High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but practical HLS design flows begin with a tedious step: refactoring software into HLS-compatible programs. Converting real-world software remains challenging due to restrictive language support and the gap between software and hardware programming practices, and this preparatory phase can take domain experts days even for an initial synthesizable design. Existing automated refactoring methods and recent LLM-based workflows partially address this problem, yet they often fall short in generalizability, scalability, and cost efficiency.

Abstract Context-sensitive graph grammars are natural formalisms for the generation and parsing of visual programming languages. Being intuitive, rigorous, and expressive tools, they have been frequently employed in a wide range of research fields. Nevertheless, the expressive powers of the existing context-sensitive formalisms have not been investigated yet. To this end, this paper is dedicated to the comparison of expressive powers of the two prevalent graph grammar formalisms, Reserved Graph Grammar (RGG) and Edge-based Graph Grammar (EGG). By introducing a special variant of RGG as an intermediary, the relation between them concerning the expressive power is revealed that the set of graph languages of EGG is a proper subset of that of RGG. Moreover, bidirectional transformations between EGG and the variant of RGG are accordingly established, allowing them to take the advantages of each other in applications.

Abstract Automatic generation of image captions is essentially a cross‐modal conversion from image to text. Owing to the differences in linguistic characteristics between Chinese and English, quite a few Chinese image captioning methods have recently been proposed. Nevertheless, the existing Chinese image captioning models usually lack attention to local details of images or tend to produce general descriptions. To address these challenges, a Chinese image captioning method is proposed that incorporates fusion encoder, visual keyword search, and reinforcement learning. The fusion encoder can simultaneously extract local and global features of the input image to enrich the semantic information in the decoding stage, visual keyword search can pursue potential visual words associated with the image content, and the reinforcement learning mechanism can optimize the evaluation metric CIDEr at sentence level to promote the lexical diversity of image description. The results of extensive experiments demonstrate that the proposed model outperforms the state‐of‐the‐art models and delivers expressive and informative Chinese image captions.

Generative Adversarial Nets (GAN) has been a popular research topic in processing of images, speech, texts, and videos, and many other fields.However, GAN still has some drawbacks such as unstable training and mode collapse.To address these challenges, this paper proposes an auto-encoding GAN, which is composed of a set of generators, a discriminator, an encoder and a decoder.A set of generators is responsible for learning different modes, accelerating the convergence of the model and preventing model collapse.The discriminator is used to distinguish between real samples and generated ones.In order to improve feature representation of the encoder and prevent multiple generators from covering a certain mode, an approach consisting of three phases is proposed accordingly.First, a clustering algorithm is presented to perceive the distribution of real and generated samples.Then, cluster center matching is utilized to keep consistency of the distribution of real and generated samples.Finally, the encoder and decoder are jointly optimized by the generated and real samples.Therefore, the encoder can map the generated and real samples to the embedding space so as to encode distinguishable features, and the decoder can distinguish from which generator the generated samples come and from which mode the real samples come.Experiments are conducted on image datasets to verify effectiveness of the auto-encoding GAN for reducing mode collapse and enhancing feature representation.

Graph Convolutional Network (GCN) is a new method for extracting, learning, and inferencing graph data that builds an embedded representation of the target node by aggregating information from neighbouring nodes. GCN is decisive for node classification and link prediction tasks in recent research. Although the existing GCN performs well, we argue that the current design ignores the potential features of the node. In addition, the presence of features with low correlation to nodes can likewise limit the learning ability of the model. Due to the above two problems, we propose Feature Recommendation Strategy (FRS) for Graph Convolutional Network in this paper. The core of FRS is to employ a principled approach to capture both node-to-node and node-to-feature relationships for encoding, then recommending the maximum possible features of nodes and replacing low-correlation features, and finally using GCN for learning of features. We perform a node clustering task on three citation network datasets and experimentally demonstrate that FRS can improve learning on challenging tasks relative to state-of-the-art (SOTA) baselines.

Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines.

Abstract As a two-dimensional formal method, graph grammar is widely used in defining various visual programming languages. This paper presents a new graph grammar formalism called coordinate graph grammar (CGG). CGG is extended from the edge-based graph grammar (EGG) by introducing the spatial mechanism into the theoretical framework, which consists of continuous coordinate graph grammar (cCGG) and discrete coordinate graph grammar (dCGG). By combining quantitative and qualitative spatial semantics in one framework, CGG provides strong expressiveness and flexibility for specifying various spatial graphs. This paper focuses on several important issues on the new formalism. First, the theoretical framework of CGG is given. Second, two matching algorithms for cCGG and dCGG are proposed, which use the spatial relationships between nodes to narrow down the search space during parsing. Finally, an application of CGG is demonstrated, which generates parsable flowcharts in a uniform layout.

Context-sensitive graph grammars have been suitable formalisms for specifying visual programming languages, as they are intuitive, sufficient expressive and equipped with parsing mechanisms. Parsing has been a fundamental issue in the research of context-sensitive graph grammars. However, the existent parsing algorithms are either inefficient or confined to a minority of graph grammars. This paper presents two strategies for general parsing algorithms, one is context matching, and the other is partitioning of productions. Through narrowing down the searching space of potential redexex, the two strategies can considerably improve the parsing performance.

Summary As a two‐dimensional formal tool, graph grammars are capable of handling the layout problems of visual programming languages. Based on an edge‐based graph grammar (EGG), this paper proposes a novel layout approach that uses the unique features of EGG and overcomes the weakness of existing layout approaches. In order to make the approach rigorous yet concise, the graph grammar mechanisms with layout constraints and quantitative analysis techniques are combined together as an integrity. First, the basic notions of EGG are briefly introduced; second, the layout approach is presented that consists of two phases, ie, bottom‐up parsing and top‐down derivation. Finally, a case study is given by taking the standard flowchart as an example to demonstrate the working process of the proposed approach.

Context-sensitive graph grammars have been rigorous formalisms for specifying visual programming languages, as they possess sufficient expressive powers and intuitive forms. Efficient parsing mechanisms are essential to these formalisms. However, the existent parsing algorithms are either inefficient or confined to a minority of graph grammars. This paper introduces the notion of partial precedence, defines the partial precedence graph of a graph grammar and theoretically unveils the existence of a valid parsing path conforming to the topological orderings of the partial precedence graph. Then, it provides algorithms for computing the partial precedence graph and presents an approach to improving general parsing algorithms with the graph based on the drawn conclusion. It is shown that the approach can considerably improve the efficiency of general parsing algorithms.

To stay on the cutting edge, Web services ought to adapt themselves to the evolving business requirements and the changing environments. For a long-running service choreography, its member services may need to evolve even at run-time. However, inconsistencies or spurious results (e.g., unspecified receptions and deadlocks) may occur if these services evolve dynamically in an uncoordinated manner. To cope with this problem, we propose an approach that supports the dynamic evolution of choreographies. In our approach, two mechanisms are proposed to make sure that the choreography evolution can be conducted in an orderly fashion. First, an evolution protocol is proposed to support dynamic co-evolution of the member services in a choreography. Second, the proposed approach restricts choreography changes to one single service only if the relevant partner services can evolve simultaneously. A typical purchase order application is used to motivate our proposal and illustrate the viability of our approach.

Self-adaptive software is expected to adjust itself attributes or structures at runtime in response to changes. Aiming at addressing some challenging problems such as difficult mathematically modeling software using the current control theoretical methods, we propose a novel fuzzy-control-based approach to achieve self-adaptive software, which is presented as framework of fuzzy self-adaptive software (FFSAS). In this framework, the general model, the implementation architecture, and the design methodology are put forward and discussed in detail. The fuzzy-control-based approach is evaluated with a news-website case study.