Representation Learning of Enhanced Graphs Using Random Walk Graph Convolutional Network

In this paper, we design and evaluate a new substructure-aware Graph Representation Learning (GRL) approach. GRL aims to map graph structure information into low-dimensional representations. While extensive efforts have been made for modeling global and/or local structure information, GRL can be improved by substructure information. Some recent studies exploit adversarial learning to incorporate substructure awareness, but hindered by unstable convergence. This study will address the major research question: is there a better way to integrate substructure awareness into GRL? As subsets of the graph structure, interested substructures (i.e., subgraph) are unique and representative for differentiating graphs, leading to the high correlation between the representation of the graph-level structure and substructures. Since mutual information (MI) is to evaluate the mutual dependence between two variables, we develop a MI inducted substructure-aware GRL method. We decompose the GRL pipeline into two stages: (1) node-level, where we introduce to maximize MI between the original and learned representation by the intuition that the original and learned representation should be highly correlated; (2) graph-level, where we preserve substructures by maximizing MI between the graph-level structure and substructure representation. Finally, we present extensive experimental results to demonstrate the improved performances of our method with real-world data.

A spatial–temporal graph neural network framework for automated software bug triaging

Navigating through the Maze of Homogeneous Catalyst Design with Machine Learning

BLoG: Bootstrapped graph representation learning with local and global regularization for recommendation

Dynamic heterogeneous graph representation learning with neighborhood type modeling

Representation Learning (RL) aims to convert data into low-dimensional and dense real-valued vectors, so as to realize reasoning in vector space. RL is one of the important research contents in the analysis of health data. This paper systematically reviews the latest research on Electronic Health Records (EHR) RL. We searched the Web of Science, Google Scholar, and Association for Computing Machinery Digital Library for papers involving EHR RL. On the basis of literature review, we propose a new taxonomy to categorize the state-of-the-art EHR RL methods into three categories: statistics learning-based RL methods, knowledge RL methods and graph RL methods. We analyze and summarize their characteristics according to the input data form and underlying learning mechanisms. In addition, we provide evaluation strategies to verify the quality of EHR representations from both intrinsic and extrinsic perspectives. Finally, we put forward three promising research directions to promote future research. Overall, this survey aims to provide a profound overview of state-of-the-art developments in the field of EHR RL and to help researchers find the most appropriate methods.

Increased awareness of the opioid epidemic has resulted in the need to significantly reduce the number of opioids prescribed after surgery. However, up to one in five patients require a refill after discharge. Accurate identification of patients at risk of needing a refill after surgery is critically important, as it has the potential to improve pain control and patient experience while avoiding overprescription of opioids after surgery. In this paper, two graph representation learning methods are proposed for predicting opioid refills in postoperative patients. The first approach represents patients as nodes in a graph and performs node classification. The second approach is based on graph classification where each patient is represented as a graph. Performance results on a real-world retrospective cohort of postoperative patients show that a node classification approach with graph sample and aggregation (GraphSAGE) achieves the best performance in prediction of opioid refill.

Effect of mesoscopic structure of citrus pectin on its emulsifying properties: Compactness is more important than size

The fundamental relationship between the mesoscopic structure of neuronal circuits and organismic functions they subserve is one of the major challenges in contemporary neuroscience. Formation of structurally connected modules of neurons enacts the conversion from single-cell firing to large-scale behaviour of an organism, highlighting the importance of their accurate profiling in the data. While connectomes are typically characterized by significant sparsity of neuronal connections, recent advances in network theory and machine learning have revealed fundamental limitations of traditionally used community detection approaches in cases where the network is sparse. Here we studied the optimal community structure in the structural connectome of Caenorhabditis elegans, for which we exploited a non-conventional approach that is based on non-backtracking random walks, virtually eliminating the sparsity issue. In full agreement with the previous asymptotic results, we demonstrated that non-backtracking walks resolve the ground truth annotation into clusters on stochastic block models (SBM) with the size and density of the connectome better than the spectral methods related to simple random walks. Based on the cluster detectability threshold, we determined that the optimal number of modules in a recently mapped connectome of C. elegans is 10, which precisely corresponds to the number of isolated eigenvalues in the spectrum of the non-backtracking flow matrix. The discovered communities have a clear interpretation in terms of their functional role, which allows one to discern three structural compartments in the worm: the Worm Brain (WB), the Worm Movement Controller (WMC), and the Worm Information Flow Connector (WIFC). Broadly, our work provides a robust network-based framework to reveal mesoscopic structures in sparse connectomic datasets, paving way to further investigation of connectome mechanisms for different functions.

