Graph Alignment Research Articles

Graph embedding-based heterogeneous domain adaptation with domain-invariant feature learning and distributional order preserving

Heterogeneous domain adaptation (HDA) methods leverage prior knowledge from the source domain to train models for the target domain and address the differences in their feature spaces. However, incorrect alignment of categories and distribution structure disruption may be caused by unlabeled target samples during the domain alignment process for most existing methods, resulting in negative transfer. Additionally, the previous works rarely focus on the robustness and interpretability of the model. To address these issues, we propose a novel Graph embedding-based Heterogeneous domain-Invariant feature learning and Distributional order preserving framework (GHID). Specifically, a bidirectional robust cross-domain alignment graph embedding structure is proposed to globally align two domains, which learns the domain-invariant and discriminative features simultaneously. In addition, the interpretability of the proposed graph structures is demonstrated through two theoretical analyses, which can elucidate the correlation between important samples from a global perspective in heterogeneous domain alignment scenarios. Then, a heterogeneous discriminative distributional order preserving graph embedding structure is designed to preserve the original distribution relationship of each domain to prevent negative transfer. Moreover, the dynamic centroid strategy is incorporated into the graph structures to improve the robustness of the model. Comprehensive experimental results on four benchmarks demonstrate that the proposed method outperforms other state-of-the-art approaches in effectiveness.

A relation enhanced model for temporal knowledge graph alignment

A relation enhanced model for temporal knowledge graph alignment

IHerd: an integrative hierarchical graph representation learning framework to quantify network changes and prioritize risk genes in disease.

Different genes form complex networks within cells to carry out critical cellular functions, while network alterations in this process can potentially introduce downstream transcriptome perturbations and phenotypic variations. Therefore, developing efficient and interpretable methods to quantify network changes and pinpoint driver genes across conditions is crucial. We propose a hierarchical graph representation learning method, called iHerd. Given a set of networks, iHerd first hierarchically generates a series of coarsened sub-graphs in a data-driven manner, representing network modules at different resolutions (e.g., the level of signaling pathways). Then, it sequentially learns low-dimensional node representations at all hierarchical levels via efficient graph embedding. Lastly, iHerd projects separate gene embeddings onto the same latent space in its graph alignment module to calculate a rewiring index for driver gene prioritization. To demonstrate its effectiveness, we applied iHerd on a tumor-to-normal GRN rewiring analysis and cell-type-specific GCN analysis using single-cell multiome data of the brain. We showed that iHerd can effectively pinpoint novel and well-known risk genes in different diseases. Distinct from existing models, iHerd's graph coarsening for hierarchical learning allows us to successfully classify network driver genes into early and late divergent genes (EDGs and LDGs), emphasizing genes with extensive network changes across and within signaling pathway levels. This unique approach for driver gene classification can provide us with deeper molecular insights. The code is freely available at https://github.com/aicb-ZhangLabs/iHerd. All other relevant data are within the manuscript and supporting information files.

A Domain-Oriented Entity Alignment Approach Based on Filtering Multi-Type Graph Neural Networks

Owing to the heterogeneity and incomplete information present in various domain knowledge graphs, the alignment of distinct source entities that represent an identical real-world entity becomes imperative. Existing methods focus on cross-lingual knowledge graph alignment, and assume that the entities of knowledge graphs in the same language are unique. However, due to the ambiguity of language, heterogeneous knowledge graphs in the same language are often duplicated, and relationship triples are far less than those of cross-lingual knowledge graphs. Moreover, existing methods rarely exclude noisy entities in the process of alignment. These make it impossible for existing methods to deal effectively with the entity alignment of domain knowledge graphs. In order to address these issues, we propose a novel entity alignment approach based on domain-oriented embedded representation (DomainEA). Firstly, a filtering mechanism employs the language model to extract the semantic features of entities and to exclude noisy entities for each entity. Secondly, a Structural Aggregator (SA) incorporates multiple hidden layers to generate high-order neighborhood-aware embeddings of entities that have few relationship connections. An Attribute Aggregator (AA) introduces self-attention to dynamically calculate weights that represent the importance of the attribute values of the entities. Finally, the approach calculates a transformation matrix to map the embeddings of distinct domain knowledge graphs onto a unified space, and matches entities via the joint embeddings of the SA and AA. Compared to six state-of-the-art methods, our experimental results on multiple food datasets show the following: (i) Our approach achieves an average improvement of 6.9% on MRR. (ii) The size of the dataset has a subtle influence on our approach; there is a positive correlation between the expansion of the dataset size and an improvement in most of the metrics. (iii) We can achieve a significant improvement in the level of recall by employing a filtering mechanism that is limited to the top-100 nearest entities as the candidate pairs.

Graph matching for knowledge graph alignment using edge-coloring propagation

Knowledge graph (KG) is a kind of structured human knowledge of modeling the relationships between real-world entities. High quality KG is of crucial importance for many knowledge-based applications, e.g., question answering, recommender systems, etc. This paper studies the problem of entity alignment in KGs to promote knowledge fusion. Existing methods model the semantic representation of entities by using graph structural information or attribute information of the KG and then align the entities across different domains by calculating the distances between entities’ embeddings. However, these methods only consider the node-to-node similarity in the alignment procedure while the edge-to-edge similarity is ignored. Our research hypothesis is that the graph edge alignment information is critical in entity alignment. We reformulate the knowledge entity alignment as a quadratic assignment problem (QAP) by adding relation alignment under the one-to-one mapping constraint. To solve the notorious QAP in a large-scale heterogeneous graph like KG, we propose a model, dual neighborhood consensus network (DNCN), which approximately decomposes the QAP into two small-scale linear assignment problems, i.e., entity alignment and relation alignment. After that, an edge-coloring propagation method is proposed to refine the coarse entity alignment result using the relation correspondence. Theoretical proof shows that this method can guarantee the isomorphism between local sub-graphs. The performance of DNCN is evaluated using the DBP15K and DWY100K benchmarks. Experimental results show that DNCN achieves the best performance on the DBP15K benchmark, and is computationally efficient. Ablation studies verify the importance of graph edge alignment information.

Chaining for accurate alignment of erroneous long reads to acyclic variation graphs.

Aligning reads to a variation graph is a standard task in pangenomics, with downstream applications such as improving variant calling. While the vg toolkit [Garrison et al. (Variation graph toolkit improves read mapping by representing genetic variation in the reference. Nat Biotechnol 2018;36:875-9)] is a popular aligner of short reads, GraphAligner [Rautiainen and Marschall (GraphAligner: rapid and versatile sequence-to-graph alignment. Genome Biol 2020;21:253-28)] is the state-of-the-art aligner of erroneous long reads. GraphAligner works by finding candidate read occurrences based on individually extending the best seeds of the read in the variation graph. However, a more principled approach recognized in the community is to co-linearly chain multiple seeds. We present a new algorithm to co-linearly chain a set of seeds in a string labeled acyclic graph, together with the first efficient implementation of such a co-linear chaining algorithm into a new aligner of erroneous long reads to acyclic variation graphs, GraphChainer. We run experiments aligning real and simulated PacBio CLR reads with average error rates 15% and 5%. Compared to GraphAligner, GraphChainer aligns 12-17% more reads, and 21-28% more total read length, on real PacBio CLR reads from human chromosomes 1, 22, and the whole human pangenome. On both simulated and real data, GraphChainer aligns between 95% and 99% of all reads, and of total read length. We also show that minigraph [Li et al. (The design and construction of reference pangenome graphs with minigraph. Genome Biol 2020;21:265-19.)] and minichain [Chandra and Jain (Sequence to graph alignment using gap-sensitive co-linear chaining. In: Proceedings of the 27th Annual International Conference on Research in Computational Molecular Biology (RECOMB 2023). Springer, 2023, 58-73.)] obtain an accuracy of <60% on this setting. GraphChainer is freely available at https://github.com/algbio/GraphChainer. The datasets and evaluation pipeline can be reached from the previous address.

Dynamic structure of motor cortical neuron coactivity carries behaviorally relevant information.

Skillful, voluntary movements are underpinned by computations performed by networks of interconnected neurons in the primary motor cortex (M1). Computations are reflected by patterns of coactivity between neurons. Using pairwise spike time statistics, coactivity can be summarized as a functional network (FN). Here, we show that the structure of FNs constructed from an instructed-delay reach task in nonhuman primates is behaviorally specific: Low-dimensional embedding and graph alignment scores show that FNs constructed from closer target reach directions are also closer in network space. Using short intervals across a trial, we constructed temporal FNs and found that temporal FNs traverse a low-dimensional subspace in a reach-specific trajectory. Alignment scores show that FNs become separable and correspondingly decodable shortly after the Instruction cue. Finally, we observe that reciprocal connections in FNs transiently decrease following the Instruction cue, consistent with the hypothesis that information external to the recorded population temporarily alters the structure of the network at this moment.

