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.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “node-orderless”

Segmented Graph-Bert for Graph Instance Modelingcs.LG

SEG-BERT improves graph instance learning by adapting GRAPH-BERT.

problem Graph instance representation learning challenges due to diverse sizes and node order.

method Adapted GRAPH-BERT with a segmented architecture to handle graph node orderlessness and diverse sizes.

result SEG-BERT outperforms comparison methods on six out of seven benchmark datasets.

Graph instance learning GRAPH-BERT Segmented GRAPH-BERT Node orderlessness Graph node size

2020-02-09abs ↗pdf ↗

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classificationcs.LG

IsoNN learns graph representations without node order constraints.

problem Lack of interpretability and erratic performance in graph classification due to node-orderless property.

method IsoNN uses graph matching with subgraph templates to learn isomorphic features and break node-order.

result IsoNN achieves superior performance on graph classification tasks compared to existing methods.

graph representation learning graph classification neural networks node-orderless isomorphic features

2019-07-22abs ↗pdf ↗