Graph Matching Research Articles

Mobility-Aware Task Offloading Scheme for 6G Networks With Temporal Graph and Graph Matching

Mobility-Aware Task Offloading Scheme for 6G Networks With Temporal Graph and Graph Matching

Graph alignment exploiting the spatial organization improves the similarity of brain networks.

Every brain is unique, having its structural and functional organization shaped by both genetic and environmental factors over the course of its development. Brain image studies tend to produce results by averaging across a group of subjects, under the common assumption that it is possible to subdivide the cortex into homogeneous areas while maintaining a correspondence across subjects. We investigate this assumption: can the structural properties of a specific region of an atlas be assumed to be the same across subjects? This question is addressed by looking at the network representation of the brain, with nodes corresponding to brain regions and edges to their structural relationships. Using an unsupervised graph matching strategy, we align the structural connectomes of a set of healthy subjects, considering parcellations of different granularity, to understand the connectivity misalignment between regions. First, we compare the obtained permutations with four different algorithm initializations: Spatial Adjacency, Identity, Barycenter, and Random. Our results suggest that applying an alignment strategy improves the similarity across subjects when the number of parcels is above 100 and when using Spatial Adjacency and Identity initialization (the most plausible priors). Second, we characterize the obtained permutations, revealing that the majority of permutations happens between neighbors parcels. Lastly, we study the spatial distribution of the permutations. By visualizing the results on the cortex, we observe no clear spatial patterns on the permutations and all the regions across the context are mostly permuted with first and second order neighbors.

PrivFusion: Privacy-Preserving Model Fusion via Decentralized Federated Graph Matching

PrivFusion: Privacy-Preserving Model Fusion via Decentralized Federated Graph Matching

Contrastive Learning Network for Unsupervised Graph Matching

Contrastive Learning Network for Unsupervised Graph Matching

Graph-Based Robust Localization of Object-Level Map for Mobile Robotic Navigation

Global localization is an integral part of indoor robot navigation. Traditional methods implemented at image-level still face challenges when encountering dynamic environments, illumination variation and large viewpoint changes. Methods based on 3D point cloud have low computational efficiency and high localization difficulty. In this case, an efficient global localization framework based on graph matching to solve the problem of low localization stability in object-level navigation and robot abduction is proposed. Firstly, semantic information is extracted by the instance segmentation network. An efficient 3D bounding box extraction algorithm is used to obtain the object-level map. Then the object-level map is transformed into a semantic topological graph and preprocessed. The feature matrix of the map is obtained by the tree generation and the graph kernel method. The matching method based on the voting mechanism is adopted to realize the correspondence between the local graph and the global graph. Finally, the pose of the robot is obtained by a two-stage point cloud registration method. Experiments are carried out in SceneNN dataset and three real indoor environments. Extensive experiments show that our approach reaches high accuracy and can achieve robust global localization under large viewpoint changes.

Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining.

The success of existing cross-modal retrieval (CMR) methods heavily rely on the assumption that the annotated cross-modal correspondence is faultless. In practice, however, the correspondence of some pairs would be inevitably contaminated during data collection or annotation, thus leading to the so-called Noisy Correspondence (NC) problem. To alleviate the influence of NC, we propose a novel method termed Consistency REfining And Mining (CREAM) by revealing and exploiting the difference between correspondence and consistency. Specifically, the correspondence and the consistency only be coincident for true positive and true negative pairs, while being distinct for false positive and false negative pairs. Based on the observation, CREAM employs a collaborative learning paradigm to detect and rectify the correspondence of positives, and a negative mining approach to explore and utilize the consistency. Thanks to the consistency refining and mining strategy of CREAM, the overfitting on the false positives could be prevented and the consistency rooted in the false negatives could be exploited, thus leading to a robust CMR method. Extensive experiments verify the effectiveness of our method on three image-text benchmarks including Flickr30K, MS-COCO, and Conceptual Captions. Furthermore, we adopt our method into the graph matching task and the results demonstrate the robustness of our method against fine-grained NC problem. The code is available on https://github.com/XLearning-SCU/2024-TIP-CREAM.

A Novel Approach for Single-Shot Target Recognition by Matching Graph of Feature Pixels

Image feature extraction and matching constitute fundamental steps in computer vision and image analysis, enabling various applications ranging from object recognition to scene reconstruction. Object recognition is one of the major applications of artificial intelligence. Since last two decades, different techniques for object recognition were given by researchers from across the world. This paper presents a novel approach for automatic target recognition in autonomous weapons by matching connected graph of feature pixels. The Moving and Stationary Target Acquisition and Recognition (MSTAR) is taken for experimental purpose. The Proposed model has three stages for a target recognition; Image Denoising, Feature extraction & graph generation, and feature matching. Firstly, a sample image of targets taken from the MSTAR is taken as an input. Further, input sample is de-noised and features are extracted using Speeded-Up Robust Features (SURF) algorithm. Thereafter, a graph is created using feature pixels and this complete process is repeated with test image. Further, both graphs are compared using a proposed feature graph matching algorithm which results an recognition accuracy score. Proposed model is tested over the MSTAR dataset and it resulted in varying accuracy at different feature matching thresholds.

