Recognition: unknown
Deep Graph Infomax
read the original abstract
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics
RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.
-
Graph self-supervised learning based on frequency corruption
FC-GSSL improves graph SSL by generating high-frequency biased corrupted graphs via low-frequency contribution-based corruption, reconstructing low-frequency features in an autoencoder, and aligning multi-view represe...
-
Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation
A persona-driven SBRS framework learns unsupervised user personas from an LLM-initialized heterogeneous KG and incorporates them into data-driven sequential recommenders, reporting consistent gains over session-histor...
-
Disentangled Dual-Branch Graph Learning for Conversational Emotion Recognition
A dual-branch graph model with modality disentanglement and speaker-aware hypergraphs outperforms baselines on IEMOCAP and MELD for multimodal conversational emotion recognition.
-
Intent Propagation Contrastive Collaborative Filtering
IPCCF improves collaborative filtering by propagating intents across graph structures with contrastive alignment to provide direct supervision and reduce biases in disentanglement.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.