Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, covers, and cartoons), existing methods for natural scene visual text generation still have significant deficiencies: methods based on rendering engines rely on manually crafted rules, which struggle to adapt to diverse backgrounds and leave obvious artificial traces, while their text layouts may be placed in unreasonable areas (e.g., sky or ground) and text content is semantically disconnected from the scene; diffusion model-based methods, on the other hand, face difficulties in generating small characters, depend on manually designed prompts to ensure reasonable layout and content, fail to generate text at precise locations, and cannot effectively control text attributes (e.g., font and color). In this paper, we propose a two-stage method named SceneVTG++ to address these issues. SceneVTG++ comprises two core components: a Text Layout and Content Generator (TLCG) and a Controllable Local Text Diffusion (CLTD). The former leverages the world knowledge and visual reasoning capabilities of multimodal large language models to identify reasonable text areas and recommend scene-relevant text content based on natural scene background images; the latter generates controllable multilingual text using a diffusion model, ensuring alignment with the outputs of TLCG. Through extensive experiments, we verified the effectiveness of both TLCG and CLTD, and demonstrated that SceneVTG++ achieves state-of-the-art performance in natural scene visual text generation. Additionally, the images generated by SceneVTG++ exhibit superior utility for training natural scene optical character recognition (OCR) tasks, including text detection and text recognition. Codes and datasets will be made publicly available.

With the continued scaling of integrated circuits (ICs), IR drop analysis for on-chip power grids (PGs) is crucial but increasingly computationally demanding. Traditional numerical methods deliver high accuracy but are prohibitively time-intensive, while various machine learning (ML) methods have been introduced to alleviate these computational burdens. However, most CNN-based methods ignore the fine structure and topological information of PGs, and face interpretability or scalability issues. In this work, we propose a novel graphbased framework, IRGNN, leveraging the PG topology with the integration of numerical solutions and point clouds. Our framework applies a numerical solver, AMG-PCG, to generate rough numerical solutions as a reliable interpretability foundation for ML. Then, to capture PG topology, we regard nodes of PG as point clouds and extract point cloud features, and we introduce a novel graph structure, IRGraph. Furthermore, a novel graph-based model IRGNN is designed, incorporating a designed neighbor distance attention (NDA) layer for distanceaware PG features aggregation and graph transformer (GT) layer to capture global information. It should be noted that our framework can analyze the IR drop of each node in PG, which CNN-based methods cannot do. Experimental evaluations demonstrate that our framework achieves significantly higher accuracy than previous CNN-based approaches and numerical solvers while substantially reducing computation time.

IR Drop analysis for on-chip power grids (PGs) is vital but computationally challenging due to the rapid growth in the integrated circuit (IC) scale. Traditional numerical methods employed by current EDA software are accurate but extremely time-consuming. To achieve rapid analysis of IR drop, various machine learning (ML) methods have been introduced to address the inefficiency of numerical methods. However, the issue of interpretability or scalability has been limiting practical applications. In this work, we propose IR-Fusion, which aims to combine numerical methods with ML to achieve the trade-off and complementarity between accuracy and efficiency in static IR drop analysis. Specifically, the numerical method is used to obtain rough solutions and ML models are utilized to improve accuracy further. In our framework, an efficient numerical solver, AMG-PCG, is applied to get rough numerical solutions. Then, based on the numerical solution, the fusion of hierarchical numerical-structural information representing the multilayer structure of the PG is employed, and an Inception Attention U-Net model is designed to capture details and interaction of features at different scales. To cope with the limitations and diversity of PG designs, an augmented curriculum learning strategy is applied to the training phase. Evaluation of IR-Fusion shows that its accuracy is significantly better than previous ML-based methods while requiring considerably less iteration on solver to achieve the same accuracy compared with numerical methods.

