最近的顺序推荐模型越来越多地依赖连续的短期用户相互作用序列来建模用户兴趣。但是，这些方法引起了人们对短期和长期利益的关注。 （1）{\ IT短期}：交互序列可能不是由单一的兴趣引起的，而是来自几个相互交织的利益，即使在短时间内，也导致了它们无法模拟Skip行为的失败； （2）{\ it长期}：相互作用序列主要是在离散的间隔内稀疏观察，而不是长期连续的。这使得难以推断长期利益，因为只能考虑到跨序列的利益动态，因此只能得出离散的利息表示。在这项研究中，我们通过学习来解决这些问题（1）短期利益的多尺度表示； （2）长期利益的动态意识表示。为此，我们提出了一个\ textbf {i} nterest \ textbf {d} ynamics建模框架，使用生成\ textbf {n} eural \ textbf {p textbf {p} rocesses，coincined IDNP，以从功能角度来看，以模拟用户兴趣。 IDNP学习了一个全球兴趣函数家族，以定义每个用户的长期兴趣作为功能实例化，从而通过功能连续性表现出兴趣动态。具体而言，IDNP首先将每个用户的短期交互编码为多尺度表示，然后将其汇总为用户上下文。通过将潜在的全球兴趣与用户上下文相结合，IDNP然后重建长期用户兴趣功能，并在即将到来的查询时间段上预测交互。此外，即使相互作用序列受到限制和非连续性，IDNP也可以建模此类兴趣功能。在四个现实世界数据集上进行的广泛实验表明，我们的模型在各种评估指标上的最先进。

机器学习理论中的主要开放问题之一是表征过度参数化的政权中的概括，在该制度中，大多数传统的概括范围变得不一致。在许多情况下，它们的失败可以归因于掩盖训练算法与基础数据分布之间的关键相互作用。为了解决这一缺点，我们提出了一个名为兼容性的概念，该概念以与数据相关的和算法相关的方式定量地表征了概括。通过考虑整个训练轨迹并专注于早期迭代的迭代术，兼容性充分利用了算法信息，因此可以提供更好的概括保证。我们通过理论上研究与梯度下降过度参数化的线性回归设置的兼容性来验证这一点。具体而言，我们执行与数据相关的轨迹分析，并在这种设置下得出足够的兼容性条件。我们的理论结果表明，从兼容性的意义上讲，概括性对问题实例的限制明显弱，而不是上次迭代分析。

我们建议基于张量CP分解模拟矩阵时间序列。而不是使用作为估计CP分解的标准做法的迭代算法，我们提出了一种基于由底层过程的串行依赖结构构成的广义特征分析的新的和单遍估计过程。新程序的一个关键思想是将在具有全排序矩阵的秩减少矩阵方面将概要的矩阵预定为下方，以避免以前的前者的复杂性可以为零，有限和无限。在没有实践性的情况下，在一般环境下建立了渐近理论。例如，图2示出了CP - 分解中的所有组件系数矢量，根据时间序列尺寸与样本大小之间的相对大小一致地估计CP分解中的所有组件系数矢量。建议的模型和估计方法进一步用模拟和真实数据说明;显示有效维度降低模型和预测矩阵时间序列。

现场感知对于驾驶决策和交通安全至关重要。然而，作为一种常见的天气，经常出现在现实世界中，特别是在山区，难以准确地观察周围环境。因此，精确地估计了有雾天气下的能见度，可以显着利益交通管理和安全性。要解决此问题，大多数现有方法使用在道路上的固定位置上装备的专业仪器来执行可见性测量;这些方法昂贵且更柔韧。在本文中，我们提出了一种创新的端到端卷积神经网络框架，以估计利用koschmieder的定律专门使用图像数据来估计能见度。所提出的方法通过将物理模型集成到所提出的框架中来估计可见性，而不是通过卷积神经工作直接预测可见度值。此外，我们估计与先前可见性测量方法的可见性地图的可见性估算，其单独预测整个图像的单个值。因此，我们的方法的估计结果是更有信息丰富的，特别是在不均匀的雾场景中，这可以有利于开发更精确的早期预警系统进行有雾的天气，从而更好地保护智能交通基础设施系统并促进其发展。为了验证所提出的框架，使用AIRSIM平台收集包含不同浓度的3,000个有雾图像的虚拟数据集Faci。详细实验表明，该方法达到了最先进的方法竞争性能。

高光谱（HS）图像的特征在于近似连续的频谱信息，通过捕获微妙的光谱差异来实现材料的精细识别。由于它们出色的局部上下文建模能力，已被证明是HS Image分类中的强大特征提取器的卷积神经网络（CNNS）。但是，由于其固有的网络骨干的限制，CNNS无法挖掘并表示频谱签名的序列属性。为了解决这个问题，我们从与变换器的顺序透视重新考虑HS图像分类，并提出一个名为\ ul {spectralformer}的新型骨干网。除了经典变压器中的带明智的表示之外，Spectralformer能够从HS图像的相邻频带中学习频谱局部序列信息，产生群体方向谱嵌入。更重要的是，为了减少在层面传播过程中丢失有价值信息的可能性，我们通过自适应地学习跨层熔断“软”残留物来传达横向跳过连接以传送从浅层到深层的存储器样组件。值得注意的是，所提出的光谱变压器是一个高度灵活的骨干网络，可以适用于像素和修补程序的输入。我们通过进行广泛的实验评估三个HS数据集上提出的光谱变压器的分类性能，显示了经典变压器的优越性，与最先进的骨干网络相比，实现了显着改进。这项工作的代码将在https://github.com/danfenghong/ieee_tgrs_spectralformer下获得，以便再现性。

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.

Theoretical properties of bilevel problems are well studied when the lower-level problem is strongly convex. In this work, we focus on bilevel optimization problems without the strong-convexity assumption. In these cases, we first show that the common local optimality measures such as KKT condition or regularization can lead to undesired consequences. Then, we aim to identify the mildest conditions that make bilevel problems tractable. We identify two classes of growth conditions on the lower-level objective that leads to continuity. Under these assumptions, we show that the local optimality of the bilevel problem can be defined via the Goldstein stationarity condition of the hyper-objective. We then propose the Inexact Gradient-Free Method (IGFM) to solve the bilevel problem, using an approximate zeroth order oracle that is of independent interest. Our non-asymptotic analysis demonstrates that the proposed method can find a $(\delta, \varepsilon)$ Goldstein stationary point for bilevel problems with a zeroth order oracle complexity that is polynomial in $d, 1/\delta$ and $1/\varepsilon$.

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.

Stance detection refers to the task of extracting the standpoint (Favor, Against or Neither) towards a target in given texts. Such research gains increasing attention with the proliferation of social media contents. The conventional framework of handling stance detection is converting it into text classification tasks. Deep learning models have already replaced rule-based models and traditional machine learning models in solving such problems. Current deep neural networks are facing two main challenges which are insufficient labeled data and information in social media posts and the unexplainable nature of deep learning models. A new pre-trained language model chatGPT was launched on Nov 30, 2022. For the stance detection tasks, our experiments show that ChatGPT can achieve SOTA or similar performance for commonly used datasets including SemEval-2016 and P-Stance. At the same time, ChatGPT can provide explanation for its own prediction, which is beyond the capability of any existing model. The explanations for the cases it cannot provide classification results are especially useful. ChatGPT has the potential to be the best AI model for stance detection tasks in NLP, or at least change the research paradigm of this field. ChatGPT also opens up the possibility of building explanatory AI for stance detection.

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.