Deep generative models have achieved great success in areas such as image, speech, and natural language processing the past few years. Thanks to advances graph-based deep learning, particular graph representation generation methods recently emerged with new applications ranging from discovering novel molecular structures modeling social networks. This paper conducts a comprehensive survey on learning-based approaches classifies them into five broad categories, namely, autoregressive,...

Graph data structures are fundamental for studying connected entities. With an increase in the number of applications where is represented as graphs, problem graph generation has recently become a hot topic. However, despite its significance, conditional that creates graphs with desired features relatively less explored previous studies. This paper addresses class-conditional uses class labels constraints by introducing Class Conditioned Generator (CCGG). We built CCGG injecting information...

Deep learning-based graph generation approaches have remarkable capacities for data modeling, allowing them to solve a wide range of real-world problems. Making these methods able consider different conditions during the procedure even increases their effectiveness by empowering generate new samples that meet desired criteria. This paper presents conditional deep method called SCGG considers particular type structural conditions. Specifically, our proposed model takes an initial subgraph and...

Missing data is unavoidable in graphs, which can significantly affect the accuracy of downstream tasks. Many methods have been proposed to mitigate missing partially observed graphs. Most these approaches assume they complete access graph nodes and only focus on recovering links, while practice a part also be out access. This work presents Deep Node Predictor (DMNP), novel deep learning-based approach partly Our does not rely additional information that many cases exist. We compare our model...

Temporal Graph Neural Networks have garnered substantial attention for their capacity to model evolving structural and temporal patterns while exhibiting impressive performance. However, it is known that these architectures are encumbered by issues constrain performance, such as over-squashing over-smoothing. Meanwhile, Transformers demonstrated exceptional computational effectively address challenges related long-range dependencies. Consequently, we introduce Todyformer-a novel...

Electronic Design Automation (EDA) is essential for IC design and has recently benefited from AI-based techniques to improve efficiency. Logic synthesis, a key EDA stage, transforms high-level hardware descriptions into optimized netlists. Recent research employed machine learning predict Quality of Results (QoR) pairs And-Inverter Graphs (AIGs) synthesis recipes. However, the severe scarcity data due very limited number available AIGs results in overfitting, significantly hindering...

Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining implementation of circuits. Logic Synthesis Optimization (LSO) operates at one level within Electronic Design Automation (EDA) workflow, targeting improvements in circuits with respect to performance metrics such as size and speed final layout. Recent trends field show a growing interest leveraging Machine Learning (ML) for EDA, notably through ML-guided synthesis utilizing...

Deep generative models have achieved great success in areas such as image, speech, and natural language processing the past few years. Thanks to advances graph-based deep learning, particular graph representation generation methods recently emerged with new applications ranging from discovering novel molecular structures modeling social networks. This paper conducts a comprehensive survey on learning-based approaches classifies them into five broad categories, namely, autoregressive,...

Deep learning-based graph generation approaches have remarkable capacities for data modeling, allowing them to solve a wide range of real-world problems. Making these methods able consider different conditions during the procedure even increases their effectiveness by empowering generate new samples that meet desired criteria. This paper presents conditional deep method called SCGG considers particular type structural conditions. Specifically, our proposed model takes an initial subgraph and...