pith. sign in

arxiv: 1709.05584 · v3 · pith:PVFHEBSTnew · submitted 2017-09-17 · 💻 cs.SI · cs.LG

Representation Learning on Graphs: Methods and Applications

classification 💻 cs.SI cs.LG
keywords learningapproachesgraphgraphsapplicationsmachinemethodsembed
0
0 comments X
read the original abstract

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. Here we provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. We review methods to embed individual nodes as well as approaches to embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recent approaches, and we highlight a number of important applications and directions for future work.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Temporal Graph Networks for Deep Learning on Dynamic Graphs

    cs.LG 2020-06 unverdicted novelty 7.0

    Temporal Graph Networks combine memory modules and graph operators to learn on dynamic graphs as timed event sequences, outperforming prior methods on transductive and inductive tasks while unifying earlier models as ...

  2. Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0

    VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.

  3. Tracking Temporal Evolution of Graphs using Non-Timestamped Data

    cs.SI 2019-07 unverdicted novelty 6.0

    Presents YoutubeGraph-Dyn, a multi-modal dynamic graph dataset from YouTube interactions with intra-day snapshots, and benchmarks clustering for community migration plus time series and RNN methods for forecasting non...

  4. Image Classification with Hierarchical Multigraph Networks

    cs.CV 2019-07 unverdicted novelty 4.0

    Hierarchical multigraph GCNs applied to superpixels achieve competitive or superior accuracy to CNNs on standard image classification benchmarks.

  5. Network Embedding: on Compression and Learning

    cs.SI 2019-07 unverdicted novelty 4.0

    NECL uses neighborhood-similarity graph compression as a preprocessing step to accelerate random-walk network embedding algorithms without reducing their effectiveness on classification tasks.

  6. Deep Conversational Recommender in Travel

    cs.CL 2019-06 unverdicted novelty 3.0

    DCR augments seq2seq with latent topics for topic control, GCN for venue matching, and pointer networks for response generation, reporting superior performance over baselines on a multi-turn travel dialog dataset.