本文提出了一种新的方法，称为模块化语法进化（MGE），以验证以下假设，即限制了神经进化的解决方案空间到模块化和简单的神经网络，可以有效地生成较小，更结构化的神经网络，同时提供可接受的（在某些方面）案例优于大型数据集的精度。 MGE还在两个方向上增强了最新的语法演化（GE）方法。首先，MGE的表示是模块化的，因为每个个体都有一组基因，并且每个基因都通过语法规则映射到神经元。其次，所提出的表示形式减轻了GE的两个重要缺点，即表示较低的表示性和弱位置，以生成具有大量神经元的模块化和多层网络。我们使用MGE定义和评估具有和不具有模块化的五种不同形式的结构，并找到没有耦合更有效的单层模块。我们的实验表明，模块化有助于更快地找到更好的神经网络。我们使用了十个具有不同尺寸，功能计数和输出类计数的众所周知的分类基准验证了提出的方法。我们的实验结果表明，MGE相对于现有的神经进化方法提供了卓越的准确性，并且返回分类器比其他机器学习生成的分类器要简单得多。最后，我们从经验上证明，MGE在局部性和可伸缩性属性方面优于其他GE方法。

未来发生的一些事件对于公司，政府甚至我们的个人生活可能很重要。在建立之前对这些事件的预测有助于有效的决策。我们称此类事件新兴实体。它们尚未发生，在KB中没有有关它们的信息。但是，有些线索存在于不同领域，尤其是在社交媒体上。因此，检索这些类型的实体是可能的。本文提出了一种早期发现新兴实体的方法。我们使用短消息的语义聚类。为了评估提案的绩效，我们设计和利用了绩效评估指标。结果表明，我们提出的方法发现了Twitter趋势并非总是能够有能力的那些新兴实体。

推荐系统（RSS）旨在模拟和预测用户偏好，同时与诸如兴趣点（POI）的项目进行交互。这些系统面临着几种挑战，例如数据稀疏性，限制了它们的有效性。在本文中，我们通过将社会，地理和时间信息纳入矩阵分解（MF）技术来解决这个问题。为此，我们基于两个因素模拟社会影响：用户之间的相似之处在常见的办理登机手续和它们之间的友谊方面。我们根据明确的友谊网络和用户之间的高支票重叠介绍了两个友谊。我们基于用户的地理活动中心友好算法。结果表明，我们所提出的模型在两个真实的数据集中优于最先进的。更具体地说，我们的消融研究表明，社会模式在精确的@ 10分别在Gowalla和Yelp数据集中提高了我们所提出的POI推荐系统的表现。

Code generation from text requires understanding the user's intent from a natural language description (NLD) and generating an executable program code snippet that satisfies this intent. While recent pretrained language models (PLMs) demonstrate remarkable performance for this task, these models fail when the given NLD is ambiguous due to the lack of enough specifications for generating a high-quality code snippet. In this work, we introduce a novel and more realistic setup for this task. We hypothesize that ambiguities in the specifications of an NLD are resolved by asking clarification questions (CQs). Therefore, we collect and introduce a new dataset named CodeClarQA containing NLD-Code pairs with created CQAs. We evaluate the performance of PLMs for code generation on our dataset. The empirical results support our hypothesis that clarifications result in more precise generated code, as shown by an improvement of 17.52 in BLEU, 12.72 in CodeBLEU, and 7.7\% in the exact match. Alongside this, our task and dataset introduce new challenges to the community, including when and what CQs should be asked.

In data-driven systems, data exploration is imperative for making real-time decisions. However, big data is stored in massive databases that are difficult to retrieve. Approximate Query Processing (AQP) is a technique for providing approximate answers to aggregate queries based on a summary of the data (synopsis) that closely replicates the behavior of the actual data, which can be useful where an approximate answer to the queries would be acceptable in a fraction of the real execution time. In this paper, we discuss the use of Generative Adversarial Networks (GANs) for generating tabular data that can be employed in AQP for synopsis construction. We first discuss the challenges associated with constructing synopses in relational databases and then introduce solutions to those challenges. Following that, we organized statistical metrics to evaluate the quality of the generated synopses. We conclude that tabular data complexity makes it difficult for algorithms to understand relational database semantics during training, and improved versions of tabular GANs are capable of constructing synopses to revolutionize data-driven decision-making systems.

