Effective representations of complex web semantic graphs are essential for various web applications, including link prediction, recommendation systems, and social network analysis. However, existing methods assume that multi-interactions (or multi-relationships) between two connected nodes are independent, while these relationships inherently exhibit characteristics of mutual promotion or mutual inhibition. Moreover, these semantic characteristics across different relationships cannot be easily captured by a simple linear combination. To tackle this challenge, we propose an Adaptive Multi-Interaction (AMI) web semantic graph representation method. Specifically, AMI consists of three modules, including a multi-interaction aggregation module, a global pattern aggregation module, and an adaptive relation-specific decoder module. Firstly, we construct a learnable multi-interaction behavior pattern matrix that captures the mutual promotion and mutual inhibition effects between two connected nodes. Secondly, the global pattern aggregation module is designed to efficiently capture global homogeneous interaction patterns through graph convolution networks. Finally, the adaptive relation-specific decoder module employs a hybrid scoring strategy to adaptively decode node embeddings based on their distinct relationships. Extensive experiments on benchmark web datasets for link prediction tasks demonstrate that AMI outperforms state-of-the-art baselines. Our codes are available at https://github.com/AI-stronger123/AMI.

Graphs are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottlenecks due to the inherent irregularity of graphs. An innovative solution is converting graphs into textual representations, thereby harnessing the powerful capabilities of Large Language Models (LLMs) to process and comprehend graphs. In this article, we present a comprehensive review of methodologies for applying LLMs to graphs, termed LLM4graph. The core of LLM4graph lies in transforming graphs into texts for LLMs to understand and analyze. Thus, we propose a novel taxonomy of LLM4graph methods from the view of the transformation. Specifically, existing methods can be divided into two paradigms: Graph2text and Graph2token, which transform graphs into texts or tokens as the input of LLMs, respectively. We point out four challenges during the transformation to systematically present existing methods from a problem-oriented perspective. For practical concerns, we provide a guideline for researchers on selecting appropriate models and LLMs for different graphs and hardware constraints. To empirically evaluate our taxonomy and different technical choices, we conduct experiments with representative methods in Graph2text and Graph2token. We also identify five future research directions for LLM4graph.

This work introduces a framework to diagnose the strengths and shortcomings of Autonomous Vehicle (AV) collision avoidance technology with synthetic yet realistic potential collision scenarios adapted from real-world, collision-free data. Our framework generates counterfactual collisions with diverse crash properties, e.g., crash angle and velocity, between an adversary and a target vehicle by adding perturbations to the adversary's predicted trajectory from a learned AV behavior model. Our main contribution is to ground these adversarial perturbations in realistic behavior as defined through the lens of data-alignment in the behavior model's parameter space. Then, we cluster these synthetic counterfactuals to identify plausible and representative collision scenarios to form the basis of a test suite for downstream AV system evaluation. We demonstrate our framework using two state-of-the-art behavior prediction models as sources of realistic adversarial perturbations, and show that our scenario clustering evokes interpretable failure modes from a baseline AV policy under evaluation.

ABSTRACT To overcome the problems of texture information loss and insufficiently prominent targets in existing fusion networks, an information decomposition‐based autoencoder fusion network for infrared and visible images is proposed in this paper. Two salient information encoders with unshared weights and two scene information encoders with shared weights are designed to extract different features from infrared and visible images, respectively. The constraint is added to the loss function in order to ensure the ability of the salient information encoders to extract representative features and the scene information encoder to extract the cross‐modality feature. In addition, by introducing the pre‐trained semantic segmentation networks to guide the network training and constructing a feature saliency‐based fusion strategy, the ability of the fusion network is further enhanced to distinguish between targets and backgrounds. Extensive experiments are carried out on five datasets. Comparison experiments with state‐of‐the‐art fusion networks and ablation experiments indicate that the proposed method can obtain fused images with richer and more comprehensive information and is more robust to challenging factors, such as strong and weak light smoke and fog environments. At the same time, the fused images by our proposed method are more beneficial for downstream tasks such as target detection.