The application of superconducting materials is becoming more and more widespread. Traditionally, the discovery of new superconducting materials relies on the experience of experts and a large number of "trial and error" experiments, which not only increases the cost of experiments but also prolongs the period of discovering new superconducting materials. In recent years, machine learning has been increasingly applied to materials science. Based on this, this manuscript proposes the use of XGBoost model to identify superconductors; the first application of deep forest model to predict the critical temperature of superconductors; the first application of deep forest to predict the band gap of materials; and application of a new sub-network model to predict the Fermi energy level of materials. Compared with our known similar literature, all the above algorithms reach state-of-the-art. Finally, this manuscript uses the above models to search the COD public dataset and identify 50 candidate superconducting materials with possible critical temperature greater than 90 K.

电子商务查询通常简短而模棱两可。因此，查询理解通常使用查询重写来消除用户输入查询。在使用电子商务搜索工具时，用户倾向于在购买之前输入多个搜索，我们称之为上下文。这些历史搜索包含有关用户真正购物意图的上下文见解。因此，对此类上下文信息进行建模对于更好的查询重写模型至关重要。但是，现有的查询重写模型忽略了用户的历史行为，而仅考虑即时搜索查询，这通常是一个简短的字符串，提供有关真实购物意图的有限信息。我们建议一个端到端的上下文感知查询重写模型来弥合此差距，从而考虑了搜索上下文。具体而言，我们的模型使用历史记录搜索查询及其包含的单词构建了会话图。然后，我们采用图形注意机制，该机制对交叉关系进行建模并计算会话的上下文信息。随后，模型通过使用聚合网络将上下文信息与即时搜索查询组合来计算会话表示。然后将会话表示形式解码以生成重写的查询。从经验上讲，我们证明了我们方法对各种指标下最先进的方法的优越性。在从线购物平台的内部数据上，通过介绍上下文信息，我们的模型在MRR（平均值等级）指标下取得了11.6％的改善，并在HIT@16度量指标（命中率指标）下提高了20.1％使用最佳基线方法（基于变压器的模型）。

已经提出了图形神经网络（GNN）预训练方法来增强GNN的能力。具体而言，首先在大规模的未标记图上预先训练GNN，然后在单独的小标记图上进行微调，以用于下游应用程序，例如节点分类。一种流行的预训练方法是掩盖一部分边缘，并接受了GNN的培训以恢复它们。但是，这种生成方法遭受了图不匹配。也就是说，输入到GNN偏离原始图的蒙版图。为了减轻此问题，我们提出了DIP-GNN（图神经网络的歧视性预训练）。具体来说，我们训练一个发电机以恢复蒙版边缘的身份，同时，我们训练一个判别器，以区分生成的边缘与原始图的边缘。在我们的框架中，鉴别器看到的图形更好地匹配原始图，因为生成器可以恢复蒙版边缘的一部分。大规模同质和异质图的广泛实验证明了该框架的有效性。

随着人工智能的快速发展，材料数据库和机器学习的结合促进了材料信息学的进步。因为铝合金在许多领域被广泛使用，因此预测铝合金的性质是很重要的。在本文中，使用Al-Cu-Mg-X（X：Zn，Zr等）合金的数据输入组成，衰老条件（时间和温度）并预测其硬度。分别提出了基于自动机器学习和引入深度神经网络二级学习者的注意机制的集合学习解决方案。实验结果表明，选择正确的二级学习者可以进一步提高模型的预测准确性。该手稿介绍了基于深神经网络的二级学习者的注意机制，并获得了具有更好性能的融合模型。最佳模型的R平方为0.9697，MAE为3.4518hv。

在不规则的几何结构和高维空间的情况下，三维点云学习被广泛应用，但是点云仍无法令人满意地处理分类和识别任务。在3D空间中，点云由于其密度而倾向于具有规则的欧几里得结构。相反，由于高维度，高维空间的空间结构更为复杂，而点云主要在非欧洲结构中呈现。此外，在当前的3D点云分类算法中，基于欧几里得距离的规范胶囊算法很难有效分解并有效地识别非欧几里得结构。因此，针对3D和高维空间中非欧国人结构的点云分类任务时，本文是指基于测量距离的LLE算法，以优化并提出了高维点云的无监督算法。在本文中，在提取过程中考虑了点云的几何特征，以便将高维的非欧几里得结构转变为具有保持空间几何特征的较低维度的欧几里得结构。为了验证高维点云胶囊的无监督算法的可行性，在瑞士滚动数据集，点云MNIST数据集和点云LFW数据集中进行了实验。结果表明，（1）可以在瑞士滚动数据集中有效地确定（1）非欧几里得结构； （2）在Point Clouds MNIST数据集中实现了重要的无监督学习效果。总之，本文提出的高维点云无监督算法有利于扩展当前点云分类和识别任务的应用程序方案。

从理论上讲，通过引入蛋白质3D结构信息，可以改善化合物蛋白结合亲和力（CPA）中计算模型的准确性。但是，由于缺乏有效编码信息蛋白质特征的有效方法，这些模型中的大多数仍然存在低精度。主要的挑战是如何结合多模式信息，例如蛋白质的残基序列，残基原子坐标和扭转角。为了解决这个问题，我们开发了快速的进化关注和彻底的图形神经网络（featnn），以促进蛋白质3D结构信息的应用以预测CPA。具体而言，我们建立了一种新型的端到端结构，以共同嵌入扭转矩阵，离散距离矩阵以及蛋白质和提取具有深图卷积层的复合特征的序列信息。此外，引入了一种新的成对映射注意机制，以全面了解蛋白质和化合物之间的潜在相互作用信息。在CPA预测中，R2系数升高约21.33％，在CPA预测中的各种最新基准都大大优于各种最新基线。因此，壮举为高度准确的CPA预测提供了出色的方法，并促进了候选药物的高通量虚拟筛查。

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.

We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning. We derive a theory of human-like few-shot learning from von-Neuman-Landauer's principle. modelling human learning is difficult as how people learn varies from one to another. Under commonly accepted definitions, we prove that all human or animal few-shot learning, and major models including Free Energy Principle and Bayesian Program Learning that model such learning, approximate our theory, under Church-Turing thesis. We find that deep generative model like variational autoencoder (VAE) can be used to approximate our theory and perform significantly better than baseline models including deep neural networks, for image recognition, low resource language processing, and character recognition.

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.

We consider infinite horizon Markov decision processes (MDPs) with fast-slow structure, meaning that certain parts of the state space move "fast" (and in a sense, are more influential) while other parts transition more "slowly." Such structure is common in real-world problems where sequential decisions need to be made at high frequencies, yet information that varies at a slower timescale also influences the optimal policy. Examples include: (1) service allocation for a multi-class queue with (slowly varying) stochastic costs, (2) a restless multi-armed bandit with an environmental state, and (3) energy demand response, where both day-ahead and real-time prices play a role in the firm's revenue. Models that fully capture these problems often result in MDPs with large state spaces and large effective time horizons (due to frequent decisions), rendering them computationally intractable. We propose an approximate dynamic programming algorithmic framework based on the idea of "freezing" the slow states, solving a set of simpler finite-horizon MDPs (the lower-level MDPs), and applying value iteration (VI) to an auxiliary MDP that transitions on a slower timescale (the upper-level MDP). We also extend the technique to a function approximation setting, where a feature-based linear architecture is used. On the theoretical side, we analyze the regret incurred by each variant of our frozen-state approach. Finally, we give empirical evidence that the frozen-state approach generates effective policies using just a fraction of the computational cost, while illustrating that simply omitting slow states from the decision modeling is often not a viable heuristic.