Graphs, which encode pairwise relations between entities, are a kind of universal data structure for a lot of real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. Recently, machine learning techniques are widely developed and utilized to effectively tame graphs for discovering actionable patterns and harnessing them for advancing various graph-related computational tasks. Huge success has been achieved and numerous real-world applications have benefited from it. However, since in today's world, we are generating and gathering data in a much faster and more diverse way, real-world graphs are becoming increasingly large-scale and complex. More dedicated efforts are needed to propose more advanced machine learning techniques and properly deploy them for real-world applications in a scalable way. Thus, we organize The 3rd International Workshop on Machine Learning on Graphs (MLoG), held in conjunction with the 16th ACM Conference on Web Search and Data Mining (WSDM), which provides a venue to gather academia researchers and industry researchers/practitioners to present the recent progress on machine learning on graphs.

We propose the molecular omics network (MOOMIN) a multimodal graph neural network used by AstraZeneca oncologists to predict the synergy of drug combinations for cancer treatment. Our model learns drug representations at multiple scales based on a drug-protein interaction network and metadata. Structural properties of compounds and proteins are encoded to create vertex features for a message-passing scheme that operates on the bipartite interaction graph. Propagated messages form multi-resolution drug representations which we utilized to create drug pair descriptors. By conditioning the drug combination representations on the cancer cell type we define a synergy scoring function that can inductively score unseen pairs of drugs. Experimental results on the synergy scoring task demonstrate that MOOMIN outperforms state-of-the-art graph fingerprinting, proximity preserving node embedding, and existing deep learning approaches. Further results establish that the predictive performance of our model is robust to hyperparameter changes. We demonstrate that the model makes high-quality predictions over a wide range of cancer cell line tissues, out-of-sample predictions can be validated with external synergy databases, and that the proposed model is data efficient at learning.

In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task. The primary objective of the library is to make deep drug pair scoring models accessible to machine learning researchers and practitioners in a streamlined framework. The design of ChemicalX reuses existing high level model training utilities, geometric deep learning, and deep chemistry layers from the PyTorch ecosystem. Our system provides neural network layers, custom pair scoring architectures, data loaders, and batch iterators for end users. We showcase these features with example code snippets and case studies to highlight the characteristics of ChemicalX. A range of experiments on real world drug-drug interaction, polypharmacy side effect, and combination synergy prediction tasks demonstrate that the models available in ChemicalX are effective at solving the pair scoring task. Finally, we show that ChemicalX could be used to train and score machine learning models on large drug pair datasets with hundreds of thousands of compounds on commodity hardware.

What is the value of an individual model in an ensemble of binary classifiers? We answer this question by introducing a class of transferable utility cooperative games called ensemble games. In machine learning ensembles, pre-trained models cooperate to make classification decisions. To quantify the importance of models in these ensemble games, we define Troupe - an efficient algorithm that allocates payoffs based on approximate Shapley values of the classifiers. We argue that the Shapley value of models in these games is an effective decision metric for choosing a high-performing subset of models from the ensemble. Our analytical findings prove that our Shapley value estimation scheme is precise and scalable; its performance increases with the size of the dataset and ensemble. Empirical results on real-world graph classification tasks demonstrate that our algorithm produces high-quality estimates of the Shapley value. We find that Shapley values can be utilized for ensemble pruning and that adversarial models receive a low valuation. Complex classifiers are frequently found to be responsible for both correct and incorrect classification decisions.

We present PyTorch Geometric Temporal, a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easy-to-use framework. PyTorch Geometric Temporal was created with foundations on existing libraries in the PyTorch eco-system, streamlined neural network layer definitions, temporal snapshot generators for batching, and integrated benchmark datasets. These features are illustrated with a tutorial-like case study. Experiments demonstrate the predictive performance of the models implemented in the library on real-world problems such as epidemiological forecasting, ride-hail demand prediction, and web traffic management. Our sensitivity analysis of runtime shows that the framework can potentially operate on web-scale datasets with rich temporal features and spatial structure.

In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model. PDNs inductively learn an aggregated weight for each edge, optimized to produce the best outcome for the downstream learning task. PDNs are a generalization of attention mechanisms on graphs which allow flexible construction of similarity functions between nodes. They also support edge convolutions and cheap multiscale mixing layers. We show that PDNs overcome weaknesses of existing methods for graph attention (e.g. Graph Attention Networks), such as the diminishing weight problem.

