Code Graph Research Articles

Small fishing boat classification and recognition method based on GASF temporal graph coding and EMPViT model

Effective classification and identification algorithms of small fishing vessels are the key to strengthen ship management. This paper proposes a classification and recognition method for small fishing boats based on GASF sequence diagram coding, addressing the complex and challenging recognition environment. The method focuses on four typical small fishing vessels, utilizing Gramian Summation Angular Field (GASF) time series images and the Efficiency MPViT (EMPViT) model. Unlike traditional approaches, this study initially employs a high-precision laser sensor to gather one-dimensional contour data of fishing boats. Subsequently, the polynomial fitting method is used to delineate the shape of the fishing boat contour, which is then encoded into a two-dimensional time series image using the GASF encoding method. The enhanced EMPViT model is then applied to classify and identify small fishing vessels, with the results verified through ablation experiments. These experiments demonstrate that the EMPViT model surpasses traditional neural network models such as CNN and ViT in both accuracy and performance, achieving a peak accuracy of 99.98%.

Deep Semantics-Enhanced Neural Code Search

Code search uses natural language queries to retrieve code snippets from a vast database, identifying those that are semantically similar to the query. This enables developers to reuse code and enhance software development efficiency. Most existing code search algorithms focus on capturing semantic and structural features by learning from both text and code graph structures. However, these algorithms often struggle to capture deeper semantic and structural features within these sources, leading to lower accuracy in code search results. To address this issue, this paper proposes a novel semantics-enhanced neural code search algorithm called SENCS, which employs graph serialization and a two-stage attention mechanism. First, the code program dependency graph is transformed into a unique serialized encoding, and a bidirectional long short-term memory (LSTM) model is used to learn the structural information of the code in the graph sequence to generate code vectors rich in structural features. Second, a two-stage attention mechanism enhances the embedded vectors by assigning different weight information to various code features during the code feature fusion phase, capturing significant feature information from different code feature sequences, resulting in code vectors rich in semantic and structural information. To validate the performance of the proposed code search algorithm, extensive experiments were conducted on two widely used code search datasets, CodeSearchNet and JavaNet. The experimental results show that the proposed SENCS algorithm improves the average code search accuracy metrics by 8.30 % (MRR) and 17.85% (DCG) and compared to the best baseline code search model in the literature, with an average improvement of 14.86% in the SR@1 metric. Experiments with two open-source datasets demonstrate SENCS achieves a better search effect than state of-the-art models.

EA4RCA: Efficient AIE accelerator design framework for regular Communication-Avoiding Algorithm

With the introduction of the Adaptive Intelligence Engine (AIE), the Versal Adaptive Compute Acceleration Platform (Versal ACAP) has garnered great attention. However, the current focus of Vitis Libraries and limited research has mainly been on how to invoke AIE modules, without delving into a thorough discussion on effectively utilizing AIE in its typical use cases. As a result, the widespread adoption of Versal ACAP has been restricted. The Communication Avoidance (CA) algorithm is considered a typical application within the AIE architecture. Nevertheless, the effective utilization of AIE in CA applications remains an area that requires further exploration. We propose a top-down customized design framework, EA4RCA (Efficient AIE accelerator design framework for regular Communication-Avoiding Algorithm), specifically tailored for CA algorithms with regular communication patterns, and equipped with AIE Graph Code Generator software to accelerate the AIE design process. The primary objective of this framework is to maximize the performance of AIE while incorporating high-speed data streaming services. Experiments show that for the RCA algorithm Filter2D and Matrix Multiple (MM) with lower communication requirements and the RCA algorithm FFT with higher communication requirements, the accelerators implemented by the RA4RCA framework achieve the highest throughput improvements of 22.19×, 1.05×, and 3.88× compared with the current highest performance acceleration scheme (SOTA), and the highest energy efficiency improvements of 6.11×, 1.30× and 7.00×.

Qudit stabilizer codes, CFTs, and topological surfaces

We study general maps from the space of rational conformal field theories (CFTs) with a fixed chiral algebra and associated Chern-Simons (CS) theories to the space of qudit stabilizer codes with a fixed generalized Pauli group. We consider certain natural constraints on such a map and show that the map can be described as a graph homomorphism from an orbifold graph, which captures the orbifold structure of CFTs, to a code graph, which captures the structure of self-dual stabilizer codes. By studying explicit examples, we show that this graph homomorphism cannot always be a graph embedding. However, we construct a physically motivated map from universal orbifold subgraphs of CFTs to operators in a generalized Pauli group. We show that this map results in a self-dual stabilizer code if and only if the surface operators in the bulk CS theories corresponding to the CFTs in question are self-dual. For CFTs admitting a stabilizer code description, we show that the full Abelianized generalized Pauli group can be obtained from twisted sectors of certain 0-form symmetries of the CFT. Finally, we connect our construction with SymTFTs, and we argue that many equivalences between codes that arise in our setup correspond to equivalence classes of bulk topological surfaces under fusion with invertible surfaces. Published by the American Physical Society 2024

