On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “meta-graph”

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networkscs.SI

MEGA and MEGA++ embed meta-paths and meta-graphs for better network similarity.

problem Ignoring meta-paths in meta-graph-based relevance computing.

method MEGA++ uses tensor decomposition and coupled tensor-matrix decomposition for joint node embedding.

result MEGA and MEGA++ outperform state-of-the-art approaches in similarity search.

meta-graph meta-paths tensor decomposition coupled decomposition heterogeneous networks

2018-09-11abs ↗pdf ↗

Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolutioncs.LG

CoMGNN models heterogeneous graphs with evolving nodes and edges.

problem Modeling complex, evolving graphs with diverse information.

method Meta graph attention on co-evolving heterogeneous graphs.

result Significant improvement over state-of-the-art methods.

graph neural networks heterogeneous graphs node-edge co-evolution meta graph attention spatiotemporal patterns

2020-10-09abs ↗pdf ↗

Meta-Graph: Few Shot Link Prediction via Meta Learningcs.LG

Meta-Graph learns to predict missing edges quickly from few samples.

problem Few-shot link prediction on graphs, especially when samples are sparse.

method Meta-learning framework that uses higher-order gradients and learned graph signatures.

result Meta-Graph can quickly adapt to new graphs using only a small sample of true edges.

link prediction few shot learning meta learning graph neural networks gradient-based

2019-12-20abs ↗pdf ↗

HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embeddingcs.LG

A new method for embedding heterogeneous networks using spacey random walks.

problem Stationarity issues in meta-path guided random walks for HIN embedding.

method Heterogeneous personalized spacey random walk.

result Substantial improvement over existing network embedding algorithms.

Heterogeneous Information Networks Random Walks Stationarity Meta-Paths Embedding

2019-09-07abs ↗pdf ↗

Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networkscs.LG

Proposes a new method to optimize graph neural network architectures on heterogeneous information networks.

problem Weaknesses in instability and inflexibility of existing graph neural architecture search methods.

method Partial Message Meta Multigraph search (PMMM) using a differentiable framework to search for a meaningful meta multigraph.

result Significantly more stable and effective than state-of-the-art heterogeneous GNNs.

graph neural networks heterogeneous information networks meta multigraph search differentiable architecture message propagation

2022-11-27abs ↗pdf ↗