对比模式挖掘（CPM）是数据挖掘的重要且流行的子场。传统的顺序模式无法描述不同类别数据之间的对比度信息，而涉及对比概念的对比模式可以描述不同对比条件下数据集之间的显着差异。根据该领域发表的论文数量，我们发现研究人员对CPM的兴趣仍然活跃。由于CPM有许多研究问题和研究方法。该领域的新研究人员很难在短时间内了解该领域的一般状况。因此，本文的目的是为对比模式挖掘的研究方向提供最新的全面概述。首先，我们对CPM提出了深入的理解，包括评估歧视能力的基本概念，类型，采矿策略和指标。然后，我们根据CPM方法根据其特征分类为基于边界的算法，基于树的算法，基于进化模糊的系统算法，基于决策树的算法和其他算法。此外，我们列出了这些方法的经典算法，并讨论它们的优势和缺点。提出了CPM中的高级主题。最后，我们通过讨论该领域的挑战和机遇来结束调查。

为了减轻从头开始构建知识图（kg）的挑战，更一般的任务是使用开放式语料库中的三元组丰富一个kg，那里获得的三元组包含嘈杂的实体和关系。在保持知识代表的质量的同时，以新收获的三元组丰富一个公园，这是一项挑战。本文建议使用从附加语料库中收集的信息来完善kg的系统。为此，我们将任务制定为两个耦合子任务，即加入事件提取（JEE）和知识图融合（KGF）。然后，我们提出了一个协作知识图融合框架，以允许我们的子任务以交替的方式相互协助。更具体地说，探险家执行了由地面注释和主管提供的现有KG监督的JEE。然后，主管评估了探险家提取的三元组，并用高度排名的人来丰富KG。为了实施此评估，我们进一步提出了一种翻译的关系一致性评分机制，以对齐并将提取的三元组对齐为先前的kg。实验验证了这种合作既可以提高JEE和KGF的表现。

随着对比学习的兴起，无人监督的图形表示学习最近一直蓬勃发展，甚至超过了一些机器学习任务中的监督对应物。图表表示的大多数对比模型学习侧重于最大化本地和全局嵌入之间的互信息，或主要取决于节点级别的对比嵌入。然而，它们仍然不足以全面探索网络拓扑的本地和全球视图。虽然前者认为本地全球关系，但其粗略的全球信息导致本地和全球观点之间的思考。后者注重节点级别对齐，以便全局视图的作用出现不起眼。为避免落入这两个极端情况，我们通过对比群集分配来提出一种新颖的无监督图形表示模型，称为GCCA。通过组合聚类算法和对比学习，它有动力综合利用本地和全球信息。这不仅促进了对比效果，而且还提供了更高质量的图形信息。同时，GCCA进一步挖掘群集级信息，这使得它能够了解除了图形拓扑之外的节点之间的难以捉摸的关联。具体地，我们首先使用不同的图形增强策略生成两个增强的图形，然后使用聚类算法分别获取其群集分配和原型。所提出的GCCA进一步强制不同增强图中的相同节点来通过最小化交叉熵损失来互相识别它们的群集分配。为了展示其有效性，我们将在三个不同的下游任务中与最先进的模型进行比较。实验结果表明，GCCA在大多数任务中具有强大的竞争力。

虽然深度学习方法近年来取得了高级视频对象识别性能，但在视频中感知封闭对象仍然是一个非常具有挑战性的任务。为促进遮挡理解的发展，我们在遮挡方案中收集一个名为OVIS的大规模数据集，用于遮挡方案中的视频实例分段。 ovis由296K高质量的屏幕和901个遮挡场景组成。虽然我们的人类视觉系统可以通过语境推理和关联来感知那些遮挡物体，但我们的实验表明当前的视频了解系统不能。在ovis数据集上，所有基线方法都遇到了大约80％的大约80％的大约80％，这表明仍然有很长的路要走在复杂的真实情景中理解模糊物体和视频。为了促进对视频理解系统的新范式研究，我们基于OVI数据集启动了挑战。提交的顶级执行算法已经比我们的基线实现了更高的性能。在本文中，我们将介绍OVIS数据集，并通过分析基线的结果和提交的方法来进一步剖析。可以在http://songbai.site/ovis找到ovis数据集和挑战信息。