Joint Multimodal Entity-Relation Extraction Based on Edge-Enhanced Graph Alignment Network and Word-Pair Relation Tagging

Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This paper is the first to propose jointly performing MNER and MRE as a joint multimodal entity-relation extraction (JMERE) task . Besides, the current MNER and MRE models only consider aligning the visual objects with textual entities in visual and textual graphs but ignore the entity-entity relationships and object-object relationships. To address the above challenges, we propose an edge-enhanced graph alignment network and a word-pair relation tagging (EEGA) for the JMERE task. Specifically, we first design a word-pair relation tagging to exploit the bidirectional interaction between MNER and MRE and avoid error propagation. Then, we propose an edge-enhanced graph alignment network to enhance the JMERE task by aligning nodes and edges in the cross-graph. Compared with previous methods, the proposed method can leverage the edge information to auxiliary alignment between objects and entities and find the correlations between entity-entity relationships and object-object relationships. Experiments are conducted to show the effectiveness of our model.

Privacy-Preserved Evolutionary Graph Modeling via Gromov-Wasserstein Autoregression

Real-world graphs like social networks are often evolutionary over time, whose observations at different timestamps lead to graph sequences. Modeling such evolutionary graphs is important for many applications, but solving this problem often requires the correspondence between the graphs at different timestamps, which may leak private node information, e.g., the temporal behavior patterns of the nodes. We proposed a Gromov-Wasserstein Autoregressive (GWAR) model to capture the generative mechanisms of evolutionary graphs, which does not require the correspondence information and thus preserves the privacy of the graphs' nodes. This model consists of two autoregressions, predicting the number of nodes and the probabilities of nodes and edges, respectively. The model takes observed graphs as its input and predicts future graphs via solving a joint graph alignment and merging task. This task leads to a fused Gromov-Wasserstein (FGW) barycenter problem, in which we approximate the alignment of the graphs based on a novel inductive fused Gromov-Wasserstein (IFGW) distance. The IFGW distance is parameterized by neural networks and can be learned under mild assumptions, thus, we can infer the FGW barycenters without iterative optimization and predict future graphs efficiently. Experiments show that our GWAR achieves encouraging performance in modeling evolutionary graphs in privacy-preserving scenarios.

Heterogeneous Domain Adaptation for IoT Intrusion Detection: A Geometric Graph Alignment Approach

Data scarcity hinders the usability of data-dependent algorithms when tackling IoT intrusion detection (IID). To address this, we utilise the data rich network intrusion detection (NID) domain to facilitate more accurate intrusion detection for IID domains. In this paper, a Geometric Graph Alignment (GGA) approach is leveraged to mask the geometric heterogeneities between domains for better intrusion knowledge transfer. Specifically, each intrusion domain is formulated as a graph where vertices and edges represent intrusion categories and category-wise interrelationships, respectively. The overall shape is preserved via a confused discriminator incapable to identify adjacency matrices between different intrusion domain graphs. A rotation avoidance mechanism and a centre point matching mechanism is used to avoid graph misalignment due to rotation and symmetry, respectively. Besides, category-wise semantic knowledge is transferred to act as vertex-level alignment. To exploit the target data, a pseudo-label election mechanism that jointly considers network prediction, geometric property and neighbourhood information is used to produce fine-grained pseudo-label assignment. Upon aligning the intrusion graphs geometrically from different granularities, the transferred intrusion knowledge can boost IID performance. Comprehensive experiments on several intrusion datasets demonstrate state-of-the-art performance of the GGA approach and validate the usefulness of GGA constituting components.

GRASP: Scalable Graph Alignment by Spectral Corresponding Functions

What is the best way to match the nodes of two graphs? This graph alignment problem generalizes graph isomorphism and arises in applications from social network analysis to bioinformatics. Some solutions assume that auxiliary information on known matches or node or edge attributes is available, or utilize arbitrary graph features. Such methods fare poorly in the pure form of the problem, in which only graph structures are given. Other proposals translate the problem to one of aligning node embeddings, yet, by doing so, provide only a single-scale view of the graph. In this article, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs. We present GRASP, a method that first establishes a correspondence between functions derived from Laplacian matrix eigenvectors, which capture multiscale structural characteristics, and then exploits this correspondence to align nodes. We enhance the basic form of GRASP by altering two of its components, namely the embedding method and the assignment procedure it employs, leveraging its modular, hence adaptable design. Our experimental study, featuring noise levels higher than anything used in previous studies, shows that the enhanced form of GRASP outperforms scalable state-of-the-art methods for graph alignment across noise levels and graph types, and performs competitively with respect to the best non-scalable ones. We include in our study another modular graph alignment algorithm, CONE, which is also adaptable thanks to its modular nature, and show it can manage graphs with skewed power-law degree distributions.

