分子特性预测的深度学习模型的研究主要集中在更好的图形神经网络（GNN）架构的发展。虽然新的GNN变体继续提高性能，但它们的修改共享一个常见的主题，即减轻其基本图形到图形的内在内在的问题。在这项工作中，我们研究了这些限制，并提出了一种新的分子表现，可以完全绕过GNN的需求。与变压器模型配对时，我们的固定尺寸随机表示超出了最先进的GNN模型的性能，并提供了一种可扩展性的路径。

学习表达性分子表示对于促进分子特性的准确预测至关重要。尽管图形神经网络（GNNS）在分子表示学习中取得了显着进步，但它们通常面临诸如邻居探索，不足，过度光滑和过度阵列之类的局限性。同样，由于参数数量大，GNN通常具有较高的计算复杂性。通常，当面对相对大尺寸的图形或使用更深的GNN模型体系结构时，这种限制会出现或增加。克服这些问题的一个想法是将分子图简化为小型，丰富且有益的信息，这更有效，更具挑战性的培训GNN。为此，我们提出了一个新颖的分子图粗化框架，名为FUNQG利用函数组，作为分子的有影响力的构件来确定其性质，基于称为商图的图理论概念。通过实验，我们表明所产生的信息图比分子图小得多，因此是训练GNN的良好候选者。我们将FUNQG应用于流行的分子属性预测基准，然后比较所获得的数据集上的GNN体系结构的性能与原始数据集上的几个最先进的基线。通过实验，除了其参数数量和低计算复杂性的急剧减少之外，该方法除了其急剧减少之外，在各种数据集上的表现显着优于先前的基准。因此，FUNQG可以用作解决分子表示学习问题的简单，成本效益且可靠的方法。

Graph Neural Networks (GNNs) have shown great potential in the field of graph representation learning. Standard GNNs define a local message-passing mechanism which propagates information over the whole graph domain by stacking multiple layers. This paradigm suffers from two major limitations, over-squashing and poor long-range dependencies, that can be solved using global attention but significantly increases the computational cost to quadratic complexity. In this work, we propose an alternative approach to overcome these structural limitations by leveraging the ViT/MLP-Mixer architectures introduced in computer vision. We introduce a new class of GNNs, called Graph MLP-Mixer, that holds three key properties. First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on the Long Range Graph Benchmark (LRGB) and the TreeNeighbourMatch datasets. Second, they offer better speed and memory efficiency with a complexity linear to the number of nodes and edges, surpassing the related Graph Transformer and expressive GNN models. Third, they show high expressivity in terms of graph isomorphism as they can distinguish at least 3-WL non-isomorphic graphs. We test our architecture on 4 simulated datasets and 7 real-world benchmarks, and show highly competitive results on all of them.

Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules. Recent studies suggest that big GNN models pre-trained by self-supervised learning on unlabeled datasets enable better transfer performance in downstream molecular property prediction tasks. However, they often require large-scale datasets and considerable computational resources, which is time-consuming, computationally expensive, and environmentally unfriendly. To alleviate these limitations, we propose a novel pre-training model for molecular representation learning, Bi-branch Masked Graph Transformer Autoencoder (BatmanNet). BatmanNet features two tailored and complementary graph autoencoders to reconstruct the missing nodes and edges from a masked molecular graph. To our surprise, BatmanNet discovered that the highly masked proportion (60%) of the atoms and bonds achieved the best performance. We further propose an asymmetric graph-based encoder-decoder architecture for either nodes and edges, where a transformer-based encoder only takes the visible subset of nodes or edges, and a lightweight decoder reconstructs the original molecule from the latent representation and mask tokens. With this simple yet effective asymmetrical design, our BatmanNet can learn efficiently even from a much smaller-scale unlabeled molecular dataset to capture the underlying structural and semantic information, overcoming a major limitation of current deep neural networks for molecular representation learning. For instance, using only 250K unlabelled molecules as pre-training data, our BatmanNet with 2.575M parameters achieves a 0.5% improvement on the average AUC compared with the current state-of-the-art method with 100M parameters pre-trained on 11M molecules.

