Picture for Pavel Kordík

Pavel Kordík

beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

Add code
Sep 16, 2024
Viaarxiv icon

Bridging Offline-Online Evaluation with a Time-dependent and Popularity Bias-free Offline Metric for Recommenders

Add code
Aug 14, 2023
Viaarxiv icon

Learning to Optimize with Dynamic Mode Decomposition

Add code
Nov 29, 2022
Viaarxiv icon

SimpleTron: Eliminating Softmax from Attention Computation

Add code
Dec 02, 2021
Figure 1 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 2 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 3 for SimpleTron: Eliminating Softmax from Attention Computation
Figure 4 for SimpleTron: Eliminating Softmax from Attention Computation
Viaarxiv icon

Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks

Add code
Sep 20, 2021
Figure 1 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 2 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 3 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Figure 4 for Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
Viaarxiv icon

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

Add code
Feb 11, 2021
Figure 1 for Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Figure 2 for Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Figure 3 for Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Figure 4 for Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Viaarxiv icon

Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)

Add code
Feb 10, 2021
Figure 1 for Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)
Figure 2 for Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)
Figure 3 for Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)
Figure 4 for Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)
Viaarxiv icon