Research
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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Jun 202119922001200920172026
1 result for “Ego-Embeddings”
How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscs.LG

Heterophily affects GNN robustness; separating ego- and neighbor-embeddings improves defense.

problem The robustness of GNNs to adversarial attacks.
method Formalized relation between heterophily and GNN robustness; empirical analysis; design principles for improved robustness.
result Separating ego- and neighbor-embeddings increases GNN robustness.
Graph Neural NetworksHeterophilyAdversarial AttacksRobustnessEgo-Embeddings
2021-06-14abs ↗pdf ↗