Graph相關(圖學習|圖神經網路|圖優化等)(12篇)
[ 1 ] Hybrid Graph Embedding Techniques in Estimated Time of Arrival Task
標題：估計到達時間任務中的混合圖嵌入技術
連結：https://arxiv.org/abs/2110.04228
作者：Vadim Porvatov,Natalia Semenova,Andrey Chertok
機構： Sberbank, Moscow , Russia, National University of Science and Technology “MISIS”, Moscow , Russia, Artificial Intelligence Research Institute (AIRI)
備註：Accepted in ICCNA 2021
摘要：最近，深度學習在計算估計到達時間（ETA）方面取得了令人滿意的結果，ETA被認為是預測從起點到給定路徑上某個位置的旅行時間。ETA在智慧計程車服務或汽車導航系統中起著至關重要的作用。通常的做法是使用嵌入向量來表示道路網路的元素，例如路段和十字路口。道路要素有其自身的屬性，如長度、人行橫道的存在、車道數等。然而，道路網路中的許多路段被過少的浮動車穿過，即使是在大型叫車平臺上，也會受到各種時間事件的影響。作為本研究的主要目的，我們探討了不同空間嵌入策略的泛化能力，並提出了一種兩階段的方法來處理這些問題。
摘要：Recently, deep learning has achieved promising results in the calculation of Estimated Time of Arrival (ETA), which is considered as predicting the travel time from the start point to a certain place along a given path. ETA plays an essential role in intelligent taxi services or automotive navigation systems. A common practice is to use embedding vectors to represent the elements of a road network, such as road segments and crossroads. Road elements have their own attributes like length, presence of crosswalks, lanes number, etc. However, many links in the road network are traversed by too few floating cars even in large ride-hailing platforms and affected by the wide range of temporal events. As the primary goal of the research, we explore the generalization ability of different spatial embedding strategies and propose a two-stage approach to deal with such problems.
[ 2 ] TopoDetect: Framework for Topological Features Detection in Graph Embeddings
標題：拓撲檢測：圖嵌入中的拓撲特徵檢測框架
連結：https://arxiv.org/abs/2110.04173
作者：Maroun Haddad,Mohamed Bouguessa
機構：Department of Computer Science, University of Quebec at Montreal, Montreal, Quebec, Canada
摘要：TopoDetect是一個Python包，它允許使用者調查是否在圖形表示模型的嵌入中保留了重要的拓撲特徵，例如節點的度、節點的三角形計數或節點的區域性聚類分數。此外，該框架還可以根據節點之間拓撲特徵的分佈來視覺化嵌入。此外，TopoDetect使我們能夠通過評估嵌入對下游學習任務（如聚類和分類）的效能來研究保留這些特徵的效果。
摘要：TopoDetect is a Python package that allows the user to investigate if important topological features, such as the Degree of the nodes, their Triangle Count, or their Local Clustering Score, are preserved in the embeddings of graph representation models. Additionally, the framework enables the visualization of the embeddings according to the distribution of the topological features among the nodes. Moreover, TopoDetect enables us to study the effect of the preservation of these features by evaluating the performance of the embeddings on downstream learning tasks such as clustering and classification.
[ 3 ] New Insights into Graph Convolutional Networks using Neural Tangent Kernels
標題：利用神經切核對圖卷積網路的新認識
連結：https://arxiv.org/abs/2110.04060
作者：Mahalakshmi Sabanayagam,Pascal Esser,Debarghya Ghoshdastidar
機構：Technical University of Munich
摘要：圖卷積網路（GCN）已成為學習網路結構化資料的有力工具。儘管在經驗上取得了成功，但GCN表現出某些沒有嚴格解釋的行為——例如，GCN的效能隨著網路深度的增加而顯著下降，而隨著使用跳過連線的深度的增加而略有改善。本文重點介紹了NTKs的半監督圖和切線學習。我們推匯出對應於無限寬GCN的NTK（有和沒有跳過連線）。隨後，我們使用匯出的NTK來確定，通過適當的歸一化，網路深度並不總是顯著降低GCN的效能——我們還通過大量模擬驗證了這一事實。此外，我們建議NTK作為GCN的有效“代理模型”，它不會因超引數調整而受到效能波動的影響，因為它是一個超引數自由確定性核心。通過使用替代NTK對GCN的不同跳過連線進行比較，證明了該想法的有效性。
摘要：Graph Convolutional Networks (GCNs) have emerged as powerful tools for learning on network structured data. Although empirically successful, GCNs exhibit certain behaviour that has no rigorous explanation -- for instance, the performance of GCNs significantly degrades with increasing network depth, whereas it improves marginally with depth using skip connections. This paper focuses on semi-supervised learning on graphs, and explains the above observations through the lens of Neural Tangent Kernels (NTKs). We derive NTKs corresponding to infinitely wide GCNs (with and without skip connections). Subsequently, we use the derived NTKs to identify that, with suitable normalisation, network depth does not always drastically reduce the performance of GCNs -- a fact that we also validate through extensive simulation. Furthermore, we propose NTK as an efficient `surrogate model' for GCNs that does not suffer from performance fluctuations due to hyper-parameter tuning since it is a hyper-parameter free deterministic kernel. The efficacy of this idea is demonstrated through a comparison of different skip connections for GCNs using the surrogate NTKs.
[ 4 ] Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks
標題：基於分層圖神經網路的全域性上下文增強型社交推薦
連結：https://arxiv.org/abs/2110.04039
作者：Huance Xu,Chao Huang,Yong Xu,Lianghao Xia,Hao Xing,Dawei Yin
機構：†South China University of Technology, §JD Finance America Corporation, ‡VIPS Research, ♮Baidu inc
備註：Published as a full paper at ICDM 2020
摘要：社交推薦旨在利用使用者之間的社交關係來提高推薦效能。隨著深度學習技術的復興，人們致力於開發各種基於神經網路的社會推薦系統，如注意機制和基於圖形的訊息傳遞框架。然而，有兩個重要的挑戰尚未得到很好的解決：（i）大多數現有的社會推薦模型未能充分探討多型別使用者專案互動行為以及潛在的跨關係相互依賴性。（ii）雖然學習到的社會狀態向量能夠建模成對的使用者依賴關係，但它在跨使用者捕獲全域性社會上下文方面的表示能力仍然有限。為了解決這些侷限性，我們提出了一種新的基於層次圖神經網路的社會推薦框架（SR-HGNN）。特別是，我們首先設計了一個關係感知的重構圖神經網路，將跨型別協作語義注入到推薦框架中。此外，我們還基於低層使用者嵌入和高層全域性表示之間的互資訊學習正規化，進一步將SR-HGNN擴充套件為一個社會關係編碼器，從而賦予SR-HGNN捕獲全域性社會上下文訊號的能力。三個公共基準上的實證結果表明，SR-HGNN顯著優於最先進的推薦方法。原始碼可從以下網址獲得：https://github.com/xhcdream/SR-HGNN.
摘要：Social recommendation which aims to leverage social connections among users to enhance the recommendation performance. With the revival of deep learning techniques, many efforts have been devoted to developing various neural network-based social recommender systems, such as attention mechanisms and graph-based message passing frameworks. However, two important challenges have not been well addressed yet: (i) Most of existing social recommendation models fail to fully explore the multi-type user-item interactive behavior as well as the underlying cross-relational inter-dependencies. (ii) While the learned social state vector is able to model pair-wise user dependencies, it still has limited representation capacity in capturing the global social context across users. To tackle these limitations, we propose a new Social Recommendation framework with Hierarchical Graph Neural Networks (SR-HGNN). In particular, we first design a relation-aware reconstructed graph neural network to inject the cross-type collaborative semantics into the recommendation framework. In addition, we further augment SR-HGNN with a social relation encoder based on the mutual information learning paradigm between low-level user embeddings and high-level global representation, which endows SR-HGNN with the capability of capturing the global social contextual signals. Empirical results on three public benchmarks demonstrate that SR-HGNN significantly outperforms state-of-the-art recommendation methods. Source codes are available at: https://github.com/xhcdream/SR-HGNN.
[ 5 ] Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
標題：基於時空圖擴散網路的交通流預測
連結：https://arxiv.org/abs/2110.04038
作者：Xiyue Zhang,Chao Huang,Yong Xu,Lianghao Xia,Peng Dai,Liefeng Bo,Junbo Zhang,Yu Zheng
機構：South China University of Technology, China, JD Finance America Corporation, USA, Communication and Computer Network Laboratory of Guangdong, China, Peng Cheng Laboratory, China
備註：Published as a paper at AAAI 2021
摘要：準確預測城市範圍內的交通流量在各種時空挖掘應用中發揮著關鍵作用，如智慧交通控制和公共風險評估。雖然之前的工作在學習交通時間動態和空間相關性方面做出了重大努力，但當前模型存在兩個關鍵限制。首先，現有的方法只考慮相鄰區域之間的空間相關性，而忽略了區域間的全域性相關性。此外，這些方法無法對複雜的交通流過渡規律進行編碼，這些規律在本質上具有時間依賴性和多解析度。為了應對這些挑戰，我們開發了一種新的交通預測框架-時空圖擴散網路（ST-GDN）。特別是，ST-GDN是一種層次結構的圖神經結構，它不僅學習區域性區域的地理依賴，而且從全域性角度學習空間語義。此外，還開發了一個多尺度注意網路，使ST-GDN具有捕獲多層次時間動態的能力。在幾個實際交通資料集上的實驗表明，ST-GDN優於不同型別的最先進基線。有關實現的原始碼，請訪問https://github.com/jill001/ST-GDN.
摘要：Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global inter-region dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework-Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on several real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines. Source codes of implementations are available at https://github.com/jill001/ST-GDN.
[ 6 ] Learning Sparse Graphs with a Core-periphery Structure
標題：學習具有核心-外圍結構的稀疏圖
連結：https://arxiv.org/abs/2110.04022
作者：Sravanthi Gurugubelli,Sundeep Prabhakar Chepuri
機構：Indian Institute of Science, Bangalore, India
摘要：在本文中，我們主要研究具有核心-外圍結構的稀疏圖的學習。我們提出了一個與核心-外圍結構網路相關的資料生成模型，通過潛在圖結構來建模節點屬性對圖中節點的核心分數的依賴性。利用所提出的模型，我們聯合推斷出一個稀疏圖和節點核心分數，該分數在網路的核心部分（分別是外圍部分）誘導密集（稀疏）連線。在各種真實資料上的數值實驗表明，該方法僅從節點屬性學習核心-外圍結構圖，同時學習與現有使用圖作為輸入並忽略常用節點屬性估計核心分數的工作一致的核心分數分配。
摘要：In this paper, we focus on learning sparse graphs with a core-periphery structure. We propose a generative model for data associated with core-periphery structured networks to model the dependence of node attributes on core scores of the nodes of a graph through a latent graph structure. Using the proposed model, we jointly infer a sparse graph and nodal core scores that induce dense (sparse) connections in core (respectively, peripheral) parts of the network. Numerical experiments on a variety of real-world data indicate that the proposed method learns a core-periphery structured graph from node attributes alone, while simultaneously learning core score assignments that agree well with existing works that estimate core scores using graph as input and ignoring commonly available node attributes.
[ 7 ] Graphs as Tools to Improve Deep Learning Methods
標題：圖作為改進深度學習方法的工具
連結：https://arxiv.org/abs/2110.03999
作者：Carlos Lassance,Myriam Bontonou,Mounia Hamidouche,Bastien Pasdeloup,Lucas Drumetz,Vincent Gripon
機構：arXiv:,.,v, [cs.LG] , Oct
備註：arXiv admin note: text overlap with arXiv:2012.07439
摘要：近年來，深度神經網路（DNN）的普及程度有了顯著提高。然而，儘管它們在許多機器學習挑戰中是最先進的，但它們仍然受到一些限制。例如，DNN需要大量的訓練資料，在某些實際應用中可能無法獲得這些資料。此外，當輸入中加入小擾動時，DNN容易出現誤分類錯誤。DNN也被視為黑匣子，因此他們的決定常常因缺乏可解釋性而受到批評。在本章中，我們回顧了最近的一些工作，這些工作旨在使用圖形作為工具來改進深度學習方法。這些圖是根據深度學習體系結構中的特定層定義的。它們的頂點表示不同的樣本，它們的邊取決於相應中間表示的相似性。然後，可以使用各種方法來利用這些圖形，其中許多方法建立在圖形訊號處理之上。本章由四個主要部分組成：DNN中間層視覺化工具、資料表示去噪、優化圖形目標函式和正則化學習過程。
摘要：In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require a lot of training data, which might not be available in some practical applications. In addition, when small perturbations are added to the inputs, DNNs are prone to misclassification errors. DNNs are also viewed as black-boxes and as such their decisions are often criticized for their lack of interpretability. In this chapter, we review recent works that aim at using graphs as tools to improve deep learning methods. These graphs are defined considering a specific layer in a deep learning architecture. Their vertices represent distinct samples, and their edges depend on the similarity of the corresponding intermediate representations. These graphs can then be leveraged using various methodologies, many of which built on top of graph signal processing. This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.