Graphs encode important structural properties of complex systems. Machine learning on graphs has therefore emerged as an important technique in research and applications. We present Karate Club - a Python framework combining more than 30 state-of-the-art graph mining algorithms. These unsupervised techniques make it easy to identify and represent common graph features. The primary goal of the package is to make community detection, node and whole graph embedding available to a wide audience of machine learning researchers and practitioners. Karate Club is designed with an emphasis on a consistent application interface, scalability, ease of use, sensible out of the box model behaviour, standardized dataset ingestion, and output generation. This paper discusses the design principles behind the framework with practical examples. We show Karate Club's efficiency in learning performance on a wide range of real world clustering problems and classification tasks along with supporting evidence of its competitive speed.

Sampling graphs is an important task in data mining. In this paper, we describe Little Ball of Fur a Python library that includes more than twenty graph sampling algorithms. Our goal is to make node, edge, and exploration-based network sampling techniques accessible to a large number of professionals, researchers, and students in a single streamlined framework. We created this framework with a focus on a coherent application public interface which has a convenient design, generic input data requirements, and reasonable baseline settings of algorithms. Here we overview these design foundations of the framework in detail with illustrative code snippets. We show the practical usability of the library by estimating various global statistics of social networks and web graphs. Experiments demonstrate that Little Ball of Fur can speed up node and whole graph embedding techniques considerably with mildly deteriorating the predictive value of distilled features.

In this paper, we propose a flexible notion of characteristic functions defined on graph vertices to describe the distribution of vertex features at multiple scales. We introduce FEATHER, a computationally efficient algorithm to calculate a specific variant of these characteristic functions where the probability weights of the characteristic function are defined as the transition probabilities of random walks. We argue that features extracted by this procedure are useful for node level machine learning tasks. We discuss the pooling of these node representations, resulting in compact descriptors of graphs that can serve as features for graph classification algorithms. We analytically prove that FEATHER describes isomorphic graphs with the same representation and exhibits robustness to data corruption. Using the node feature characteristic functions we define parametric models where evaluation points of the functions are learned parameters of supervised classifiers. Experiments on real world large datasets show that our proposed algorithm creates high quality representations, performs transfer learning efficiently, exhibits robustness to hyperparameter changes and scales linearly with the input size.

Graph neural networks (GNNs) have emerged as a powerful approach for solving many network mining tasks. However, learning on large graphs remains a challenge -- many recently proposed scalable GNN approaches rely on an expensive message-passing procedure to propagate information through the graph. We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large datasets like those found in industry settings.

Modern graph embedding procedures can efficiently process graphs with millions of nodes. In this paper, we propose GEMSEC - a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their embedding. GEMSEC is a general extension of earlier work in the domain of sequence-based graph embedding. GEMSEC places nodes in an abstract feature space where the vertex features minimize the negative log-likelihood of preserving sampled vertex neighborhoods, and it incorporates known social network properties through a machine learning regularization. We present two new social network datasets and show that by simultaneously considering the embedding and clustering problems with respect to social properties, GEMSEC extracts high-quality clusters competitive with or superior to other community detection algorithms. In experiments, the method is found to be computationally efficient and robust to the choice of hyperparameters.

Analytic methods can be difficult to build and costly to train for mobility data. We show that information about the topology of the space and how mobile objects navigate the obstacles can be used to extract insights about mobility at larger distance scales. The main contribution of this paper is a topological signature that maps each trajectory to a relatively low dimensional Euclidean space, so that now they are amenable to standard analytic techniques. Data mining tasks: nearest neighbor search with locality sensitive hashing, clustering, regression, etc., work more efficiently in this signature space. We define the problem of mobility prediction at different distance scales, and show that with the signatures simple k nearest neighbor based regression perform accurate prediction. Experiments on multiple real datasets show that the framework using topological signatures is accurate on all tasks, and substantially more efficient than machine learning applied to raw data. Theoretical results show that the signatures contain enough topological information to reconstruct non-self-intersecting trajectories upto homotopy type. The construction of signatures is based on a differential form that can be generated in a distributed setting using local communication, and a signature can be locally and inexpensively updated and communicated by a mobile agent.