Subcircuit boundary prediction is an important application of machine learning in logical analysis, effectively supporting tasks such as functional verification and logic optimization. Existing methods often convert circuits into and-inverter graphs and then use directed acyclic graph neural networks to perform this task. However, two key characteristics of subcircuit boundary prediction do not align with the fundamental assumptions of directed acyclic graph (DAG) learning, which limits the model's expressiveness and generalization capabilities. To break these assumptions, we propose WideGate, which includes a receptive field generation module that extends beyond the fanin cone and fanout cone, as well as an adaptive aggregation module that focuses on boundaries. Extensive experiments show that WideGate significantly outperforms existing methods in terms of prediction accuracy and training efficiency for sub circuit boundary prediction. The code is available at https://github.com/BUPT-GAMMA/WideGate.

Graph representation learning on Analog-Mixed Signal (AMS) circuits is crucial for various downstream tasks, e.g., parasitic estimation. However, the scarcity of design data, the unbalanced distribution of labels, and the inherent diversity of circuit implementations pose significant challenges to learning robust and transferable circuit representations. To address these limitations, we propose CircuitGCL, a novel graph contrastive learning framework that integrates representation scattering and label rebalancing to enhance transferability across heterogeneous circuit graphs. CircuitGCL employs a self-supervised strategy to learn topology-invariant node embeddings through hyperspherical representation scattering, eliminating dependency on large-scale data. Simultaneously, balanced mean squared error (BMSE) and balanced softmax cross-entropy (BSCE) losses are introduced to mitigate label distribution disparities between circuits, enabling robust and transferable parasitic estimation. Evaluated on parasitic capacitance estimation (edge-level task) and ground capacitance classification (node-level task) across TSMC 28nm AMS designs, CircuitGCL outperforms all state-of-the-art (SOTA) methods, with the R2improvement of 33.64% ~ 44.20% for edge regression and F1-score gain of 0.9× ~ 2.1× for node classification. Our code is available at https://github.com/ShenShan123/CircuitGCL.

Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine learning is witnessing a paradigm transition from shallow methods to more sophisticated deep learning approaches. The capabilities of foundation models in generalization and adaptation motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This paradigm envisions models that are pre-trained on extensive graph data and can be adapted for various graph tasks. Despite this burgeoning interest, there is a noticeable lack of clear definitions and systematic analyses pertaining to this neuicew domain. To this end, this article introduces the concept of Graph Foundation Models (GFMs), and offers an exhaustive explanation of their key characteristics and underlying technologies. We proceed to classify the existing work related to GFMs into three distinct categories, based on their dependence on graph neural networks and large language models. In addition to providing a thorough review of the current state of GFMs, this article also outlooks potential avenues for future research in this rapidly evolving domain.

As feature sizes shrink, the on-chip power grid (PG) faces serious power integrity issues, and static IR drop analysis becomes critical for PG design and optimization. Many machine learning (ML) based methods have been proposed to address the inefficiencies of traditional numerical methods. However, many previous works have ignored the problems of feature confusion and imbalance IR drop distribution. In this work, we propose novel feature augmentation and selection methods to solve the feature confusion problem and use the label distribution smoothing (LDS) technique to handle unbalanced labels. Importantly, we design a static IR drop analysis model for PG using the Attention U-Net architecture (PGAU). Furthermore, two real-world datasets are used for evaluation. Experiments show that our model outperforms baselines, with a 2.6% improvement in the correlation coefficient (CC) and a 22.2% reduction in the mean absolute error (MAE). Moreover, our model is highly transferable and performs better against never-before-seen designs.