[ 8 ] Stable Prediction on Graphs with Agnostic Distribution Shift
標題：具有不可知分佈移位的圖的穩定預測
連結：https://arxiv.org/abs/2110.03865
作者：Shengyu Zhang,Kun Kuang,Jiezhong Qiu,Jin Yu,Zhou Zhao,Hongxia Yang,Zhongfei Zhang,Fei Wu
機構： College of Computer Science and Technology, Zhejiang University, China, Department of Computer Science and Technology, Tsinghua University, China, Alibaba Group, China
備註：11 pages, 6 figures
摘要：圖形是一種靈活有效的工具，在實踐中可以表示複雜的結構，圖形神經網路（GNN）已被證明在具有隨機分離的訓練和測試資料的各種圖形任務中是有效的。然而，在實際應用中，訓練圖的分佈可能與測試圖的分佈不同（例如，使用者在使用者專案訓練圖上的互動以及他們對專案的實際偏好，即測試環境，已知在推薦系統中存在不一致）。此外，當訓練GNN時，測試資料的分佈總是不可知的。因此，我們面臨著圖形學習的訓練和測試之間的不可知分佈轉移，這將導致傳統GNN在不同測試環境中的不穩定推理。為了解決這個問題，我們提出了一個新的GNNs穩定預測框架，它允許在圖上進行區域性和全域性穩定的學習和預測。特別是，由於每個節點在GNN中部分由其鄰居表示，因此我們建議通過重新加權資訊傳播/聚合過程來捕獲每個節點的穩定屬性（區域性穩定）。對於全域性穩定性，我們提出了一個穩定的正則化器，它可以減少異構環境下的訓練損失，從而使GNN具有良好的通用性。我們在幾個圖形基準和一個嘈雜的工業推薦資料集上進行了廣泛的實驗，該資料集是在產品促銷節期間連續5天收集的。結果表明，該方法在具有不可知分佈移位（包括節點標籤和屬性引起的移位）的圖的穩定預測方面優於各種SOTA GNN。
摘要：Graph is a flexible and effective tool to represent complex structures in practice and graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data. In real applications, however, the distribution of training graph might be different from that of the test one (e.g., users' interactions on the user-item training graph and their actual preference on items, i.e., testing environment, are known to have inconsistencies in recommender systems). Moreover, the distribution of test data is always agnostic when GNNs are trained. Hence, we are facing the agnostic distribution shift between training and testing on graph learning, which would lead to unstable inference of traditional GNNs across different test environments. To address this problem, we propose a novel stable prediction framework for GNNs, which permits both locally and globally stable learning and prediction on graphs. In particular, since each node is partially represented by its neighbors in GNNs, we propose to capture the stable properties for each node (locally stable) by re-weighting the information propagation/aggregation processes. For global stability, we propose a stable regularizer that reduces the training losses on heterogeneous environments and thus warping the GNNs to generalize well. We conduct extensive experiments on several graph benchmarks and a noisy industrial recommendation dataset that is collected from 5 consecutive days during a product promotion festival. The results demonstrate that our method outperforms various SOTA GNNs for stable prediction on graphs with agnostic distribution shift, including shift caused by node labels and attributes.