Vul-LMGNNs: Fusing language models and online-distilled graph neural networks for code vulnerability detection

Code Language Models (codeLMs) and Graph Neural Networks (GNNs) are widely used in code vulnerability detection. However, a critical yet often overlooked issue is that GNNs primarily rely on aggregating information from adjacent nodes, limiting structural information transfer to single-layer updates. In code graphs, nodes and relationships typically require cross-layer information propagation to fully capture complex program logic and potential vulnerability patterns. Furthermore, while some studies utilize codeLMs to supplement GNNs with code semantic information, existing integration methods have not fully explored the potential of their collaborative effects.To address these challenges, we introduce Vul-LMGNNs that integrates pre-trained CodeLMs with GNNs, leveraging knowledge distillation to facilitate cross-layer propagation of both code semantic knowledge and structural information. Specifically, Vul-LMGNNs utilizes Code Property Graphs (CPGs) to incorporate code syntax, control flow, and data dependencies, while employing gated GNNs to extract structural information in the CPG. To achieve cross-layer information transmission, we implement an online knowledge distillation (KD) program that enables a single student GNN to acquire structural information extracted from a simultaneously trained counterpart through an alternating training procedure. Additionally, we leverage pre-trained CodeLMs to extract semantic features from code sequences. Finally, we propose an ”implicit-explicit” joint training framework to better leverage the strengths of both CodeLMs and GNNs. In the implicit phase, we utilize CodeLMs to initialize the node embeddings of each student GNN. Through online knowledge distillation, we facilitate the propagation of both code semantics and structural information across layers. In the explicit phase, we perform linear interpolation between the CodeLM and the distilled GNN to learn a late fusion model. The proposed method, evaluated across four real-world vulnerability datasets, demonstrated superior performance compared to 17 state-of-the-art approaches. Our source code can be accessed via GitHub: https://github.com/Vul-LMGNN/vul-LMGGNN.

Upper Bounds for Linear Graph Codes

ABSTRACTA linear graph code is a family of graphs on vertices with the property that the symmetric difference of the edge sets of any two graphs in is also the edge set of a graph in . In this article, we investigate the maximal size of a linear graph code that does not contain a copy of a fixed graph . In particular, we show that if has an even number of edges, the size of the code is , making progress on a question of Alon. Furthermore, we show that for almost all graphs with an even number of edges, there exists such that the size of a linear graph code without a copy of is at most .

Simple Contrastive Graph Clustering.

Contrastive learning has recently attracted plenty of attention in deep graph clustering due to its promising performance. However, complicated data augmentations and time-consuming graph convolutional operations undermine the efficiency of these methods. To solve this problem, we propose a simple contrastive graph clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function. As to the architecture, our network includes two main parts, that is, preprocessing and network backbone. A simple low-pass denoising operation conducts neighbor information aggregation as an independent preprocessing, and only two multilayer perceptrons (MLPs) are included as the backbone. For data augmentation, instead of introducing complex operations over graphs, we construct two augmented views of the same vertex by designing parameter unshared Siamese encoders and perturbing the node embeddings directly. Finally, as to the objective function, to further improve the clustering performance, a novel cross-view structural consistency objective function is designed to enhance the discriminative capability of the learned network. Extensive experimental results on seven benchmark datasets validate our proposed algorithm's effectiveness and superiority. Significantly, our algorithm outperforms the recent contrastive deep clustering competitors with at least seven times speedup on average. The code of SCGC is released at SCGC. Besides, we share a collection of deep graph clustering, including papers, codes, and datasets at ADGC.

Optimal Local Identifying and Local Locating-dominating Codes

We introduce two new classes of covering codes in graphs for every positive integer r. These new codes are called local r-identifying and local r-locating-dominating codes and they are derived from r-identifying and r-locating-dominating codes, respectively. We study the sizes of optimal local 1-identifying codes in binary hypercubes. We obtain lower and upper bounds that are asymptotically tight. Together the bounds show that the cost of changing covering codes into local 1-identifying codes is negligible. For some small n optimal constructions are obtained. Moreover, the upper bound is obtained by a linear code construction. Also, we study the densities of optimal local 1-identifying codes and local 1-locating-dominating codes in the infinite square grid, the hexagonal grid, the triangular grid and the king grid. We prove that seven out of eight of our constructions have optimal densities.

