学习（理想）算法，以进一步研究SSL-AL的潜在优势，并实现Al和SSL的相互增强，即SSL，即SSL宣传标签信息，以使标签信息无标记的样本信息并为Al提供平滑的嵌入，而AL排除了具有不一致的预测和相当不确定性的样品。我们通过不同粒度的增强策略（包括细粒度的连续扰动探索和粗粒数据转换）来估计未标记的样品的不一致。在文本和图像域中，广泛的实验验证了所提出的算法的有效性，并将其与最先进的基线进行了比较。两项实际案例研究可视化应用和部署所提出的数据采样算法的实际工业价值。

基于文本的图像标题（TextCAP）需要同时对视觉内容的理解并读取图像文本以生成自然语言描述。虽然一项任务可以教导机器来了解复杂的人类环境进一步鉴于我们日常环境中的文本是全部的，但它在正常标题中提出了额外的挑战。基于文本的图像直观地包含丰富和复杂的多模式关系内容，即可以从多视图而不是单个字幕来扩散图像细节。当然，我们可以介绍额外的配对训练数据以显示图像描述的多样性，这一过程是具有额外文本的文本映射对注释的劳动密集型和耗时。基于上述洞察力，我们调查如何使用未配对的培训范例来生成专注于不同图像零件的不同标题。我们提出了多模式关系图对抗性推论（魔法）框架，用于多样化和未配对的Textcap。该框架可以自适应地构建图形之间的图像和模型复杂关系的多个多模式关系图来表示描述性分集。此外，从建模的图表中开发了一种级联的生成对抗性网络，以推断图像句子特征对齐和语言相干水平中的未配对字幕。我们验证了魔法在从图像的不同关系信息项目生成不同标题时的有效性。实验结果表明，魔法可以在不使用任何图像标题训练对的情况下产生非常有前途的结果。

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even slightly boost the generalization performance. Theoretical understanding for such experimental observations are yet to be developed. This work makes the first attempt to study how different pruning fractions affect the model's gradient descent dynamics and generalization. Specifically, this work considers a classification task for overparameterized two-layer neural networks, where the network is randomly pruned according to different rates at the initialization. It is shown that as long as the pruning fraction is below a certain threshold, gradient descent can drive the training loss toward zero and the network exhibits good generalization performance. More surprisingly, the generalization bound gets better as the pruning fraction gets larger. To complement this positive result, this work further shows a negative result: there exists a large pruning fraction such that while gradient descent is still able to drive the training loss toward zero (by memorizing noise), the generalization performance is no better than random guessing. This further suggests that pruning can change the feature learning process, which leads to the performance drop of the pruned neural network. Up to our knowledge, this is the \textbf{first} generalization result for pruned neural networks, suggesting that pruning can improve the neural network's generalization.

Time-series anomaly detection is an important task and has been widely applied in the industry. Since manual data annotation is expensive and inefficient, most applications adopt unsupervised anomaly detection methods, but the results are usually sub-optimal and unsatisfactory to end customers. Weak supervision is a promising paradigm for obtaining considerable labels in a low-cost way, which enables the customers to label data by writing heuristic rules rather than annotating each instance individually. However, in the time-series domain, it is hard for people to write reasonable labeling functions as the time-series data is numerically continuous and difficult to be understood. In this paper, we propose a Label-Efficient Interactive Time-Series Anomaly Detection (LEIAD) system, which enables a user to improve the results of unsupervised anomaly detection by performing only a small amount of interactions with the system. To achieve this goal, the system integrates weak supervision and active learning collaboratively while generating labeling functions automatically using only a few labeled data. All of these techniques are complementary and can promote each other in a reinforced manner. We conduct experiments on three time-series anomaly detection datasets, demonstrating that the proposed system is superior to existing solutions in both weak supervision and active learning areas. Also, the system has been tested in a real scenario in industry to show its practicality.

As an important variant of entity alignment (EA), multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) with multiple modalities like images. However, current MMEA algorithms all adopt KG-level modality fusion strategies but ignore modality differences among individual entities, hurting the robustness to potential noise involved in modalities (e.g., unidentifiable images and relations). In this paper we present MEAformer, a multi-modal entity alignment transformer approach for meta modality hybrid, to dynamically predict the mutual correlation coefficients among modalities for instance-level feature fusion. A modal-aware hard entity replay strategy is also proposed for addressing vague entity details. Extensive experimental results show that our model not only achieves SOTA performance on multiple training scenarios including supervised, unsupervised, iterative, and low resource, but also has limited parameters, optimistic speed, and good interpretability. Our code will be available soon.

The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions. Though plagued with noise and stochasticity, videos consist of features that are organised in a spatiotemporal hierarchy, different features possessing different temporal dynamics. In this paper, we introduce Dynamic Latent Hierarchy (DLH) -- a deep hierarchical latent model that represents videos as a hierarchy of latent states that evolve over separate and fluid timescales. Each latent state is a mixture distribution with two components, representing the immediate past and the predicted future, causing the model to learn transitions only between sufficiently dissimilar states, while clustering temporally persistent states closer together. Using this unique property, DLH naturally discovers the spatiotemporal structure of a dataset and learns disentangled representations across its hierarchy. We hypothesise that this simplifies the task of modeling temporal dynamics of a video, improves the learning of long-term dependencies, and reduces error accumulation. As evidence, we demonstrate that DLH outperforms state-of-the-art benchmarks in video prediction, is able to better represent stochasticity, as well as to dynamically adjust its hierarchical and temporal structure. Our paper shows, among other things, how progress in representation learning can translate into progress in prediction tasks.

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning.