大型变压器模型实现了自然语言理解任务的最新状态，并越来越成为建模源代码的基线模型体系结构。通常，变压器在大型无监督的语料库中进行预训练，学习令牌表示和与通常可用的文本相关的转换，然后对特定的下游感兴趣的任务进行微调。虽然微调是一种尝试将模型调整为新领域的久经考验的方法（例如，在给定主题上提出问题，概括仍然是一个持续的挑战。在本文中，我们探索并评估了变形金刚的模型以进行个性化。在为Java方法生成单元测试的背景下，我们评估学习以使用多种个性化技术为特定的软件项目个性化。我们考虑三种关键方法：（i）自定义微调，这允许调整所有模型参数； （ii）轻巧的微调，它冻结了大多数模型的参数，可以单独调整令牌嵌入和SoftMax层或单独的最终层； （iii）前缀调整，该调谐使模型参数冻结，但优化了小型项目特定的前缀矢量。这些技术中的每一个都提供了总计算成本和预测性能的权衡，我们通过代码和特定任务指标，培训时间和总计算操作进行评估。我们比较了这些微调策略以生成代码，并讨论了各种部署方案中每个策略的潜在概括和成本益处。

In software development, it is common for programmers to copy-paste or port code snippets and then adapt them to their use case. This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable identifiers in a pasted snippet of code to the surrounding, preexisting source code. However, no existing approach has been shown to effectively address this task. In this paper, we introduce AdaptivePaste, a learning-based approach to source code adaptation, based on transformers and a dedicated dataflow-aware deobfuscation pre-training task to learn meaningful representations of variable usage patterns. We evaluate AdaptivePaste on a dataset of code snippets in Python. Results suggest that our model can learn to adapt source code with 79.8% accuracy. To evaluate how valuable is AdaptivePaste in practice, we perform a user study with 10 Python developers on a hundred real-world copy-paste instances. The results show that AdaptivePaste reduces the dwell time to nearly half the time it takes for manual code adaptation, and helps to avoid bugs. In addition, we utilize the participant feedback to identify potential avenues for improvement of AdaptivePaste.

协作软件开发是现代软件开发生命周期不可或缺的一部分，这对于大规模软件项目的成功至关重要。当多个开发人员围绕相同的代码进行同时更改时，可能会发生合并冲突。这种冲突停滞不前的请求和连续的集成管道数小时至几天，严重损害了开发人员的生产力。为了解决这个问题，我们介绍了Mergebert，这是一个新型的神经程序合并框架，基于令牌级别的三向差异和变压器编码器模型。通过利用合并冲突决议的受限性质，我们重新制定了将分辨率序列作为分类任务生成的任务，而不是从现实世界合并提交提交数据中提取的一组原始合并模式上进行分类任务。我们的模型可实现合并分辨率合成的63-68％精度，对现有的半结构化的性能提高了近3倍，而对神经程序合并工具的改善为2倍。最后，我们证明Mergebert足够灵活地使用Java，JavaScript，Typescript和C＃编程语言中的源代码文件。为了衡量Mergebert的实际使用，我们进行了一项用户研究，以评估Mergebert的建议，其中25位来自大型OSS项目的开发人员在他们遇到的122场现实世界冲突中进行了研究。结果表明，实际上，Mergebert决议将被接受比自动指标估计的精确度和准确性更高的速率。此外，我们使用参与者的反馈来确定未来改善Mergebert的途径。

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve the results of learning and accelerate it. We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning, where a task sequence is created based on the success rate of each task. In this setting, each task is an algorithmically created environment instance with a unique configuration. The algorithm selects the order of tasks that provide the fastest learning for agents. The probability of selecting any of the tasks for the next stage of learning is determined by evaluating its performance score in previous stages. Experiments were carried out in the Partially Observable Grid Environment for Multiple Agents (POGEMA) and Procgen benchmark. We demonstrate that SITP matches or surpasses the results of other curriculum design methods. Our method can be implemented with handful of minor modifications to any standard RL framework and provides useful prioritization with minimal computational overhead.

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.

Determining and predicting reservoir formation properties for newly drilled wells represents a significant challenge. One of the variations of these properties evaluation is well-interval similarity. Many methodologies for similarity learning exist: from rule-based approaches to deep neural networks. Recently, articles adopted, e.g. recurrent neural networks to build a similarity model as we deal with sequential data. Such an approach suffers from short-term memory, as it pays more attention to the end of a sequence. Neural network with Transformer architecture instead cast their attention over all sequences to make a decision. To make them more efficient in terms of computational time, we introduce a limited attention mechanism similar to Informer and Performer architectures. We conduct experiments on open datasets with more than 20 wells making our experiments reliable and suitable for industrial usage. The best results were obtained with our adaptation of the Informer variant of Transformer with ROC AUC 0.982. It outperforms classical approaches with ROC AUC 0.824, Recurrent neural networks with ROC AUC 0.934 and straightforward usage of Transformers with ROC AUC 0.961.

Recent increases in the computational demands of deep neural networks (DNNs) have sparked interest in efficient deep learning mechanisms, e.g., quantization or pruning. These mechanisms enable the construction of a small, efficient version of commercial-scale models with comparable accuracy, accelerating their deployment to resource-constrained devices. In this paper, we study the security considerations of publishing on-device variants of large-scale models. We first show that an adversary can exploit on-device models to make attacking the large models easier. In evaluations across 19 DNNs, by exploiting the published on-device models as a transfer prior, the adversarial vulnerability of the original commercial-scale models increases by up to 100x. We then show that the vulnerability increases as the similarity between a full-scale and its efficient model increase. Based on the insights, we propose a defense, $similarity$-$unpairing$, that fine-tunes on-device models with the objective of reducing the similarity. We evaluated our defense on all the 19 DNNs and found that it reduces the transferability up to 90% and the number of queries required by a factor of 10-100x. Our results suggest that further research is needed on the security (or even privacy) threats caused by publishing those efficient siblings.

The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\delta}, a set S of features is {\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.

In this article, the analysis of existing models of satellite image recognition was carried out, the problems in the field of satellite image recognition as a source of information were considered and analyzed, deep learning methods were compared, and existing image recognition methods were analyzed. The results obtained will be used as a basis for the prospective development of a fire recognition model based on satellite images and the use of recognition results as input data for a cognitive model of forecasting the macro-economic situation based on fuzzy cognitive maps.

This paper discusses the development of a convolutional architecture of a deep neural network for the recognition of wildfires on satellite images. Based on the results of image classification, a fuzzy cognitive map of the analysis of the macroeconomic situation was built. The paper also considers the prospect of using hybrid cognitive models for forecasting macroeconomic indicators based on fuzzy cognitive maps using data on recognized wildfires on satellite images.