EDTBERT: Event Detection and Tracking in Twitter using Graph Clustering and Pre-trained Language Model

The identification of events from social media platforms such as Twitter (now known as X) is a hot research problem. It has applications in diverse domains such as journalism, marketing, public safety, crisis management and disaster response. The process includes the identification, monitoring, and analysis of events or incidents while they are being discussed or reported on Twitter. When it comes to identifying events from tweets (i.e. feeds from Twitter), many of the currently available event detection methods mainly rely on keyword burstiness features or structural changes in the network. However, due to the intricate characteristics of tweets and the ever-changing nature of events, they frequently fail to recognise noteworthy occurrences before they become trending. Moreover, these methods face difficulties when it comes to capturing the evolving characteristics of events with limited or insufficient contextual information. In this paper, we propose a window-based tweet-processing method called EDTBERT for detecting events and tracking the evolution of events over time. Our proposed method utilizes the structural and semantic affinities that exist among words in tweets. The method starts by generating graph of tweets, where tweets are represented as nodes, and edges are the similarities between tweets. The method utilizes overlapping hashtags and named entities to capture the structural relationship between tweets. Additionally, a pre-trained sentence transformer model, specifically BERT, is employed to collect contextual knowledge and find semantically similar tweets. Next, the graph clustering technique is employed to identify optimized event clusters. Subsequently, our method generates chain of event clusters for each event to track the evolving variation of the event over time by utilising the ”Maximum-Weight Bipartite Graph Matching” (MWBGM) algorithm. The effectiveness of our approach is assessed using standard Tweet Datasets. Our evaluation demonstrates that our approach outperforms the baseline approaches.

Sparse graph matching network for temporal language localization in videos

Temporal language localization in videos aims to retrieve the moment that best matches the text description in the untrimmed video using the query text. Existing methods using graph convolutional networks have been effective in feature representation and cross-modal interaction, but the existing methods do not consider the sparsity constraint of the graph when constructing the graph structure, which can easily cause an increase in computational cost and introduce redundant connections that may adversely affect the accuracy of the results. Therefore, we propose a novel sparse graph matching network for temporal language localization in videos. Specifically, we use graph convolutional networks to learn video features and dynamically construct video graph with constraints on sparsity and connectivity; the complementarity between the sequential context and the syntactic structure of text is used to model the semantic features of text. For cross-modal interaction, we design a sparse graph matching method based on affinity matrix to match video and text graphs, and align cross-modal semantic features. Finally, by fusing the features of the two modalities, candidate moments are generated, and their confidence scores are calculated to locate the moment matching the query. Experimental results on the public datasets TACoS, ActivityNet Caption, and QVHighlights demonstrate the superiority of our method compared to state-of-the-art methods.

DGTRL: Deep graph transfer reinforcement learning method based on fusion of knowledge and data

Deep reinforcement learning has shown promising application effects in many fields. However, issues such as low sample efficiency and weak knowledge transfer and generalization capabilities constrain its in-depth development. This paper proposes a deep graph transfer reinforcement learning method based on knowledge and data fusion. Through knowledge transfer between tasks and data training in exploration, efficient learning driven by knowledge and data fusion is realized. First, we map the trajectories of agents in the source and target domains into graph structures to represent knowledge and environmental models and use a graph matching method to match the knowledge adaptation domain based on similarity. Second, real-time transfer of source domain knowledge is carried out in a similar mapping domain, and policy mapping, verification, and adaptive transfer mechanisms based on knowledge reuse frequency are designed to effectively improve the transfer effect. Finally, we evaluate and validate the proposed algorithm, mechanism, and their application effectiveness in diverse and multitask knowledge transfer scenarios using three indicators in environments such as maze. The results show that the method improves the target task time indicators by 84.7% and 70% under the conditions of no verification exploration and a standard transfer setting, respectively, achieving significant knowledge reuse effects.

Edge-Connectivity and Pairwise Disjoint Perfect Matchings in Regular Graphs

For 0≤t≤r\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0 \\le t \\le r$$\\end{document} let m(t, r) be the maximum number s such that every t-edge-connected r-graph has s pairwise disjoint perfect matchings. There are only a few values of m(t, r) known, for instance m(3,3)=m(4,r)=1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$m(3,3)=m(4,r)=1$$\\end{document}, and m(t,r)≤r-2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$m(t,r) \\le r-2$$\\end{document} for all t≠5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$t \ ot = 5$$\\end{document}, and m(t,r)≤r-3\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$m(t,r) \\le r-3$$\\end{document} if r is even. We prove that m(2l,r)≤3l-6\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$m(2l,r) \\le 3l - 6$$\\end{document} for every l≥3\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l \\ge 3$$\\end{document} and r≥2l\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$r \\ge 2 l$$\\end{document}.

Seeing both sides: context-aware heterogeneous graph matching networks for extracting-related arguments

Our research focuses on extracting exchanged views from dialogical documents through argument pair extraction (APE). The objective of this process is to facilitate comprehension of complex argumentative discourse by finding the related arguments. The APE comprises two stages: argument mining and argument matching. Researchers typically employ sequence labeling models for mining arguments and text matching models to calculate the relationships between them, thereby generating argument pairs. However, these approaches fail to capture long-distance contextual information and struggle to fully comprehend the complex structure of arguments. In our work, we propose the context-aware heterogeneous graph matching (HGMN) model for the APE task. First, we design a graph schema specifically tailored to argumentative texts, along with a heterogeneous graph attention network that effectively captures context information and structural information of arguments. Moreover, the text matching between arguments is converted into a graph matching paradigm and a multi-granularity graph matching model is proposed to handle the intricate relationships between arguments at various levels of granularity. In this way, the semantics of argument are modeled structurally and thus capture the complicated correlations between arguments. Extensive experiments are conducted to evaluate the HGMN model, including comparisons with existing methods and the GPT series of large language models (LLM). The results demonstrate that HGMN outperforms the state-of-the-art method.

Landmark Topology Descriptor-Based Place Recognition and Localization under Large View-Point Changes.

Accurate localization between cameras is a prerequisite for a vision-based heterogeneous robot systems task. The core issue is how to accurately perform place recognition from different view-points. Traditional appearance-based methods have a high probability of failure in place recognition and localization under large view-point changes. In recent years, semantic graph matching-based place recognition methods have been proposed to solve the above problem. However, these methods rely on high-precision semantic segmentation results and have a high time complexity in node extraction or graph matching. In addition, methods only utilize the semantic labels of the landmarks themselves to construct graphs and descriptors, making such approaches fail in some challenging scenarios (e.g., scene repetition). In this paper, we propose a graph-matching method based on a novel landmark topology descriptor, which is robust to view-point changes. According to the experiment on real-world data, our algorithm can run in real-time and is approximately four times and three times faster than state-of-the-art algorithms in the graph extraction and matching phases, respectively. In terms of place recognition performance, our algorithm achieves the best place recognition precision at a recall of 0-70% compared with classic appearance-based algorithms and an advanced graph-based algorithm in the scene of significant view-point changes. In terms of positioning accuracy, compared to the traditional appearance-based DBoW2 and NetVLAD algorithms, our method outperforms by 95%, on average, in terms of the mean translation error and 95% in terms of the mean RMSE. Compared to the state-of-the-art SHM algorithm, our method outperforms by 30%, on average, in terms of the mean translation error and 29% in terms of the mean RMSE. In addition, our method outperforms the current state-of-the-art algorithm, even in challenging scenarios where the benchmark algorithms fail.

Dictionary-based matching graph network for biomedical named entity recognition

Biomedical named entity recognition (BioNER) is an essential task in biomedical information analysis. Recently, deep neural approaches have become widely utilized for BioNER. Biomedical dictionaries, implemented through a masked manner, are frequently employed in these methods to enhance entity recognition. However, their performance remains limited. In this work, we propose a dictionary-based matching graph network for BioNER. This approach utilizes the matching graph method to project all possible dictionary-based entity combinations in the text onto a directional graph. The network is implemented coherently with a bi-directional graph convolutional network (BiGCN) that incorporates the matching graph information. Our proposed approach fully leverages the dictionary-based matching graph instead of a simple masked manner. We have conducted numerous experiments on five typical Bio-NER datasets. The proposed model shows significant improvements in F1 score compared to the state-of-the-art (SOTA) models: 2.8% on BC2GM, 1.3% on BC4CHEMD, 1.1% on BC5CDR, 1.6% on NCBI-disease, and 0.5% on JNLPBA. The results show that our model, which is superior to other models, can effectively recognize natural biomedical named entities.