Understanding the functionality of Boolean networks is crucial for processes such as functional equivalence checking, logic synthesis and malicious logic identification. With the proliferation of deep learning in electronic design automation (EDA), graph neural networks (GNNs) are widely used for embedding the and-inverter graphs (AIGs), a standard form of Boolean networks, into vectorized representation. A key challenge in the use of GNN for Boolean representation is that although GNNs can well encapsulate the structural properties of AIGs, they usually fail to fully capture the functionality of Boolean logic. Moreover, most GNNs designed for AIGs (also called AIGNNs) either rely on a large amount of training data or require complex supervisory tasks, making it difficult to maintain high training efficiency and prediction accuracy. In this work, for the first time, we focus on breaking the bottleneck of AIGNNs by augmenting their capability of functional representation, providing an efficient solution called PolarGate, which naturally aligns the message passing process with the logical functionality of AIGs. Specifically, we map the behavior of the logic gate into an ambipolar state space, customize differentiable logical operators, and design a functionality-aware message passing strategy. Experimental results on two logically related tasks (i.e., signal probability prediction and truth-table distance prediction) show that PolarGate outperforms the state-of-the-art GNN-based methods for Boolean representation, with an improvement of 62.1% (40.6%) in learning capability and 79.5% (85.6%) in efficiency on two tasks. The code is avaliable at https://github.com/BUPT-GAMMA/PolarGate.

Pre-trained graph models (PGMs) aim to capture transferable inherent structural properties and apply them to different downstream tasks. Similar to pre-trained language models, PGMs also inherit biases from human society, resulting in discriminatory behavior in downstream applications. The debiasing process of existing fair methods is generally coupled with parameter optimization of GNNs. However, different downstream tasks may be associated with different sensitive attributes in reality, directly employing existing methods to improve the fairness of PGMs is inflexible and inefficient. Moreover, most of them lack a theoretical guarantee, i.e., provable lower bounds on the fairness of model predictions, which directly provides assurance in a practical scenario. To overcome these limitations, we propose a novel adapter-tuning framework that endows pre-trained Graph models with Provable fAiRness (called GraphPAR). GraphPAR freezes the parameters of PGMs and trains a parameter-efficient adapter to flexibly improve the fairness of PGMs in downstream tasks. Specifically, we design a sensitive semantic augmenter on node representations, to extend the node representations with different sensitive attribute semantics for each node. The extended representations will be used to further train an adapter, to prevent the propagation of sensitive attribute semantics from PGMs to task predictions. Furthermore, with GraphPAR, we quantify whether the fairness of each node is provable, i.e., predictions are always fair within a certain range of sensitive attribute semantics. Experimental evaluations on real-world datasets demonstrate that GraphPAR achieves state-of-the-art prediction performance and fairness on node classification task. Furthermore, based on our GraphPAR, around 90% nodes have provable fairness.

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep neural networks, it can also introduce quantization noise and reduce prediction accuracy, especially in extremely low-bit settings. How to determine the appropriate quantization parameters (e.g., scaling factors and rounding of weights) is the main problem facing now. Existing methods attempt to determine these parameters by minimize the distance between features before and after quantization, but such an approach only considers local information and may not result in the most optimal quantization parameters. We analyze this issue and propose PD-Quant, a method that addresses this limitation by considering global information. It determines the quantization parameters by using the information of differences between network prediction before and after quantization. In addition, PD-Quant can alleviate the overfitting problem in PTQ caused by the small number of calibration sets by adjusting the distribution of activations. Experiments show that PD-Quant leads to better quantization parameters and improves the prediction accuracy of quantized models, especially in low-bit settings. For example, PD-Quant pushes the accuracy of ResNet-18 up to 53.14% and RegNetX-600MF up to 40.67% in weight 2-bit activation 2-bit. The code is released at https://github.com/hustv1/PD-Quant.

Abnormal event detection, which refers to mining unusual interactions among involved entities, plays an important role in many real applications. Previous works mostly oversimplify this task as detecting abnormal pair-wise interactions. However, real-world events may contain multi-typed attributed entities and complex interactions among them, which forms an Attributed Heterogeneous Information Network (AHIN). With the boom of social networks, abnormal event detection in AHIN has become an important, but seldom explored task. In this paper, we firstly study the unsupervised abnormal event detection problem in AHIN. The events are considered as star-schema instances of AHIN and are further modeled by hypergraphs. A novel hypergraph contrastive learning method, named AEHCL, is proposed to fully capture abnormal event patterns. AEHCL designs the intra-event and inter-event contrastive modules to exploit self-supervised AHIN information. The intra-event contrastive module captures the pair-wise and multivariate interaction anomalies within an event, and the inter-event module captures the contextual anomalies among events. These two modules collaboratively boost the performance of each other and improve the detection results. During the testing phase, a contrastive learning-based abnormal event score function is further proposed to measure the abnormality degree of events. Extensive experiments on three datasets in different scenarios demonstrate the effectiveness of AEHCL, and the results improve state-of-the-art baselines up to 12.0% in Average Precision (AP) and 4.6% in Area Under Curve (AUC) respectively.