Graph Neural Networks (GNNs) have demonstrated significant success in various graph-related tasks. However, their performance is highly dependent on the availability of sufficient, class-balanced annotated data and an accurate graph structure. GNNs are vulnerable to substantial performance degradation when confronted with limited annotated samples, class imbalance, or noisy graph structures. First, a Dual GNN learning framework is introduced for semi-supervised node classification under limited supervision. The framework comprises two GNN-based node prediction modules: a primary module, which uses the input graph structure to induce standard node embeddings and predictions, and an auxiliary module, which leverages spectral clustering to construct a new graph structure and learn new node embeddings and predictions. These modules collaborate to enable end-to-end learning of discriminative node representations. Next, a graph augmentation method called Graph Dual Mixup (GDM) is proposed for graph classification with scarce labels. GDM employs a graph structural auto-encoder to learn structural embeddings, applying mixup in the learned structural embedding space to generate new graph structures. Additionally, mixup is applied to input node features, generating node features for new graph instances. Together, these generated node features and graph structures contribute new graphs that increase the size and diversity of the labeled dataset, improving classification performance. To enhance robustness against adversarial attacks on graph structures, an Efficient Low-Rank GNN is introduced. This approach learns robust low-rank sparse graph structures through a two-stage process. In the first stage, Singular Value Decomposition is used to estimate a low-rank approximation of the graph structure. This estimate is refined in the second stage by jointly learning a low-rank sparse graph structure alongside the GNN model, resulting in enhanced robustness. Finally, to address class-imbalanced node classification, a Unified GNN Learning (Uni-GNN) framework is proposed. Uni-GNN integrates structural and semantic connectivity representations to extend the propagation of embeddings to non-adjacent structural neighbors and semantically similar nodes, facilitating the diffusion of discriminative information. Additionally, it incorporates a balanced pseudo-label generation mechanism to improve the representations of minority classes. Comprehensive evaluations on benchmark datasets demonstrate that these methods outperform state-of-the-art approaches and hold significant potential for advancing GNN learning with limited supervision.

Laser-based metal additive manufacturing (MAM), particularly laser powder bed fusion (LPBF) and laser directed energy deposition (L-DED), is a transformative technology enabling the production of complex, high-performance metal components with precision and minimal waste. However, its wider adoption is hindered by challenges in ensuring repeatability and consistency due to the complex, dynamic nature of the process. Closed-loop systems with in-situ monitoring and control have gained attention for quality assurance, where machine learning (ML) models are crucial for correlating sensor data with process state diagnosis and facilitating control actions. This review adopts an ML perspective to elucidate the role of ML in closed-loop control systems. It first outlines sensor data types and preprocessing methods used as ML datasets, then discusses roles and applications of ML models for in-situ monitoring, highlighting limitations and potential solutions. An ML-based closed-loop control framework is also presented, with emphasis on the integration of ML in the control component. Finally, future development directions of advanced ML approaches are envisioned. This review provides new insights into enhancing the role of ML models in laser-based MAM closed-loop control systems, serving as a crucial aid in the development of intelligent control systems.

Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generalize to various downstream applications. Yet, the adversarial robustness of such pre-trained graph learning models remains largely unexplored. More importantly, most existing defense techniques designed for end-to-end graph representation learning methods require pre-specified label definitions, and thus cannot be directly applied to the pre-training methods. In this paper, we propose an unsupervised defense technique to robustify pre-trained deep graph models, so that the perturbations on the input graph can be successfully identified and blocked before the model is applied to different downstream tasks. Specifically, we introduce a mutual information-based measure, graph representation vulnerability (GRV), to quantify the robustness of graph encoders on the representation space. We then formulate an optimization problem to learn the graph representation by carefully balancing the trade-off between the expressive power and the robustness (i.e., GRV) of the graph encoder. The discrete nature of graph topology and the joint space of graph data make the optimization problem intractable to solve. To handle the above difficulty and to reduce computational expense, we further relax the problem and thus provide an approximate solution. Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks. Extensive experiments demonstrate that even without access to labels and tasks, our model is still able to enhance robustness against adversarial attacks on three downstream tasks (node classification, link prediction, and community detection) by an average of +16.5% compared with existing methods.

DynHEN: A heterogeneous network model for dynamic bipartite graph representation learning

In recent years, graph representation learning has played a huge role in the fields and research of node clustering, node classification, link prediction, etc., among which many excellent models and methods have emerged. These methods can achieve better results for model training and verification of data in a single space domain. However, in real scenarios, the solution of cross-domain problems of multiple information networks is very practical and important, and the existing methods cannot be applied to cross-domain scenarios, so we research on cross-domain representation is based on multi-network space integration. This paper conducts representation learning research for cross-domain scenarios. First, we use different network representation learning methods to perform representation learning in a single network space. Second, we use the attention mechanism to fuse representations in different spaces to obtain a fusion representation of multiple network spaces; Finally, the model is verified through cross-domain experiments. The experimental results show that the fusion model proposed in this paper can improve the performance of cross-domain scenarios.

Long non-coding RNAs (lncRNAs) play a broad spectrum of distinctive regulatory roles through interactions with proteins. However, only a few plant lncRNAs have been experimentally characterized. We propose GPLPI, a graph representation learning method, to predict plant lncRNA-protein interaction (LPI) from sequence and structural information. GPLPI employs a generative model using long short-term memory (LSTM) with graph attention. Evolutionary features are extracted using frequency chaos game representation (FCGR). Manifold regularization and l2-norm are adopted to obtain discriminant feature representations and mitigate overfitting. The model captures locality preserving and reconstruction constraints that lead to better generalization ability. Finally, potential interactions between lncRNAs and proteins are predicted by integrating catboost and regularized Logistic regression based on L-BFGS optimization algorithm. The method is trained and tested on Arabidopsis thaliana and Zea mays datasets. GPLPI achieves accuracies of 85.76% and 91.97% respectively. The results show that our method consistently outperforms other state-of-the-art methods.