Solving dynamic vehicle routing problem with time windows by ant colony system with bipartite graph matching

Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) is an extension of the traditional VRPTW by considering dynamic customer characteristics. In this problem, new customers with specific time windows are received dynamically as time progresses and must be incorporated into the evolving schedule. The goal of DVRPTW is to use the minimum number of vehicles to fulfill all the customer demands with the minimum total traveling time. Little work has been done for solving this dynamic variant. In this paper, an evolutionary algorithm using Ant Colony System and Kuhn-Munkres bipartite graph matching, named ACS-KM, is proposed. It can tackle the dynamic issues during the evolutionary process. Experiments show that the proposed algorithm is very effective and has fast convergence. It achieves the best results on 40 out of 48 benchmark instances. For the DVRPTW instances with different levels of dynamicity, the algorithm can always produce better solutions than the previous works.

Anti-Ramsey number of matchings in outerplanar graphs

A subgraph of an edge-colored graph is rainbow if all of its edges have different colors. Given a graph family G and a graph H, the anti-Ramsey number AR(G,H) is the maximum number of colors in an edge-coloring of a graph G∈G which has no rainbow copy of H. When G={G}, we write AR(G,H) for short. Erdős, Simonovits and Sós introduced these numbers in the 1970s, they studied the case when G is a complete graph. Since then, many results have appeared considering G and H belonging to specific graph classes. In particular, Jendrol’, Schiermeyer and Tu (Jendrol’ et al., 2014) obtained an upper bound for AR(Tn,kK2) in terms of n and k for k≥3 and n≥2k, where Tn is the family of maximal planar graphs on n vertices. Jin and Ye (Jin and Ye, 2018) continued the study of anti-Ramsey numbers of matchings in planar graphs, by deriving an upper bound for AR(Mn,kK2), where Mn is the family of maximal outerplanar graphs on n vertices. In both works, examples are shown for which there are colorings using many colors while avoiding rainbow matchings, but the numbers of colors in these examples do not reach the upper bounds. The bounds of AR(Tn,kK2) were improved in following works by other researchers. This paper goes in the same direction of these two works, proving exact value for AR(Bn,kK2) in terms of n and k for n≥6 and k≥3, where Bn is the family of maximal bipartite outerplanar graphs on n vertices which contains a Hamilton cycle.

Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions.

Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods. The source code is available here, or you can visit this website: https://github.com/RenMin1991/Dyamic-Graph-Representation.

A New Approach on Bipolar Second Degree Perfect Fuzzy Matching for Bipolar Fuzzy Graphs Based on Vertices

Graph is a visual representation of data. In mathematics, graph is a structure which creates the pairwise relation between objects. The objects are known as nodes or vertices and the connection between two nodes are known as links or edges. A graph is a symmetric binary relation on a non-empty set whereas Fuzzy graph is a symmetric binary fuzzy relation on a fuzzy subset. Bipolar Fuzzy graph is a generalization of graph theory by using bipolar Fuzzy set. The bipolar Fuzzy sets are the extension of Fuzzy sets. Our main objective is to introduce Bipolar Second Degree Perfect Fuzzy Matching for Bipolar Fuzzy Graph based on vertices. Secondly, we proved the necessary conditions under which they are equivalent and also proved that for a particular condition a perfect second-degree fuzzy matching is not a regular bipolar fuzzy graph. Next, we discussed about perfect second-degree Fuzzy matching and second degree fuzzy matching number for bipolar fuzzy graph on the cycle.

An Approach to Comparing Java Programs through the Graph Edit Distance with Similar Instruction Matching of Control Flow Graphs

An Approach to Comparing Java Programs through the Graph Edit Distance with Similar Instruction Matching of Control Flow Graphs

Presenting a model based on knowledge management in modeling and optimizing the dynamic viscosity of MWCNT (30%) - ZnO (70%) / SAE 40 oil hybrid nano-lubricant with response surface methodology (RSM) for industrial uses

Thermophysical characteristics of MWCNT-ZnO (30–70%)/SAE40 hybrid nanofluid (HNF) using knowledge management cycle and RSM in different solid volume fractions (SVFs), temperature and shear rates (SRs) have been investigated. Emphasis on knowledge management through the use of fast and high-precision methods has led to the use of the RSM for modeling the viscosity of HNF. Different models such as linear model, 2FI, Quadratic, Cubic, Quartic, Fifth and Sixth models are presented. Fifth order model is better than others. Values of R2, Predicted R² and Adjusted R² for all three parameters are 0.9998, which displays good precision of the modeling. The knowledge management cycle is used to evaluate the model to increase sufficient confidence. Examining the matching graphs, deviation coefficient and standard deviation parameters displays good precision of modeling. MOD value is also within ± 2%. With the help of knowledge management in finding the best mode, the optimal viscosity value is equal to 209.53 mPa.sec in temperature, SVF and SR, respectively 31.156 °C, 0.063 % and 933.923 s−1.