Finding the seed set that maximizes the influence spread over a network is a well-known NP-hard problem. Though a greedy algorithm can provide near-optimal solutions, the subproblem of influence estimation renders the solutions inefficient. In this work, we propose GLIE, a graph neural network that learns how to estimate the influence spread of the independent cascade. GLIE relies on a theoretical upper bound that is tightened through supervised training. Experiments indicate that it provides accurate influence estimation for real graphs up to 10 times larger than the train set. Subsequently, we incorporate it into two influence maximization techniques. We first utilize Cost Effective Lazy Forward optimization substituting Monte Carlo simulations with GLIE, surpassing the benchmarks albeit with a computational overhead. To improve computational efficiency we develop a provably submodular influence spread based on GLIE's representations, to rank nodes while building the seed set adaptively. The proposed algorithms are inductive, meaning they are trained on graphs with less than 300 nodes and up to 5 seeds, and tested on graphs with millions of nodes and up to 200 seeds. The final method exhibits the most promising combination of time efficiency and influence quality, outperforming several baselines.

We address the problem of influence maximization when the social network is accompanied by diffusion cascades. In the literature, such information is used to compute influence probabilities, which is utilized by stochastic diffusion models in influence maximization. Motivated by the recent criticism on diffusion models and the galloping advancements in influence learning, we proposeIMINFECTOR(Influence Maximization with INFluencer vECTORs), a method that uses representations learned from diffusion cascades to perform model-independent influence maximization. The first part of our methodology is a multi-task neural network that learns embeddings of nodes that initiate cascades (influencer vectors) and embeddings of nodes that participate in them (susceptible vectors). The norm of an influencer vector captures a node’s aptitude to initiate lengthy cascades and is used to reduce the number of candidate seeds. The combination of influencer and susceptible vectors form the diffusion probabilities between nodes. These are used to reformulate the computation of the influence spread and propose a greedy solution to influence maximization that retains the theoretical guarantees. We apply our method in three sizable datasets and evaluate it using cascades from future time steps.IMINFECTOR’s scalability and accuracy outperform various competitive algorithms and metrics from the diverse landscape of influence maximization.

The recent outbreak of COVID-19 has affected millions of individuals around the world and has posed a significant challenge to global healthcare. From the early days of the pandemic, it became clear that it is highly contagious and that human mobility contributes significantly to its spread. In this paper, we utilize graph representation learning to capitalize on the underlying relationship of population movement with the spread of COVID-19. Specifically, we create a graph where the nodes correspond to a country's regions, the features include the region's history of COVID-19, and the edge weights denote human mobility from one region to another. Subsequently, we employ graph neural networks to predict the number of future cases, encoding the underlying diffusion patterns that govern the spread into our learning model. Furthermore, to account for the limited amount of training data, we capitalize on the pandemic's asynchronous outbreaks across countries and use a model-agnostic meta-learning based method to transfer knowledge from one country's model to another's. We compare the proposed approach against simple baselines and more traditional forecasting techniques in 4 European countries. Experimental results demonstrate the superiority of our method, highlighting the usefulness of GNNs in epidemiological prediction. Transfer learning provides the best model, highlighting its potential to improve the accuracy of the predictions in case of secondary waves, given data from past/parallel outbreaks.

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.

Both distracted and aggressive driving are habitual in nature, constituting an insurance risk, which has been difficult to quantify. Here, in this paper, we propose a method that produces short term predictions for these two dangerous driving behaviors. The method feeds an Extreme Gradient Boosting (XGB) algorithm with the most informative features of a set of physiological and vehicular variables. The XGB algorithm operates on a learning window covering the last 30 seconds to make fast track predictions (FT) for the next 10 seconds. For aggressive driving, FT predictions are final, while for distracted driving, FT predictions are weighted over one minute, to form a meta-prediction. This more deliberative process for predicting distractions fits their intermittent manifestation. The method has been tested on SIM 1, a publicly available dataset from a distracted driving experiment. In this dataset, the drivers ($n=59$) are labeled as distracted based on the presence of mental activity or physical interactions antagonistic to the driving task; their driving style is defined by steering and acceleration, and is classified as aggressive or normal. The method attains classification performance that exceeds 87%. Alerting drivers when distractions and aggressiveness have taken hold on them can provide sobering awareness, given that people drift into these states subconsciously. The behavioral modification effects of such awareness mechanisms are rooted in Cognitive Behavioral Theory. The proposed method can also be used in future vehicles with advanced automation, weighing in the computer’s decision to wrest vehicular control from an unrepentant driver.

In the field of Brain Computer Interfaces, one of the most crucial hindrances towards everyday applicability is the problem of subject-to-subject generalization. This adheres to the fact that neural signals vary significantly across subjects, because of the inherent person specific variability, rendering a subject calibration process necessary for the pattern recognition mechanisms of a BCI to achieve a notable performance. In the present work, we explore this phenomenon on two open datasets from mental monitoring experiments which utilized a commercial BCI device (Neurosky). This passive BCI setting with economical hardware is one of the must promising in terms of commercial appeal and hence it has more potential to be employed by multiple subjects-users. We visualize the so-called inter subject variability problem and apply machine learning methods commonly used in BCI literature. Subsequently we employ multi-task learning algorithms, setting each subject specific classification as a separate task. The experiments reveal that multi-task approaches achieve better accuracy with increasing number of subjects in contrast to conventional models, while providing insights that are consistent among subjects and agree with the relevant literature.

This paper presents the first distributed triangle listing algorithm with provable CPU, I/O, Memory, and Network bounds. Finding all triangles (3-cliques) in a graph has numerous applications for density and connectivity metrics, but the majority of existing algorithms for massive graphs are sequential, while distributed versions of algorithms do not guarantee their CPU, I/O, Memory, or Network requirements. Our Parallel and Distributed Triangle Listing (PDTL) framework focuses on efficient external-memory access in distributed environments instead of fitting sub graphs into memory. It works by performing efficient orientation and load-balancing steps, and replicating graphs across machines by using an extended version of Hu et al.'s Massive Graph Triangulation algorithm. PDTL suits a variety of computational environments, from single-core machines to high-end clusters, and computes the exact triangle count on graphs of over 6B edges and 1B vertices (e.g. Yahoo graphs), outperforming and using fewer resources than the state-of-the-art systems Power Graph, OPT, and PATRIC by 2x to 4x. Our approach thus highlights the importance of I/O in a distributed environment.