187 citations · 575 across the 29 of their papers we have counts for
6 papers · 1 filter
TabDDPM: Modelling Tabular Data with Diffusion Models
Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev +1
Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities. Being the most prevalent in the comp…
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
Oleg Platonov, Denis Kuznedelev, Artem Babenko +1
Homophily is a graph property describing the tendency of edges to connect similar nodes; the opposite is called heterophily. It is often believed that heterophilous graphs are chal…
Revisiting Pretraining Objectives for Tabular Deep Learning
Ivan Rubachev, Artem Alekberov, Yury Gorishniy +1
Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from…
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
Harsha Vardhan Simhadri, George Williams, Martin Aumüller +9
Despite the broad range of algorithms for Approximate Nearest Neighbor Search, most empirical evaluations of algorithms have focused on smaller datasets, typically of 1 million poi…
When, Why, and Which Pretrained GANs Are Useful?
Timofey Grigoryev, Andrey Voynov, Artem Babenko
The literature has proposed several methods to finetune pretrained GANs on new datasets, which typically results in higher performance compared to training from scratch, especially…
On Embeddings for Numerical Features in Tabular Deep Learning
Yury Gorishniy, Ivan Rubachev, Artem Babenko
Recently, Transformer-like deep architectures have shown strong performance on tabular data problems. Unlike traditional models, e.g., MLP, these architectures map scalar values of…