Query-driven Active Surveying for Collective Classification

By Galileo Namata, Ben London, Lise Getoor, Bert Huang. 2012

616 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Predict then Propagate: Graph Neural Networks meet Personalized PageRank (2018, background): “, 2000; Bojchevski & Günnemann, 2018) and PUBMED (Namata et al., 2012) are citation graphs, where each node represents a paper and the edges represent citations between them.”
Pitfalls of Graph Neural Network Evaluation (2018, methodology): “If we, however, consider a different random split with the same train/validation/test set sizes the ranking of models is completely different, with GCN being ﬁrst on CORA and CiteSeer, and MoNet winning on PubMed.”
Geom-GCN: Geometric Graph Convolutional Networks (2020, background): “Cora, Citeseer, and Pubmed are standard citation network benchmark datasets (Sen et al., 2008; Namata et al., 2012).”
Hyperbolic Graph Convolutional Neural Networks (2019, background): “C ORA [36] and P UB M ED [27] are standard benchmarks describing citation networks where nodes represent scientiﬁc papers, edges are citations between them, and node labels are academic (sub)areas.”
Understanding over-squashing and bottlenecks on graphs via curvature (2021, methodology): “Cora (McCallum et al., 2000), Citeseer (Sen et al., 2008) and Pubmed (Namata et al., 2012) are medium homophilic datasets based on citation networks.”
On the Equivalence between Positional Node Embeddings and Structural Graph Representations (2019, unknown): “(2017a), namely Cora, Citeseer, Pubmed (Namata et al., 2012; Sen et al., 2008) and PPI (Zitnik & Leskovec, 2017).”
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks (2021, methodology): “We evaluate the performance of our GGCN model and existing GNNs in node classification on various real-world datasets (Tang et al., 2009; Rozemberczki et al., 2019; Sen et al., 2008; Namata et al., 2012; Bojchevski & Günnemann, 2018; Shchur et al., 2018).”
Graph Neural Networks with Heterophily (2020, background): “…under implicit homophily assumptions suffer from poor performance in heterophily settings, which can be problematic for applications like fraudster detection (Pandit et al. 2007; Dou et al. 2020) or analysis of protein structures (Fout et al. 2017), where heterophilous connections are common.”
HGNN+: General Hypergraph Neural Networks (2022, background): “Graph Structure 6.2.1 Datasets Five public benchmarks are selected in this experiment, which belong to two categories, i.e., publication citation network (Cora [25], Citeseer and Pubmed [26]) and social media network (Github Web ML and Facebook [27]).”
A Comprehensive Survey on Community Detection With Deep Learning (2021, background): “Community detection in citation networks [25], [26] determines the importance and interconnectedness of research topics and identiﬁes research trends.”
Exploiting Edge Features in Graph Neural Networks. (2018, methodology): “Since our EGNN models require the edge directions to construct edge features, we use the original version from [23] and [20].”
GRAND: Graph Neural Diffusion (2021, methodology): “Datasets We report results for the most widely used citation networks Cora (McCallum et al., 2000), Citeseer (Sen et al., 2008), Pubmed (Namata et al., 2012).”
A critical look at the evaluation of GNNs under heterophily: are we really making progress? (2023, background): “The most popular of them are three citation networks: cora , citeseer , and pubmed (Giles et al., 1998; McCallum et al., 2000; Namata et al., 2012; Sen et al., 2008; Yang et al., 2016).”
Multi-scale Attributed Node Embedding (2019, methodology): “We use standard (well-established) node classification webgraph benchmark datasets (Cora, Citeseer [34], Pubmed [35]) together with publicly available social network benchmarks—LastFM Asia, Deezer Europe [8]).”
Subgraph Federated Learning with Missing Neighbor Generation (2021, background): “, 2008), PubMed (Namata et al., 2012), and MSAcademic (Shchur et al.”
A Gentle Introduction to Deep Learning for Graphs (2019, methodology): “In node classification, three major datasets in literature are usually employed to assess the performances of DGNs, namely Cora, Citeseer [107] and PubMed [93], for which a rigorous evaluation is presented in [108].”
Diffusion Improves Graph Learning (2019, methodology): “We evaluate GDC on six datasets: The citation graphs CITESEER [66], CORA [48], and PUBMED [53], the co-author graph COAUTHOR CS [67], and the co-purchase graphs AMAZON COMPUTERS and AMAZON PHOTO [47, 67].”
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks (2021, methodology): “[29] Galileo Namata, Ben London, Lise Getoor, Bert Huang, and UMD EDU.”