[ 9 ] CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
標題：CCGG：一種用於類條件圖生成的深度自迴歸模型
連結：https://arxiv.org/abs/2110.03800
作者：Matin Yousefabadi,Yassaman Ommi,Faezeh Faez,Amirmojtaba Sabour,Mahdieh Soleymani Baghshah,Hamid R. Rabiee
機構： Department of Computer Engineering, Sharif university of Technology, Tehran, Iran, Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran
摘要：圖形資料結構是研究連通實體的基礎。隨著將資料表示為圖形的應用程式數量的增加，圖形生成問題最近已成為許多訊號處理領域的一個熱門話題。然而，儘管條件圖生成具有重要意義，但在以前的研究中，建立具有所需特徵的圖的條件圖生成相對較少。本文通過引入類條件圖生成器（CCGG），解決了以類標籤作為生成約束的類條件圖生成問題。我們通過新增類別資訊作為圖形生成器模型的額外輸入，並在其總損失中包含分類損失以及梯度傳遞技巧，構建了CCGG。我們的實驗表明，CCGG在各種資料集上都優於現有的條件圖生成方法。它還能夠根據基於分佈的評估指標來維護生成的圖的質量。
摘要：Graph data structures are fundamental for studying connected entities. With an increase in the number of applications where data is represented as graphs, the problem of graph generation has recently become a hot topic in many signal processing areas. However, despite its significance, conditional graph generation that creates graphs with desired features is relatively less explored in previous studies. This paper addresses the problem of class-conditional graph generation that uses class labels as generation constraints by introducing the Class Conditioned Graph Generator (CCGG). We built CCGG by adding the class information as an additional input to a graph generator model and including a classification loss in its total loss along with a gradient passing trick. Our experiments show that CCGG outperforms existing conditional graph generation methods on various datasets. It also manages to maintain the quality of the generated graphs in terms of distribution-based evaluation metrics.
[ 10 ] Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
標題：Knowledge Shees：一種知識圖嵌入的Sheaf理論框架
連結：https://arxiv.org/abs/2110.03789
作者：Thomas Gebhart,Jakob Hansen,Paul Schrater
機構：Department of Computer Science, University of Minnesota, Department of Mathematics, The Ohio State University
摘要：知識圖嵌入涉及到學習實體（圖的頂點）和關係（圖的邊）的表示法，這樣得到的表示法對知識圖表示的已知事實資訊進行編碼，這些資訊在內部是一致的，可以用於新關係的推斷。我們證明了知識圖嵌入自然地用拓撲和範疇語言\textit{cellular Treans}表示：學習知識圖嵌入對應於在圖上學習\textit{knowledge sheaf}，受一定約束。除了為知識圖嵌入模型的推理提供一個通用框架外，這一層理論觀點還承認了對嵌入的一大類先驗約束的表達，並提供了新的推理能力。我們利用最近發展起來的Laplacian層譜理論來理解嵌入的區域性和全域性一致性，並通過對Laplacian層的調和延拓來開發複合關係推理的新方法。然後，我們實施這些想法，以突出這種新視角所激發的擴充套件的好處。
摘要：Knowledge graph embedding involves learning representations of entities -- the vertices of the graph -- and relations -- the edges of the graph -- such that the resulting representations encode the known factual information represented by the knowledge graph are internally consistent and can be used in the inference of new relations. We show that knowledge graph embedding is naturally expressed in the topological and categorical language of \textit{cellular sheaves}: learning a knowledge graph embedding corresponds to learning a \textit{knowledge sheaf} over the graph, subject to certain constraints. In addition to providing a generalized framework for reasoning about knowledge graph embedding models, this sheaf-theoretic perspective admits the expression of a broad class of prior constraints on embeddings and offers novel inferential capabilities. We leverage the recently developed spectral theory of sheaf Laplacians to understand the local and global consistency of embeddings and develop new methods for reasoning over composite relations through harmonic extension with respect to the sheaf Laplacian. We then implement these ideas to highlight the benefits of the extensions inspired by this new perspective.
[ 11 ] Label Propagation across Graphs: Node Classification using Graph Neural Tangent Kernels
標題：跨圖的標籤傳播：基於圖神經切核的節點分類
連結：https://arxiv.org/abs/2110.03763
作者：Artun Bayer,Arindam Chowdhury,Santiago Segarra
機構：Electrical and Computer Engineering, Rice University, USA
備註：Under review at IEEE ICASSP 2022
摘要：近幾年來，圖形神經網路（GNNs）在節點分類任務上取得了優異的效能。通常情況下，這是在一個半監督學習設定中構建的，其中整個圖形（包括要標記的目標節點）可用於訓練。在一定程度上受可伸縮性的驅動，最近的工作集中在歸納的情況下，其中只有圖形的標記部分可用於訓練。在這種情況下，我們當前的工作考慮了一個具有挑戰性的歸納設定，其中一組標記的圖可用於訓練，而未標記的目標圖是完全獨立的，即標記的和未標記的節點之間沒有連線。在假設測試圖和訓練圖來自相似分佈的隱式假設下，我們的目標是開發一個可推廣到未觀測連通結構的標記函式。為此，我們使用一個對應於無限寬GNN的圖神經切線核（GNTK）來根據拓撲和節點特徵查詢不同圖中節點之間的對應關係。我們通過剩餘連線來增強GNTK的能力，並以經驗的方式說明其在標準基準上的效能提升。
摘要：Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph, including the target nodes to be labeled, is available for training. Driven in part by scalability, recent works have focused on the inductive case where only the labeled portion of a graph is available for training. In this context, our current work considers a challenging inductive setting where a set of labeled graphs are available for training while the unlabeled target graph is completely separate, i.e., there are no connections between labeled and unlabeled nodes. Under the implicit assumption that the testing and training graphs come from similar distributions, our goal is to develop a labeling function that generalizes to unobserved connectivity structures. To that end, we employ a graph neural tangent kernel (GNTK) that corresponds to infinitely wide GNNs to find correspondences between nodes in different graphs based on both the topology and the node features. We augment the capabilities of the GNTK with residual connections and empirically illustrate its performance gains on standard benchmarks.
