Benjamin Rozonoyer

[Benjamin Rozonoyer @brozonoyer]

Excited to share that our paper *Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders*, is now available on arXiv!

https://t.co/KVINXIsMO5

[Benjamin Rozonoyer @brozonoyer]

Paper link 📎: https://t.co/jw9ftFjkGV

[Benjamin Rozonoyer @brozonoyer]

Excited to present our NeurIPS paper "Learning Representations for Hierarchies with Minimal Support" at the morning poster session on December 12! Stop by at poster #3500 in the East Building!

[Benjamin Rozonoyer @brozonoyer]

We see robust performance and fast convergence on synthetic hierarchies and the Medical Subject Headings taxonomy, with up to a ⚡ 99% reduction ⚡ in the size of the training example set.

[Benjamin Rozonoyer @brozonoyer]

🚀 We show that we can train node embedding models with greater efficiency using just this reduced set of examples, provided that our model has an appropriate inductive bias (in our case, transitivity bias).

[Benjamin Rozonoyer @brozonoyer]

💡 Applying this insight to hierarchies (transitively-closed directed acyclic graphs), we present an algorithm to compute the provably minimal set of edges to logically identify a graph among all hierarchies.

[Benjamin Rozonoyer @brozonoyer]

If we know that the graph has a certain structural property, then only a small subset of positive and negative edges might be required to uniquely identify that graph among all other graphs with that property.

[Benjamin Rozonoyer @brozonoyer]

When learning geometric representations of graphs, the model needs to see both “positive” edges from the graph, as well as “negative” edges from the edge complement.