基于1-HOP邻居之间的消息传递（MP）范式交换信息的图形神经网络（GNN），以在每一层构建节点表示。原则上，此类网络无法捕获在图形上学习给定任务的可能或必需的远程交互（LRI）。最近，人们对基于变压器的图的开发产生了越来越多的兴趣，这些方法可以考虑超出原始稀疏结构以外的完整节点连接，从而实现了LRI的建模。但是，仅依靠1跳消息传递的MP-gnn与位置特征表示形式结合使用时通常在几个现有的图形基准中表现得更好，因此，限制了Transferter类似体系结构的感知效用和排名。在这里，我们介绍了5个图形学习数据集的远程图基准（LRGB）：Pascalvoc-SP，Coco-SP，PCQM-Contact，Peptides-Func和肽结构，可以说需要LRI推理以在给定的任务中实现强大的性能。我们基准测试基线GNN和Graph Transformer网络，以验证捕获长期依赖性的模型在这些任务上的性能明显更好。因此，这些数据集适用于旨在捕获LRI的MP-GNN和Graph Transformer架构的基准测试和探索。

Graph classification is an important area in both modern research and industry. Multiple applications, especially in chemistry and novel drug discovery, encourage rapid development of machine learning models in this area. To keep up with the pace of new research, proper experimental design, fair evaluation, and independent benchmarks are essential. Design of strong baselines is an indispensable element of such works. In this thesis, we explore multiple approaches to graph classification. We focus on Graph Neural Networks (GNNs), which emerged as a de facto standard deep learning technique for graph representation learning. Classical approaches, such as graph descriptors and molecular fingerprints, are also addressed. We design fair evaluation experimental protocol and choose proper datasets collection. This allows us to perform numerous experiments and rigorously analyze modern approaches. We arrive to many conclusions, which shed new light on performance and quality of novel algorithms. We investigate application of Jumping Knowledge GNN architecture to graph classification, which proves to be an efficient tool for improving base graph neural network architectures. Multiple improvements to baseline models are also proposed and experimentally verified, which constitutes an important contribution to the field of fair model comparison.

我们提出了一个食谱，讲述了如何建立具有线性复杂性和最先进的结果的一般，功能可扩展的（GPS）图形变压器，并在各种基准测试基准上。 Graph Transformers（GTS）在图形表示学习领域中获得了多种近期出版物的知名度，但它们对构成良好的位置或结构编码的共同基础以及与众不同的区别。在本文中，我们总结了具有更清晰的定义的不同类型的编码，并将其分类为$ \ textit {local} $，$ \ textit {global} $或$ \ textit {fextit {ferseal} $。此外，GTS仍被限制在具有数百个节点的小图上，我们提出了第一个具有复杂性线性的体系结构对节点和边缘$ O（n+e）$的数量，通过将局部实质汇总从完全 - 连接的变压器。我们认为，这种解耦并不会对表现性产生负面影响，而我们的体系结构是图形的通用函数近似器。我们的GPS配方包括选择3种主要成分：（i）位置/结构编码，（ii）局部消息通讯机制和（iii）全局注意机制。我们构建和开源一个模块化框架$ \ textit {graphgps} $，该{GraphGps} $支持多种类型的编码，并且在小图和大图中提供效率和可扩展性。我们在11个基准测试上测试了我们的体系结构，并对所有这些基准显示出非常具竞争力的结果，展示了由模块化和不同策略组合获得的经验益处。

