Multiple instance learning (MIL) trains models from bags of instances, where each bag contains multiple instances, and only bag-level labels are available for supervision. The application of graph neural networks (GNNs) in capturing intrabag topology effectively improves MIL. Existing GNNs usually require filtering low-confidence edges among instances and adapting graph neural architectures to new bag structures. However, such asynchronous adjustments to structure and architecture are tedious and ignore their correlations. To tackle these issues, we propose a reinforced GNN framework for MIL (RGMIL), pioneering the exploitation of multiagent deep reinforcement learning (MADRL) in MIL tasks. MADRL enables the flexible definition or extension of factors that influence bag graphs or GNNs and provides synchronous control over them. Moreover, MADRL explores structure-to-architecture correlations while automating adjustments. Experimental results on multiple MIL datasets demonstrate that RGMIL achieves the best performance with excellent explainability. The code and data are available at https://github.com/RingBDStack/RGMIL.

Aspect-based sentiment analysis (ABSA) is dedicated to forecasting the sentiment polarity of aspect terms within sentences. Employing graph neural networks to capture structural patterns from syntactic dependency parsing has been confirmed as an effective approach for boosting ABSA. In most works, the topology of dependency trees or dependency-based attention coefficients is often loosely regarded as edges between aspects and opinions, which can result in insufficient and ambiguous syntactic utilization. To address these problems, we propose a new reinforced dependency graph convolutional network (RDGCN) that improves the importance calculation of dependencies in both distance and type views. Initially, we propose an importance calculation criterion for the minimum distances over dependency trees. Under the criterion, we design a distance-importance function that leverages reinforcement learning for weight distribution search and dissimilarity control. Since dependency types often do not have explicit syntax like tree distances, we use global attention and mask mechanisms to design type-importance functions. Finally, we merge these weights and implement feature aggregation and classification. Comprehensive experiments show the effectiveness of the criterion and importance functions. RDGCN yields excellent analysis results.

Synthetic lethality (SL) prediction is used to identify if the co-mutation of two genes results in cell death. The prevalent strategy is to abstract SL prediction as an edge classification task on gene nodes within SL data and achieve it through graph neural networks (GNNs). However, GNNs suffer from limitations in their message passing mechanisms, including over-smoothing and over-squashing issues. Moreover, harnessing the information of non-SL gene relationships within large-scale multi-omics data to facilitate SL prediction poses a non-trivial challenge. To tackle these issues, we propose a new multi-omics sampling-based graph transformer for SL prediction (MSGT-SL). Concretely, we introduce a shallow multi-view GNN to acquire local structural patterns from both SL and multi-omics data. Further, we input gene features that encode multi-view information into the standard self-attention to capture long-range dependencies. Notably, starting with batch genes from SL data, we adopt parallel random walk sampling across multiple omics gene graphs encompassing them. Such sampling effectively and modestly incorporates genes from omics in a structure-aware manner before using self-attention. We showcase the effectiveness of MSGT-SL on real-world SL tasks, demonstrating the empirical benefits gained from the graph transformer and multi-omics data.

Graph Neural Networks (GNNs) have yielded fruitful results in learning multi-view graph data. However, it is challenging for existing GNNs to capture the potential correlation information (PCI) among the graph structure features of multiple views. It is also challenging to adaptively identify valuable neighbors for node feature fusion in different views. To this end, we propose a novelReinforcedTensorGraphNeuralNetwork (RTGNN) framework to more effectively perform multi-view graph representation learning through reinforcing inter- and intra-graph aggregation. Specifically, RTGNN first uses tensor decomposition to extract the graph structure features (GSFs) of each view in the common feature space. These GSFs contain the PCI of multiple views and alleviate fusion conflicts that may be caused by differences between view feature spaces in cross-view feature fusion. Since fusing the features of all neighbor nodes may harm the features of the center node, we filter the irrelevant neighbors to improve the performance of intra-graph aggregation in each view. Concretely, a reinforcement learning (RL)-guided scheme is developed to automatically calculate the optimal filtering threshold for each view, avoiding tedious manual updates and infeasible back propagation updates. Experimental results and analysis on five datasets show that RTGNN surpasses the best multi-view graph representation baselines and achieves the maximum 14.26% performance improvement in terms of F1. The code link ishttps://github.com/RingBDStack/RTGNN.

Although surface with multiple holes (SMHs) is widely used in industrial components, the precise inspection of SMH is a knotty task due to the inefficiency of traditional surface inspection technology. Recently, a five-axis surface sweep scanning approach is emerging and shows great potential to boost the surface inspection efficiency by sensing surface in a continuous sweep scanning way. However, an efficient sweep scanning path should cater to the unique kinematic characteristics of the five-axis inspection system. In this article, we present an approach to automatically generate efficient five-axis sweep scanning paths for inspecting SMH. First, the skeleton of SMH is extracted along with the surface partitioned into several patches, based on which a guiding curve-based sweep scanning path can be defined for each surface patch. By modeling the skeleton of SMH as a directed Euler graph and finding a proper sequence to traverse the graph, a continuous five-axis sweep scanning path is then generated to sweep all patches without any transition among them. The nonsweeping time could be eliminated so that the sweep scanning efficiency is drastically improved in this way. Simulation and physical inspection experiments are conducted on two SMHs, showing that our method significantly outperforms existing approaches, such as the popular zigzag method and the method from the leading commercial software of RENISHAW.Note to Practitioners—This article aims to generate an efficient sweep scanning path of a five-axis coordinate measuring machine (CMM) for inspecting the SMHs of a precision component, such as an engine block or a gearbox cover. Although traditional five-axis CMM path generation methods can be applied to SMH inspection, most of them are designed for the point-by-point inspection mode, which intrinsically suffers from extremely low efficiency. Recently, an emerging five-axis surface sweep scanning technology shows great potential for boosting the efficiency of surface inspection by using a continuous surface sensing stylus mounted on a rapid rotary probe head. The realization of high-speed five-axis surface scanning depends on a proper sweep scanning path which takes advantage of the superior kinematic performance of the rotary probe head as much as possible and accordingly avoids assigning heavy workload to the three linear axes with weaker kinematic performance. However, up to date, only a handful of five-axis sweep scanning path planning methods are reported and mainly focus on the simple and compact surface. Therefore, existing methods are incompetent to generate a suitable sweep scanning path for high-speed inspection of SMH. For these reasons, we present a novel and practical approach to automatically generate a continuous five-axis sweep scanning path for complex SMH. The generated path exactly meets the unique kinematic requirements of high-speed five-axis inspection and eliminates all noninspection operations. In this way, the SMH inspection can be accomplished with high efficiency.