On Three Domination-based Identification Problems in Block Graphs

The problems of determining the minimum-sized identifying, locating-dominating and open locating-dominating codes of an input graph are special search problems that are challenging from both theoretical and computational viewpoints. In these problems, one selects a dominating set C of a graph G such that the vertices of a chosen subset of V(G) (i.e. either V(G) \ C or V(G) itself) are uniquely determined by their neighborhoods in C. A typical line of attack for these problems is to determine tight bounds for the minimum codes in various graph classes. In this work, we present tight lower and upper bounds for all three types of codes for block graphs (i.e. diamond-free chordal graphs). Our bounds are in terms of the number of maximal cliques (or blocks) of a block graph and the order of the graph. Two of our upper bounds verify conjectures from the literature with one of them being now proven for block graphs in this article. As for the lower bounds, we prove them to be linear in terms of both the number of blocks and the order of the block graph. We provide examples of families of block graphs whose minimum codes attain these bounds, thus showing each bound to be tight.

Improved Dual Correlation Reduction Network With Affinity Recovery.

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task. However, we observe that the existing methods suffer from the representation collapse problem and tend to encode samples with different classes into the same latent embedding. Consequently, the discriminative capability of nodes is limited, resulting in suboptimal clustering performance. To address this problem, we propose a novel deep graph clustering algorithm termed improved dual correlation reduction network (IDCRN) through improving the discriminative capability of samples. Specifically, by approximating the cross-view feature correlation matrix to an identity matrix, we reduce the redundancy between different dimensions of features, thus improving the discriminative capability of the latent space explicitly. Meanwhile, the cross-view sample correlation matrix is forced to approximate the designed clustering-refined adjacency matrix to guide the learned latent representation to recover the affinity matrix even across views, thus enhancing the discriminative capability of features implicitly. Moreover, we avoid the collapsed representation caused by the oversmoothing issue in graph convolutional networks (GCNs) through an introduced propagation regularization term, enabling IDCRN to capture the long-range information with the shallow network structure. Extensive experimental results on six benchmarks have demonstrated the effectiveness and efficiency of IDCRN compared with the existing state-of-the-art deep graph clustering algorithms. The code of IDCRN is released at https://github.com/yueliu1999/IDCRN. Besides, we share a collection of deep graph clustering, including papers, codes, and datasets at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering.

Phase Transitions of Structured Codes of Graphs

Phase Transitions of Structured Codes of Graphs

IGnnVD: A novel software vulnerability detection model based on integrated graph neural networks

Software vulnerability detection is a challenging task in the security field, the boom of deep learning technology promotes the development of automatic vulnerability detection. Compared with sequence-based deep learning models, graph neural network (GNN) can learn the structural features of code, it performs well in the field of vulnerability detection for source code. However, different GNNs have different detection results for the same code, and using a single kind of GNN may lead to high false positive rate and false negative rate. In addition, the complex structure of source code causes single GNN model cannot effectively learn their depth feature, thereby leading to low detection accuracy. To solve these limitations, we propose a software vulnerability detection model called iGnnVD based on the integrated graph neural networks. In the proposed iGnnVD model, the base detectors including GCN, GAT and APPNP are first constructed to capture the bidirectional information in the code graph structure with bidirectional structure; And then, the residual connection is used to aggregate the features while retaining the features each time; Finally, the convolutional layer is used to perform the aggregated classification. In addition, an integration module that analyzes the detection results of three detectors for final classification is designed using a voting strategy to solve the problem of high false positive rate and false negative rate caused by using a single kind of base detector. We perform extensive experiments on three datasets and experimental results show that the proposed iGnnVD model can improve the detection accuracy of vulnerabilities in source code as well as reduce the false positive rate and false negative rate compared with existing deep learning-based vulnerability detection models, it also has good stability.

Scalable codes with locality and availability derived from tessellation via [7, 3, 4] Simplex code graph

Abstract A new family of scalable codes with locality and availability for information repair in data storage systems for e-health applications was presented recently. The construction was based on a graph of the [7, 3, 4] Simplex code. In this paper it is shown that the construction can be generalized via tessellation in a Euclidian plane. The codes obtained have new interesting recoverability properties. They can in some cases repair damage to many storage nodes in multiple connected graphs via sequential decoding, which is similar to healing wounds in biological systems. The advantages of the original codes, namely the availability, functionality, efficiency and high data accessibility, will be preserved also in these new codes. The computational complexity and communication costs of their incrementation will remain constant and modest. These codes could be adapted to disaster recovery because it is straightforward to place the nodes so that the graph is easily mapped on a real structure in space.