Active Temporal Knowledge Graph Alignment

Entity alignment aims to identify equivalent entity pairs from different knowledge graphs (KGs). Recently, aligning temporal knowledge graphs (TKGs) that contain time information has aroused increasingly more interest, as the time dimension is widely used in real-life applications. The matching between TKGs requires seed entity pairs, which are lacking in practice. Hence, it is of great significance to study TKG alignment under scarce supervision. In this work, the authors formally formulate the problem of TKG alignment with limited labeled data and propose to solve it under the active learning framework. As the core of active learning is to devise query strategies to select the most informative instances to label, the authors propose to make full use of time information and put forward novel time-aware strategies to meet the requirement of weakly supervised temporal entity alignment. Extensive experimental results on multiple real-world datasets show that it is important to study TKG alignment with scarce supervision, and the proposed time-aware strategy is effective.

PanPA: generation and alignment of panproteome graphs.

Compared to eukaryotes, prokaryote genomes are more diverse through different mechanisms, including a higher mutation rate and horizontal gene transfer. Therefore, using a linear representative reference can cause a reference bias. Graph-based pangenome methods have been developed to tackle this problem. However, comparisons in DNA space are still challenging due to this high diversity. In contrast, amino acid sequences have higher similarity due to evolutionary constraints, whereby a single amino acid may be encoded by several synonymous codons. Coding regions cover the majority of the genome in prokaryotes. Thus, panproteomes present an attractive alternative leveraging the higher sequence similarity while not losing much of the genome in non-coding regions. We present PanPA, a method that takes a set of multiple sequence alignments of protein sequences, indexes them, and builds a graph for each multiple sequence alignment. In the querying step, it can align DNA or amino acid sequences back to these graphs. We first showcase that PanPA generates correct alignments on a panproteome from 1350 Escherichia coli. To demonstrate that panproteomes allow comparisons at longer phylogenetic distances, we compare DNA and protein alignments from 1073 Salmonella enterica assemblies against E.coli reference genome, pangenome, and panproteome using BWA, GraphAligner, and PanPA, respectively; with PanPA aligning around 22% more sequences. We also aligned a DNA short-reads whole genome sequencing (WGS) sample from S.enterica against the E.coli reference with BWA and the panproteome with PanPA, where PanPA was able to find alignment for 68% of the reads compared to 5% with BWA. PanPA is available at https://github.com/fawaz-dabbaghieh/PanPA.

HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval

Image-text retrieval (ITR) is a challenging task in the field of multimodal information processing due to the semantic gap between different modalities. In recent years, researchers have made great progress in exploring the accurate alignment between image and text. However, existing works mainly focus on the fine-grained alignment between image regions and sentence fragments, which ignores the guiding significance of context background information. Actually, integrating the local fine-grained information and global context background information can provide more semantic clues for retrieval. In this paper, we propose a novel Hierarchical Graph Alignment Network (HGAN) for image-text retrieval. First, to capture the comprehensive multimodal features, we construct the feature graphs for the image and text modality respectively. Then, a multi-granularity shared space is established with a designed Multi-granularity Feature Aggregation and Rearrangement (MFAR) module, which enhances the semantic corresponding relations between the local and global information, and obtains more accurate feature representations for the image and text modalities. Finally, the ultimate image and text features are further refined through three-level similarity functions to achieve the hierarchical alignment. To justify the proposed model, we perform extensive experiments on MS-COCO and Flickr30 K datasets. Experimental results show that the proposed HGAN outperforms the state-of-the-art methods on both datasets, which demonstrates the effectiveness and superiority of our model.

A Novel Spatial-Temporal Multi-Scale Alignment Graph Neural Network Security Model for Vehicles Prediction

Traffic flow forecasting is indispensable in today’s society and regarded as a key problem for Intelligent Transportation Systems (ITS), as emergency delays in vehicles can cause serious traffic security accidents. However, the complex dynamic spatial-temporal dependency and correlation between different locations on the road make it a challenging task for security in transportation. To date, most existing forecasting frames make use of graph convolution to model the dynamic spatial-temporal correlation of vehicle transportation data, ignoring semantic similarity between nodes and thus, resulting in accuracy degradation. In addition, traffic data does not strictly follow periodicity and hard to be captured. To solve the aforementioned challenging issues, we propose in this article CRFAST-GCN, a multi-branch spatial-temporal attention graph convolution network. First, we capture the multi-scale (e.g., hour, day, and week) long- short-term dependencies through three identical branches, then introduce conditional random field (CRF) enhanced graph convolution network to capture the semantic similarity globally, so then we exploit the attention mechanism to captures the periodicity. For model evaluation using two real-world datasets, performance analysis shows that the proposed CRFAST-GCN successfully handles the complex spatial-temporal dynamics effectively and achieves improvement over the baselines at 50% (maximum), outperforming other advanced existing methods.