Graph Neural Networks (GNNs) can effectively capture both the topology and attribute information of a graph, and have been extensively studied in many domains. Recently, there is an emerging trend that equips GNNs with knowledge distillation for better efficiency or effectiveness. However, to the best of our knowledge, existing knowledge distillation methods applied on GNNs all employed predefined distillation processes, which are controlled by several hyper-parameters without any supervision from the performance of distilled models. Such isolation between distillation and evaluation would lead to suboptimal results. In this work, we aim to propose a general knowledge distillation framework that can be applied on any pretrained GNN models to further improve their performance. To address the isolation problem, we propose to parameterize and learn distillation processes suitable for distilling GNNs. Specifically, instead of introducing a unified temperature hyper-parameter as most previous work did, we will learn node-specific distillation temperatures towards better performance of distilled models. We first parameterize each node's temperature by a function of its neighborhood's encodings and predictions, and then design a novel iterative learning process for model distilling and temperature learning. We also introduce a scalable variant of our method to accelerate model training. Experimental results on five benchmark datasets show that our proposed framework can be applied on five popular GNN models and consistently improve their prediction accuracies with 3.12% relative enhancement on average. Besides, the scalable variant enables 8 times faster training speed at the cost of 1% prediction accuracy.

Semi-supervised learning on graphs is an important problem in the machine learning area. In recent years, state-of-the-art classification methods based on graph neural networks (GNNs) have shown their superiority over traditional ones such as label propagation. However, the sophisticated architectures of these neural models will lead to a complex prediction mechanism, which could not make full use of valuable prior knowledge lying in the data, e.g., structurally correlated nodes tend to have the same class. In this paper, we propose a framework based on knowledge distillation to address the above issues. Our framework extracts the knowledge of an arbitrary learned GNN model (teacher model), and injects it into a well-designed student model. The student model is built with two simple prediction mechanisms, i.e., label propagation and feature transformation, which naturally preserves structure-based and feature-based prior knowledge, respectively. In specific, we design the student model as a trainable combination of parameterized label propagation and feature transformation modules. As a result, the learned student can benefit from both prior knowledge and the knowledge in GNN teachers for more effective predictions. Moreover, the learned student model has a more interpretable prediction process than GNNs. We conduct experiments on five public benchmark datasets and employ seven GNN models including GCN, GAT, APPNP, SAGE, SGC, GCNII and GLP as the teacher models. Experimental results show that the learned student model can consistently outperform its corresponding teacher model by on average. Code and data are available at https://github.com/BUPT-GAMMA/CPF

Most of existing clustering algorithms are proposed without considering the selection bias in data. In many real applications, however, one cannot guarantee the data is unbiased. Selection bias might bring the unexpected correlation between features and ignoring those unexpected correlations will hurt the performance of clustering algorithms. Therefore, how to remove those unexpected correlations induced by selection bias is extremely important yet largely unexplored for clustering. In this paper, we propose a novel Decorrelation regularized K-Means algorithm (DCKM) for clustering with data selection bias. Specifically, the decorrelation regularizer aims to learn the global sample weights which are capable of balancing the sample distribution, so as to remove unexpected correlations among features. Meanwhile, the learned weights are combined with k-means, which makes the reweighted k-means cluster on the inherent data distribution without unexpected correlation influence. Moreover, we derive the updating rules to effectively infer the parameters in DCKM. Extensive experiments results on real world datasets well demonstrate that our DCKM algorithm achieves significant performance gains, indicating the necessity of removing unexpected feature correlations induced by selection bias when clustering.