K
Kyungwoo Song
Researcher at KAIST
Publications - 29
Citations - 244
Kyungwoo Song is an academic researcher from KAIST. The author has contributed to research in topics: Deep learning & Inference. The author has an hindex of 6, co-authored 29 publications receiving 127 citations. Previous affiliations of Kyungwoo Song include Seoul National University.
Papers
More filters
Proceedings ArticleDOI
Augmented Variational Autoencoders for Collaborative Filtering with Auxiliary Information
TL;DR: These two augmentations are the first trial in the venue of the variational autoencoders, and they demonstrate their significant improvement on the performances in the applications of the collaborative filtering.
Posted Content
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder
TL;DR: This paper proposes Disentangled Causal Effect Variational Autoencoder (DCEVAE) to resolve this limitation by disentangling the exogenous uncertainty into two latent variables: either 1) independent to interventions or 2) correlated to interventions without causality.
Journal ArticleDOI
Hierarchical Context enabled Recurrent Neural Network for Recommendation
TL;DR: Wang et al. as mentioned in this paper proposed a hierarchical context-based gate structure to handle the long-term dependency and the interest drifts in the recommendation system, and they experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM.
Posted Content
Hierarchical Context enabled Recurrent Neural Network for Recommendation
TL;DR: This work suggests HCRNN with three hierarchical contexts of the global, the local, and the temporary interests, designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interest of each transition.
Posted Content
Sequential Recommendation with Relation-Aware Kernelized Self-Attention
TL;DR: This work merges the self-attention of the Transformer and the sequential recommendation by adding a probabilistic model of the recommendation task specifics, and produces a latent space model that answers the reasons for recommendation.