Synthesizing code quality rules from examples

Static Analysis tools have rules for several code quality issues and these rules are created by experts manually. In this paper, we address the problem of automatic synthesis of code quality rules from examples. We formulate the rule synthesis problem as synthesizing first order logic formulas over graph representations of code. We present a new synthesis algorithm RhoSynth that is based on Integer Linear Programming-based graph alignment for identifying code elements of interest to the rule. We bootstrap RhoSynth by leveraging code changes made by developers as the source of positive and negative examples. We also address rule refinement in which the rules are incrementally improved with additional user-provided examples. We validate RhoSynth by synthesizing more than 30 Java code quality rules. These rules have been deployed as part of Amazon CodeGuru Reviewer and their precision exceeds 75% based on developer feedback collected during live code-reviews within Amazon. Through comparisons with recent baselines, we show that current state-of-the-art program synthesis approaches are unable to synthesize most of these rules.

AIscEA: unsupervised integration of single-cell gene expression and chromatin accessibility via their biological consistency.

The integrative analysis of single-cell gene expression and chromatin accessibility measurements is essential for revealing gene regulation, but it is one of the key challenges in computational biology. Gene expression and chromatin accessibility are measurements from different modalities, and no common features can be directly used to guide integration. Current state-of-the-art methods lack practical solutions for finding heterogeneous clusters. However, previous methods might not generate reliable results when cluster heterogeneity exists. More importantly, current methods lack an effective way to select hyper-parameters under an unsupervised setting. Therefore, applying computational methods to integrate single-cell gene expression and chromatin accessibility measurements remains difficult. We introduce AIscEA-Alignment-based Integration of single-cell gene Expression and chromatin Accessibility-a computational method that integrates single-cell gene expression and chromatin accessibility measurements using their biological consistency. AIscEA first defines a ranked similarity score to quantify the biological consistency between cell clusters across measurements. AIscEA then uses the ranked similarity score and a novel permutation test to identify cluster alignment across measurements. AIscEA further utilizes graph alignment for the aligned cell clusters to align the cells across measurements. We compared AIscEA with the competing methods on several benchmark datasets and demonstrated that AIscEA is highly robust to the choice of hyper-parameters and can better handle the cluster heterogeneity problem. Furthermore, AIscEA significantly outperforms the state-of-the-art methods when integrating real-world SNARE-seq and scMultiome-seq datasets in terms of integration accuracy. AIscEA is available at https://figshare.com/articles/software/AIscEA_zip/21291135 on FigShare as well as {https://github.com/elhaam/AIscEA} onGitHub. Supplementary data are available at Bioinformatics online.

Knowledge Graph Alignment Network with Node-Level Strong Fusion

Entity alignment refers to the process of discovering entities representing the same object in different knowledge graphs (KG). Recently, some studies have learned other information about entities, but they are aspect-level simple information associations, and thus only rough entity representations can be obtained, and the advantage of multi-faceted information is lost. In this paper, a novel node-level information strong fusion framework (SFEA) is proposed, based on four aspects: structure, attribute, relation and names. The attribute information and name information are learned first, then structure information is learned based on these two aspects of information through graph convolutional network (GCN), the alignment signals from attribute and name are already carried at the beginning of the learning structure. In the process of continuous propagation of multi-hop neighborhoods, the effect of strong fusion of structure, attribute and name information is achieved and the more meticulous entity representations are obtained. Additionally, through the continuous interaction between sub-alignment tasks, the effect of entity alignment is enhanced. An iterative framework is designed to improve performance while reducing the impact on pre-aligned seed pairs. Furthermore, extensive experiments demonstrate that the model improves the accuracy of entity alignment and significantly outperforms 13 previous state-of-the-art methods.

Multi-Semantic Alignment Graph Convolutional Network

ABSTRACT 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.

Efficient alignment-based average delay time estimation in fluctuating delayed propagation

We propose an alignment-based average delay time estimation algorithm between two time series in the propagation of time-varying delay. Though the number of the minimum cost alignments may be exponential in the length of the time series, the proposed algorithm takes account of all such alignments, and as a post-alignment process, it runs in time linear in the number of the nodes in the minimum cost alignment graph , which is at most the length squared. The efficiency of our algorithm is confirmed through numerical experiments compared to the naive enumeration algorithm using recursive calls to traverse the graph. • Proposed average time delay estimation takes account of all the minimum cost alignments. • The proposed algorithm runs in time linear to the number of nodes in the minimum cost alignment graph. • The time complexity of the proposed algorithm does not depend on the number of the minimum cost alignments.