Hawkes processes have recently risen to the forefront of tools when it comes to modeling and generating sequential events data. Multidimensional Hawkes processes model both the self and cross-excitation between different types of events and have been applied successfully in various domain such as finance, epidemiology and personalized recommendations, among others. In this work we present an adaptation of the Frank-Wolfe algorithm for learning multidimensional Hawkes processes. Experimental results show that our approach has better or on par accuracy in terms of parameter estimation than other first order methods, while enjoying a significantly faster runtime.

Graph neural networks have shown to learn effective node representations, enabling node-, link-, and graph-level inference. Conventional graph networks assume static relations between nodes, while relations between entities in a video often evolve over time, with nodes entering and exiting dynamically. In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations. To address this problem, we propose MTD-GNN, a graph network for predicting temporally-dynamic edges for multiple types of relations. We propose a factorized spatio-temporal graph attention layer to learn dynamic node representations and present a multi-task edge prediction loss that models multiple relations simultaneously. The proposed architecture operates on top of scene graphs that we obtain from videos through object detection and spatio-temporal linking. Experimental evaluations on ActionGenome and CLEVRER show that modeling multiple relations in our temporally-dynamic graph network can be mutually beneficial, outperforming existing static and spatio-temporal graph neural networks, as well as state-of-the-art predicate classification methods.

The Longest Common Subsequence (LCS) is the problem of finding a subsequence among a set of strings that has two properties of being common to all and is the longest. The LCS has applications in computational biology and text editing, among many others. Due to the NP-hardness of the general longest common subsequence, numerous heuristic algorithms and solvers have been proposed to give the best possible solution for different sets of strings. None of them has the best performance for all types of sets. In addition, there is no method to specify the type of a given set of strings. Besides that, the available hyper-heuristic is not efficient and fast enough to solve this problem in real-world applications. This paper proposes a novel hyper-heuristic to solve the longest common subsequence problem using a novel criterion to classify a set of strings based on their similarity. To do this, we offer a general stochastic framework to identify the type of a given set of strings. Following that, we introduce the set similarity dichotomizer ($S^2D$) algorithm based on the framework that divides the type of sets into two. This algorithm is introduced for the first time in this paper and opens a new way to go beyond the current LCS solvers. Then, we present a novel hyper-heuristic that exploits the $S^2D$ and one of the internal properties of the set to choose the best matching heuristic among a set of heuristics. We compare the results on benchmark datasets with the best heuristics and hyper-heuristics. The results show a higher performance of our proposed hyper-heuristic in both quality of solutions and run time factors.

Continuous behavioural authentication methods add a unique layer of security by allowing individuals to verify their unique identity when accessing a device. Maintaining session authenticity is now feasible by monitoring users' behaviour while interacting with a mobile or Internet of Things (IoT) device, making credential theft and session hijacking ineffective. Such a technique is made possible by integrating the power of artificial intelligence and Machine Learning (ML). Most of the literature focuses on training machine learning for the user by transmitting their data to an external server, subject to private user data exposure to threats. In this paper, we propose a novel Federated Learning (FL) approach that protects the anonymity of user data and maintains the security of his data. We present a warmup approach that provides a significant accuracy increase. In addition, we leverage the transfer learning technique based on feature extraction to boost the models' performance. Our extensive experiments based on four datasets: MNIST, FEMNIST, CIFAR-10 and UMDAA-02-FD, show a significant increase in user authentication accuracy while maintaining user privacy and data security.

Current pre-trained language models rely on large datasets for achieving state-of-the-art performance. However, past research has shown that not all examples in a dataset are equally important during training. In fact, it is sometimes possible to prune a considerable fraction of the training set while maintaining the test performance. Established on standard vision benchmarks, two gradient-based scoring metrics for finding important examples are GraNd and its estimated version, EL2N. In this work, we employ these two metrics for the first time in NLP. We demonstrate that these metrics need to be computed after at least one epoch of fine-tuning and they are not reliable in early steps. Furthermore, we show that by pruning a small portion of the examples with the highest GraNd/EL2N scores, we can not only preserve the test accuracy, but also surpass it. This paper details adjustments and implementation choices which enable GraNd and EL2N to be applied to NLP.