基于K-Nearest的邻居（KNN）的深度学习方法，由于其简单性和几何解释性，已应用于许多应用。但是，尚未对基于KNN的分类模型的鲁棒性进行彻底探索，而KNN攻击策略欠发达。在本文中，我们提出了对敌对的软knn（询问）损失，以设计更有效的KNN攻击策略，并为他们提供更好的防御能力。我们的问损失方法有两个优势。首先，与以前的作品中提出的目标相比，问问损失可以更好地近似KNN分类错误的可能性。其次，询问损失是可以解释的：它保留了扰动输入和课堂参考数据之间的相互信息。我们使用询问损失来生成一种名为Ask-Attack（Ask-ATK）的新颖攻击方法，该方法显示出相对于先前的KNN攻击，显示出了卓越的攻击效率和准确性降解。然后，基于Ask-ATK，我们得出了一个Ask \ supessline {def} ense（ask-def）方法，该方法优化了Ask-ATK引起的最坏情况训练损失。 CIFAR-10（IMAGENET）上的实验表明，（i）Ask-Atk成就$ \ geq 13 \％$（$ \ geq 13 \％$）提高了先前的KNN攻击的攻击成功率，以及（ii）ask-def $ \ geq 6.9 \％$（$ \ geq 3.5 \％$）在稳健性改善方面胜过常规的对抗训练方法。

我们的视频是否可以在场景中存在沉重的遮挡时感知对象？为了回答这个问题，我们收集一个名为OVIS的大型数据集，用于遮挡视频实例分段，即同时检测，段和跟踪遮挡场景中的实例。 OVIS由25个语义类别的296K高质量的掩码组成，通常发生对象遮挡。虽然我们的人类视觉系统可以通过语境推理和关联来理解那些被遮挡的情况，但我们的实验表明当前的视频理解系统不能。在ovis数据集上，最先进的算法实现的最高AP仅为16.3，这揭示了我们仍然处于创建对象，实例和视频中的新生阶段。我们还提出了一个简单的即插即用模块，执行时间特征校准，以补充闭塞引起的缺失对象线索。基于MaskTrack R-CNN和SIPMASK构建，我们在OVIS数据集中获得了显着的AP改进。 ovis数据集和项目代码可在http://songbai.site/ovis获得。

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference.

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.

Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships. However, this fundamental assumption cannot always be satisfied, as real-world graphs are always incomplete, noisy, or redundant. How to reveal the inherent graph structure in a unified way remains under-explored. We proposed PRI-GSL, a Graph Structure Learning framework guided by the Principle of Relevant Information, providing a simple and unified framework for identifying the self-organization and revealing the hidden structure. PRI-GSL learns a structure that contains the most relevant yet least redundant information quantified by von Neumann entropy and Quantum Jensen-Shannon divergence. PRI-GSL incorporates the evolution of quantum continuous walk with graph wavelets to encode node structural roles, showing in which way the nodes interplay and self-organize with the graph structure. Extensive experiments demonstrate the superior effectiveness and robustness of PRI-GSL.

Normalizing flow is a class of deep generative models for efficient sampling and density estimation. In practice, the flow often appears as a chain of invertible neural network blocks; to facilitate training, existing works have regularized flow trajectories and designed special network architectures. The current paper develops a neural ODE flow network inspired by the Jordan-Kinderleherer-Otto (JKO) scheme, which allows efficient block-wise training of the residual blocks and avoids inner loops of score matching or variational learning. As the JKO scheme unfolds the dynamic of gradient flow, the proposed model naturally stacks residual network blocks one-by-one, reducing the memory load and difficulty of performing end-to-end training of deep flow networks. We also develop adaptive time reparameterization of the flow network with a progressive refinement of the trajectory in probability space, which improves the model training efficiency and accuracy in practice. Using numerical experiments with synthetic and real data, we show that the proposed JKO-iFlow model achieves similar or better performance in generating new samples compared with existing flow and diffusion models at a significantly reduced computational and memory cost.