Popularity bias is a widespread problem in the field of recommender syst...
Graph-based models have become increasingly important in various domains...
Generating graphs from a target distribution is a significant challenge
...
We question the current evaluation practice on diffusion-based purificat...
We tackle the problem of feature unlearning from a pretrained image
gene...
Learning dynamical systems is a promising avenue for scientific discover...
We present our solution for the EvalRS DataChallenge. The EvalRS
DataCha...
Designing a neural network architecture for molecular representation is
...
Encrypted control has been introduced to protect controller data by
encr...
We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose l...
While a growing body of literature has been studying new Graph Neural
Ne...
We consider the problem of machine unlearning to erase a target dataset,...
Deep learning-based symbol detector gains increasing attention due to th...
We present a rotated hyperbolic wrapped normal distribution (RoWN), a si...
Crowdsourcing systems enable us to collect noisy labels from crowd worke...
We study how to evaluate the quantitative information content of a regio...
Cross-entropy loss with softmax output is a standard choice to train neu...
Graph neural networks (GNNs) have been extensively studied for predictio...
With rise of interventional cardiology, Catheter Ablation Therapy (CAT) ...
We present word2word, a publicly available dataset and an open-source Py...
Mutual information is widely applied to learn latent representations of
...
Despite great popularity of applying softmax to map the non-normalised
o...
Online trolling has raised serious concerns about manipulating public op...
Prediction suffix trees (PST) provide an effective tool for sequence
mod...
We present a neural sequence model designed specifically for symbolic mu...
Much of scientific progress stems from previously published findings, bu...
Sequence modeling with neural networks has lead to powerful models of
sy...
Knowledge graph construction consists of two tasks: extracting informati...
The counting grid is a grid of microtopics, sparse word/feature
distribu...
In latent Dirichlet allocation (LDA), topics are multinomial distributio...