[ 12 ] StairwayGraphNet for Inter- and Intra-modality Multi-resolution Brain Graph Alignment and Synthesis
標題：用於通道間和通道內多解析度腦圖對齊和合成的階梯圖形網路(STRIDWAY GraphNet)
連結：https://arxiv.org/abs/2110.04279
作者：Islem Mhiri,Mohamed Ali Mahjoub,Islem Rekik
機構：ID ,⋆, BASIRA Lab, Istanbul Technical University
備註：arXiv admin note: substantial text overlap with arXiv:2107.06281
摘要：綜合多模態醫學資料提供補充知識，幫助醫生做出準確的臨床決策。儘管前景看好，但現有的多模態腦圖合成框架存在一些侷限性。首先，它們主要只處理一個問題（模態內或模態間），限制了它們的通用性，即同時合成模態間和模態內。第二，雖然很少有技術能夠在單一模式（即內部模式）內處理超解析度低解析度腦圖，但模式間圖的超解析度仍有待探索，儘管這可以避免昂貴的資料收集和處理。更重要的是，目標域和源域可能具有不同的分佈，這會導致它們之間的域斷開。為了填補這些空白，我們提出了一個多解析度GraphNet（SG-Net）框架，以基於給定的模態和域間和域內的超解析度腦圖聯合推斷目標圖模態。我們的SG網路基於三個主要貢獻：（i）基於新的圖形生成對抗網路，在內部（如形態功能）和內部（如功能）域從源圖形預測目標圖形，（ii）生成高解析度腦圖而無需訴諸耗時且昂貴的MRI處理步驟，以及（iii）使用模態間對準器來放鬆損失函式以優化，強制源分佈以匹配地面真值圖。此外，我們還設計了一個新的保留基本真值的損失函式來指導兩個生成器更準確地學習基本真值腦圖的拓撲結構。我們使用多解析度階梯從源圖預測目標腦圖的綜合實驗表明，與其變體和最先進的方法相比，我們的方法具有更好的效能。
摘要：Synthesizing multimodality medical data provides complementary knowledge and helps doctors make precise clinical decisions. Although promising, existing multimodal brain graph synthesis frameworks have several limitations. First, they mainly tackle only one problem (intra- or inter-modality), limiting their generalizability to synthesizing inter- and intra-modality simultaneously. Second, while few techniques work on super-resolving low-resolution brain graphs within a single modality (i.e., intra), inter-modality graph super-resolution remains unexplored though this would avoid the need for costly data collection and processing. More importantly, both target and source domains might have different distributions, which causes a domain fracture between them. To fill these gaps, we propose a multi-resolution StairwayGraphNet (SG-Net) framework to jointly infer a target graph modality based on a given modality and super-resolve brain graphs in both inter and intra domains. Our SG-Net is grounded in three main contributions: (i) predicting a target graph from a source one based on a novel graph generative adversarial network in both inter (e.g., morphological-functional) and intra (e.g., functional-functional) domains, (ii) generating high-resolution brain graphs without resorting to the time consuming and expensive MRI processing steps, and (iii) enforcing the source distribution to match that of the ground truth graphs using an inter-modality aligner to relax the loss function to optimize. Moreover, we design a new Ground Truth-Preserving loss function to guide both generators in learning the topological structure of ground truth brain graphs more accurately. Our comprehensive experiments on predicting target brain graphs from source graphs using a multi-resolution stairway showed the outperformance of our method in comparison with its variants and state-of-the-art method.