Share This Author
YouTube-8M: A Large-Scale Video Classification Benchmark
- Sami Abu-El-Haija, Nisarg Kothari, Sudheendra Vijayanarasimhan
- Computer ScienceArXiv
- 27 September 2016
YouTube-8M is introduced, the largest multi-label video classification dataset, composed of ~8 million videos (500K hours of video), annotated with a vocabulary of 4800 visual entities, and various (modest) classification models are trained on the dataset.
Local Low-Rank Matrix Approximation
- Joonseok Lee, Seungyeon Kim, G. Lebanon, Y. Singer
- Computer ScienceInternational Conference on Machine Learning
- 16 June 2013
A new matrix approximation model is proposed where it is assumed that the matrix is locally of low-rank, leading to a representation of the observed matrix as a weighted sum ofLow-rank matrices, and improvements in prediction accuracy over classical approaches for recommendation tasks.
Local collaborative ranking
The experiments indicate that the combination of a mixture of local low-rank matrices each of which was trained to minimize a ranking loss outperforms many of the currently used state-of-the-art recommendation systems.
N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification
- Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee
- Computer ScienceConference on Uncertainty in Artificial…
- 24 February 2018
The proposed N-GCN model improves state-of-the-art baselines on all of the challenging node classification tasks the authors consider: Cora, Citeseer, Pubmed, and PPI, and has other desirable properties, including generalization to recently proposed semi-supervised learning methods such as GraphSAGE, and resilience to adversarial input perturbations.
A Comparative Study of Collaborative Filtering Algorithms
- Joonseok Lee, Mingxuan Sun, G. Lebanon
- Computer ScienceProceedings of the International Conference on…
- 14 May 2012
This paper conducts a study comparing several collaborative ltering techniques, both classic and recent state-of-the-art, in a variety of experimental contexts to identify what algorithms work well and in what conditions.
LLORMA: Local Low-Rank Matrix Approximation
- Joonseok Lee, Seungyeon Kim, G. Lebanon, Y. Singer, Samy Bengio
- Computer ScienceJournal of machine learning research
This paper proposes, analyzes, and experiment with two procedures, one parallel and the other global, for constructing local matrix approximations, which approximate the observed matrix as a weighted sum of low-rank matrices.
PREA: personalized recommendation algorithms toolkit
This paper describes an open-source toolkit implementing many recommendation algorithms as well as popular evaluation metrics, and in contrast to other packages, this toolkit implements recent state-of-the-art algorithms as to most classic algorithms.
Learning multiple-question decision trees for cold-start recommendation
- Mingxuan Sun, Fuxin Li, Joonseok Lee, Ke Zhou, G. Lebanon, H. Zha
- Computer ScienceWSDM '13
- 4 February 2013
A novel algorithm that learns to conduct the interview process guided by a decision tree with multiple questions at each split is proposed, which outperforms state-of-the-art approaches in terms of both the prediction accuracy and user cognitive efforts.
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
- Inioluwa Deborah Raji, Timnit Gebru, Margaret Mitchell, Joy Buolamwini, Joonseok Lee, Emily L. Denton
- Computer ScienceAAAI/ACM Conference on AI, Ethics, and Society
- 3 January 2020
A set of five ethical concerns in the particular case of auditing commercial facial processing technology are demonstrated, highlighting additional design considerations and ethical tensions the auditor needs to be aware of so as not to exacerbate or complement the harms propagated by the audited system.
The 2nd YouTube-8M Large-Scale Video Understanding Challenge
- Joonseok Lee, A. Natsev, Walter Reade, R. Sukthankar, G. Toderici
- Computer ScienceECCV Workshops
- 8 September 2018
This paper briefly introduces the YouTube-8M dataset and challenge task, followed by participants statistics and result analysis, and summarizes proposed ideas by participants, including architectures, temporal aggregation methods, ensembling and distillation, data augmentation, and more.