REVIEW 21 cited by
Deep Graph Contrastive Representation Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Graph representation learning nowadays becomes fundamental in analyzing graph-structured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by leveraging a contrastive objective at the node level. Specifically, we generate two graph views by corruption and learn node representations by maximizing the agreement of node representations in these two views. To provide diverse node contexts for the contrastive objective, we propose a hybrid scheme for generating graph views on both structure and attribute levels. Besides, we provide theoretical justification behind our motivation from two perspectives, mutual information and the classical triplet loss. We perform empirical experiments on both transductive and inductive learning tasks using a variety of real-world datasets. Experimental experiments demonstrate that despite its simplicity, our proposed method consistently outperforms existing state-of-the-art methods by large margins. Moreover, our unsupervised method even surpasses its supervised counterparts on transductive tasks, demonstrating its great potential in real-world applications.
Forward citations
Cited by 21 Pith papers
-
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
A federated pretraining-and-prompt-tuning framework that aligns image, text, and graph-topology information across privacy-separated clients claims consistent state-of-the-art results on 12 multimodal graph datasets.
-
Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias
ADPrompt adds per-node feature gating and layer-wise edge message calibration to frozen pre-trained GNNs, reducing attribute and structural bias while keeping node-classification accuracy competitive.
-
Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
Khan-GCL combines KAN encoders with coefficient-based critical feature identification to generate hard negatives and reports state-of-the-art graph classification results.
-
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
MABLE learns stable node and graph embeddings on heterogeneous geospatial graphs via masked autoencoding, bi-Lipschitz decoding, and fixed cosine alignment/uniformity losses without discriminators or hard negatives.
-
STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition
Skeleton-only interaction recognition that aligns skeleton and video features during training outperforms prior state-of-the-art on four benchmarks.
-
Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding
GPH^2 pre-trains one expert per graph on edge-dropped or meta-path views and fuses frozen experts with class-wise attention, outperforming type-specific graph pre-training baselines.
-
Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
S2-DiGCL combines personalized magnetic Laplacian perturbations with BFS/DFS path sampling to improve contrastive learning on directed graphs.
-
GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
GSTBench finds that masked feature reconstruction (GraphMAE) is the only one of five graph self-supervised pretraining objectives that consistently transfers across eight datasets, while contrastive methods often perf...
-
Dual-Center Graph Clustering with Neighbor Distribution
A dual-center graph clustering method that aligns nodes to both feature centers and neighbor-distribution centers outperforms prior methods in experiments.
-
Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
CMV-ND builds one feature view per exact hop distance and then runs existing clustering methods on those views, improving attribute-missing large-scale graph clustering in experiments.
-
Str-GCL: Structural Commonsense Driven Graph Contrastive Learning
Injecting hand-designed structural rules (low-neighbor-degree and local-global similarity) via representation alignment improves graph contrastive learning accuracy on six homophilic benchmarks.
-
Exploring Semantic Clustering and Similarity Search for Heterogeneous Traffic Scenario Graph
Self-supervised graph embeddings group variable-length traffic scenarios into semantically meaningful clusters on nuPlan, with modest quantitative accuracy and no manual labels.
-
CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks
CoATA jointly augments topology and attributes, enriching features by propagation and reconstructing edges with Personalized PageRank on a node-attribute bipartite graph, to improve node classification on six of seven...
-
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
A hardness-aware reweighted contrastive loss that uses labels and similarity to upweight hard positives and negatives reduces degree bias in graph node classification.
-
Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
Spotscape improves spatial-domain identification in spatial transcriptomics by learning augmentation-invariant global spot similarities and a slice-level similarity matching objective.
-
HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation
Adding a t-SNE-based hierarchical item clustering step to graph contrastive learning yields small accuracy gains on three benchmark recommendation datasets.
-
Enhancing Contrastive Link Prediction With Edge Balancing Augmentation
CoEBA, a contrastive link prediction model using a degree-balancing edge augmentation and neighbor-concentrated contrastive losses, is reported to outperform baselines on 8 datasets, supported by a theoretical bound a...
-
Graph-based Fake Account Detection: A Survey
A structured survey of graph-based fake account detection methods, organizing classical, traditional machine learning, and deep learning approaches and their datasets.
-
Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization
A benchmark of 7 GNNs and 30 losses on 3 graphs claims hybrid losses and GIN rank best on average, but a central summary table contradicts the paper's full results.
-
Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
A survey of graph prompting methods that categorizes them by the stage at which prompts are applied: data, representation, or task.
-
Enhancing Large Language Models with Reliable Knowledge Graphs
A thesis composed of four published papers proposes contrastive KG error detection, attribute-aware error-aware embedding, inductive graph completion, and KG prompting, but adds no new result beyond those papers.
Discussion (0). Sign in to comment.