变压器架构已成为许多域中的主导选择，例如自然语言处理和计算机视觉。然而，与主流GNN变体相比，它对图形水平预测的流行排行榜没有竞争表现。因此，它仍然是一个谜，变形金机如何对图形表示学习表现良好。在本文中，我们通过提出了基于标准变压器架构构建的Gragemer来解决这一神秘性，并且可以在广泛的图形表示学习任务中获得优异的结果，特别是在最近的OGB大规模挑战上。我们在图中利用变压器的关键洞察是有效地将图形的结构信息有效地编码到模型中。为此，我们提出了几种简单但有效的结构编码方法，以帮助Gramemormer更好的模型图形结构数据。此外，我们在数学上表征了Gramemormer的表现力，并展示了我们编码图形结构信息的方式，许多流行的GNN变体都可以被涵盖为GrameRormer的特殊情况。

图形神经网络（GNN）已成为一种学习关系数据的强大技术。由于他们执行的消息传递步骤数量相对有限 - 因此一个较小的接收领域，人们对通过结合基础图的结构方面来提高其表现力引起了极大的兴趣。在本文中，我们探讨了亲和力措施作为图形神经网络中的特征，特别是由随机步行引起的措施，包括有效的阻力，击球和通勤时间。我们根据这些功能提出消息传递网络，并评估其在各种节点和图形属性预测任务上的性能。我们的体系结构具有较低的计算复杂性，而我们的功能对于基础图的排列不变。我们计算的措施使网络可以利用图表的连接性能，从而使我们能够超过相关的基准，用于各种任务，通常具有更少的消息传递步骤。在OGB-LSC-PCQM4MV1的最大公共图形回归数据集之一中，我们在编写时获得了最著名的单模验证MAE。

This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task. Our approach implements several key principles from the prior literature. At its core our GPS++ method is a hybrid MPNN/Transformer model that incorporates 3D atom positions and an auxiliary denoising task. The effectiveness of GPS++ is demonstrated by achieving 0.0719 mean absolute error on the independent test-challenge PCQM4Mv2 split. Thanks to Graphcore IPU acceleration, GPS++ scales to deep architectures (16 layers), training at 3 minutes per epoch, and large ensemble (112 models), completing the final predictions in 1 hour 32 minutes, well under the 4 hour inference budget allocated. Our implementation is publicly available at: https://github.com/graphcore/ogb-lsc-pcqm4mv2.

近年来，基于Weisfeiler-Leman算法的算法和神经架构，是一个众所周知的Graph同构问题的启发式问题，它成为具有图形和关系数据的机器学习的强大工具。在这里，我们全面概述了机器学习设置中的算法的使用，专注于监督的制度。我们讨论了理论背景，展示了如何将其用于监督的图形和节点表示学习，讨论最近的扩展，并概述算法的连接（置换 - ）方面的神经结构。此外，我们概述了当前的应用和未来方向，以刺激进一步的研究。

Most graph neural network models rely on a particular message passing paradigm, where the idea is to iteratively propagate node representations of a graph to each node in the direct neighborhood. While very prominent, this paradigm leads to information propagation bottlenecks, as information is repeatedly compressed at intermediary node representations, which causes loss of information, making it practically impossible to gather meaningful signals from distant nodes. To address this issue, we propose shortest path message passing neural networks, where the node representations of a graph are propagated to each node in the shortest path neighborhoods. In this setting, nodes can directly communicate between each other even if they are not neighbors, breaking the information bottleneck and hence leading to more adequately learned representations. Theoretically, our framework generalizes message passing neural networks, resulting in provably more expressive models, and we show that some recent state-of-the-art models are special instances of this framework. Empirically, we verify the capacity of a basic model of this framework on dedicated synthetic experiments, and on real-world graph classification and regression benchmarks, and obtain state-of-the-art results.