Author Correction: Engineering holography with stabilizer graph codes

Author Correction: Engineering holography with stabilizer graph codes

Indigo3: A Parallel Graph Analytics Benchmark Suite for Exploring Implementation Styles and Common Bugs

Graph analytics codes are widely used and tend to exhibit input-dependent behavior, making them particularly interesting for software verification and validation. This paper presents Indigo3, a labeled benchmark suite based on 7 graph algorithms that are implemented in different styles, including versions with deliberately planted bugs. We systematically combine 13 sets of implementation styles and 15 common bug types to create the 41,790 CUDA, OpenMP, and parallel C programs in the suite. Each code is labeled with the styles and bugs it incorporates. We used 4 subsets of Indigo3 to test 5 program-verification tools. Our results show that the tools perform quite differently across the bug types and implementation styles, have distinct strengths and weaknesses, and generally struggle with graph codes. We discuss the styles and bugs that tend to be the most challenging as well as the programming patterns that yield false positives.

CogCol: Code Graph-Based Contrastive Learning Model for Code Summarization

Summarizing source code by natural language aims to help developers better understand existing code, making software development more efficient. Since source code is highly structured, recent research uses code structure information like Abstract Semantic Tree (AST) to enhance the structure understanding rather than a normal translation task. However, AST can only represent the syntactic relationship of code snippets, which can not reflect high-level relationships like control and data dependency in the program dependency graph. Moreover, researchers treat the AST as the unique structure information of one code snippet corresponding to one summarization. It will be easily affected by simple perturbations as it lacks the understanding of code with similar structure. To handle the above problems, we build CogCol, a Code graph-based Contrastive learning model. CogCol is a Transformer-based model that converts code graphs into unique sequences to enhance the model’s structure learning. In detail, CogCol uses supervised contrastive learning by building several kinds of code graphs as positive samples to enhance the structural representation of code snippets and generalizability. Moreover, experiments on the widely used open-source dataset show that CogCol can significantly improve the state-of-the-art code summarization models under Meteor, BLEU, and ROUGE.

Identification research of chemical process leakage based on deep learning and correlation-distance graph coding

As a leak identification method in chemical processes, deep learning is limited by inadequate sample labels and highly coupled, nonlinear process variables, therefore difficult to model with a high identification accuracy. To address these problems, a fusion correlation-distance graph (CDG) coding aided deep learning method is proposed. First, the mechanism model is built based on dynamic process data with different leakage labels. Then, the weighted degree and spatial distribution of the dynamic dataset are computed through innovatively designed correlation and distance coding, aided by sliding window fusion into a correlation-distance matrix. Finally, the well-trained long short-term memory (LSTM) is constructed to learn the deep features of the leakage process and identify them. The applications in two industrial cases, CO2 capture and ammonia synthesis, show that CDG-LSTM presents state-of-the-art identification performance with R2 scores of 0.994 and 0.986. 6.6% and 18.4% improvement over LSTM. In addition, the proposed method effectively categorizes the unknown leak samples into known labels with nearby locations, providing a valuable reference for operators to determine the unknown leak locations.

Engineering holography with stabilizer graph codes

The discovery of holographic codes established a surprising connection between quantum error correction and the anti-de Sitter-conformal field theory correspondence. Recent technological progress in artificial quantum systems renders the experimental realization of such holographic codes now within reach. Formulating the hyperbolic pentagon code in terms of a stabilizer graph code, we give gate sequences that are tailored to systems with long-range interactions. We show how to obtain encoding and decoding circuits for the hyperbolic pentagon code, before focusing on a small instance of the holographic code on twelve qubits. Our approach allows to verify holographic properties by partial decoding operations, recovering bulk degrees of freedom from their nearby boundary.

Subgroup total perfect codes in Cayley sum graphs

Subgroup total perfect codes in Cayley sum graphs

FSD-CLCD: Functional semantic distillation graph learning for cross-language code clone detection

Code clone detection can find similar or the same code snippets, which is important in analyzing homologous components, discovering redundant code, and improving software system development and maintenance efficiency. A crucial challenge is to extract more functional semantic similarity from code in heterogeneous conditions, such as a cross-language scenario. Existing methods mainly exploit sequence models with only lexical and statistical features to compare code pairs, which are susceptible to linguistic feature noise and misclassify code pairs that have similar structure dependencies such as control flow. Meanwhile, there are issues with inconsistent node types and a great variation of node numbers while capturing structure-dependent features, resulting in a misaligned distribution of clone pairs, and weakening the detection precision. This work presents a novel cross-language code clone detection method. It represents code with a graph structure based on abstract syntax trees and introduces a global node to strengthen the connection between control flows. Prune the graph structure based on key node protection rules to reduce the impact of linguistic feature noise. Besides, optimize graph matching networks for cross-language abstract syntax trees by using contrastive loss to align the functional semantic distribution of clone pairs. The method distills the invariant functional semantic similarity with a huge discrepancy of the code graph in heterogeneous cross-language conditions. Experiment results show that the proposed method achieves scores of 0.95, 0.98, and 0.96 in terms of precision, recall and F1-score and substantially outperforms the state-of-the-art baselines.