图形神经网络（GNN）正在化学工程中出现，以基于分子图的物理化学特性端到端学习。 GNNS的一个关键要素是合并函数，将原子矢量结合到分子指纹中。大多数以前的作品都使用标准池功能来预测各种属性。但是，不合适的合并功能会导致概括不佳的非物理GNN。我们根据有关学习特性的物理知识比较并选择有意义的GNN合并方法。通过量子机械计算计算出的分子特性证明了物理池函数的影响。我们还将结果与最近的SET2Set合并方法进行了比较。我们建议使用总和池来预测取决于分子大小的性能并比较分子大小无关的属性的池函数。总体而言，我们表明物理池功能的使用显着增强了概括。

通过定向消息传递通过方向消息通过的图形神经网络最近在多个分子特性预测任务上设置了最先进的技术。然而，它们依赖于通常不可用的原子位置信息，并获得它通常非常昂贵甚至不可能。在本文中，我们提出了合成坐标，使得能够使用高级GNN而不需要真正的分子配置。我们提出了两个距离作为合成坐标：使用个性化PageRank的对称变体指定分子配置的粗糙范围和基于图的距离的距离界限。为了利用距离和角度信息，我们提出了一种将正常图形神经网络转换为定向MPNN的方法。我们表明，通过这种转变，我们可以将正常图形神经网络的误差减少55％在锌基准。我们还通过在SMP和DimeNet ++模型中纳入合成坐标，在锌和自由QM9上设定了最新技术。我们的实现可在线获取。

Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a two-step pretraining strategy. The first step of pretraining is a self-supervised approach focused on learning chemical structures, and the second step is a massive multi-task approach to learn biological information. We show that fine-tuning pretrained MolE achieves state-of-the-art results on 9 of the 22 ADMET tasks included in the Therapeutic Data Commons.

生物医学网络是与疾病网络的蛋白质相互作用的普遍描述符，从蛋白质相互作用，一直到医疗保健系统和科学知识。随着代表学习提供强大的预测和洞察的显着成功，我们目睹了表现形式学习技术的快速扩展，进入了这些网络的建模，分析和学习。在这篇综述中，我们提出了一个观察到生物学和医学中的网络长期原则 - 而在机器学习研究中经常出口 - 可以为代表学习提供概念基础，解释其当前的成功和限制，并告知未来进步。我们综合了一系列算法方法，即在其核心利用图形拓扑到将网络嵌入到紧凑的向量空间中，并捕获表示陈述学习证明有用的方式的广度。深远的影响包括鉴定复杂性状的变异性，单细胞的异心行为及其对健康的影响，协助患者的诊断和治疗以及制定安全有效的药物。

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.

Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. For this purpose, they can be defined as many different types which suitably reflect the individual contexts of the represented problem. To address cutting-edge problems based on graph data, the research field of Graph Neural Networks (GNNs) has emerged. Despite the field's youth and the speed at which new models are developed, many recent surveys have been published to keep track of them. Nevertheless, it has not yet been gathered which GNN can process what kind of graph types. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static and dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover, we distinguish between GNN models for discrete-time or continuous-time dynamic graphs and group the models according to their architecture. We find that there are still graph types that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.

Pre-publication draft of a book to be published byMorgan & Claypool publishers. Unedited version released with permission. All relevant copyrights held by the author and publisher extend to this pre-publication draft.

Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast chemical space and the limited availability of property labels make supervised learning challenging. Recently, unsupervised transformer-based language models pretrained on a large unlabelled corpus have produced state-of-the-art results in many downstream natural language processing tasks. Inspired by this development, we present molecular embeddings obtained by training an efficient transformer encoder model, MoLFormer, which uses rotary positional embeddings. This model employs a linear attention mechanism, coupled with highly distributed training, on SMILES sequences of 1.1 billion unlabelled molecules from the PubChem and ZINC datasets. We show that the learned molecular representation outperforms existing baselines, including supervised and self-supervised graph neural networks and language models, on several downstream tasks from ten benchmark datasets. They perform competitively on two others. Further analyses, specifically through the lens of attention, demonstrate that MoLFormer trained on chemical SMILES indeed learns the spatial relationships between atoms within a molecule. These results provide encouraging evidence that large-scale molecular language models can capture sufficient chemical and structural information to predict various distinct molecular properties, including quantum-chemical properties.