1 code implementation • 26 Sep 2020 • Dai Quoc Nguyen, Thanh Vu, Tu Dinh Nguyen, Dinh Phung
We propose a simple yet effective embedding model to learn quaternion embeddings for entities and relations in knowledge graphs.
1 code implementation • 12 Aug 2020 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
As demonstrated, the Quaternion space, a hyper-complex vector space, provides highly meaningful computations and analogical calculus through Hamilton product compared to the Euclidean and complex vector spaces.
1 code implementation • 22 Jun 2020 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
Despite several signs of progress have been made recently, limited research has been conducted for an inductive setting where embeddings are required for newly unseen nodes -- a setting encountered commonly in practical applications of deep learning for graph networks.
1 code implementation • 12 Nov 2019 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung
In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data.
Ranked #54 on Node Classification on Pubmed
1 code implementation • 26 Sep 2019 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
The transformer self-attention network has been extensively used in research domains such as computer vision, image processing, and natural language processing.
Ranked #1 on Graph Classification on IMDb-M
no code implementations • 25 Sep 2019 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
Thus, U2GAN can address the weaknesses in the existing models in order to produce plausible node embeddings whose sum is the final embedding of the whole graph.
1 code implementation • ACL 2020 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
Knowledge graph embedding methods often suffer from a limitation of memorizing valid triples to predict new ones for triple classification and search personalization problems.
2 code implementations • NAACL 2019 • Dai Quoc Nguyen, Thanh Vu, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung
In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (subject, relation, object).
Ranked #40 on Link Prediction on WN18RR
no code implementations • 3 May 2018 • Hung Vu, Tu Dinh Nguyen, Dinh Phung
Abnormal event detection is one of the important objectives in research and practical applications of video surveillance.
no code implementations • 12 Apr 2018 • Dai Quoc Nguyen, Thanh Vu, Tu Dinh Nguyen, Dinh Phung
After that, the 3-column matrix is fed into a deep learning architecture to re-rank the search results returned by a basis ranker.
1 code implementation • ICLR 2018 • Quan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Phung
We propose in this paper a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem.
3 code implementations • NAACL 2018 • Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung
This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps.
Ranked #58 on Link Prediction on WN18RR
no code implementations • 6 Nov 2017 • Trung Le, Tu Dinh Nguyen, Dinh Phung
In this paper, we propose a new viewpoint for GANs, which is termed as the minimizing general loss viewpoint.
no code implementations • 19 Sep 2017 • Trung Le, Khanh Nguyen, Tu Dinh Nguyen, Dinh Phung
With this spirit, in this paper, we propose Analogical-based Bayesian Optimization that can maximize black-box function over a domain where only a similarity score can be defined.
2 code implementations • NeurIPS 2017 • Tu Dinh Nguyen, Trung Le, Hung Vu, Dinh Phung
We develop theoretical analysis to show that, given the maximal discriminators, optimizing the generator of D2GAN reduces to minimizing both KL and reverse KL divergences between data distribution and the distribution induced from the data generated by the generator, hence effectively avoiding the mode collapsing problem.
Ranked #18 on Image Generation on STL-10 (Inception score metric)
no code implementations • 18 Aug 2017 • Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh
Of current representation learning schemes, restricted Boltzmann machines (RBMs) have proved to be highly effective in unsupervised settings.
no code implementations • 18 Aug 2017 • Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh
The analysis of mixed data has been raising challenges in statistics and machine learning.
no code implementations • 17 Aug 2017 • Hung Vu, Dinh Phung, Tu Dinh Nguyen, Anthony Trevors, Svetha Venkatesh
Automated detection of abnormalities in data has been studied in research area in recent years because of its diverse applications in practice including video surveillance, industrial damage detection and network intrusion detection.
no code implementations • 16 Aug 2017 • Trung Le, Hung Vu, Tu Dinh Nguyen, Dinh Phung
Training model to generate data has increasingly attracted research attention and become important in modern world applications.
no code implementations • 8 Aug 2017 • Quan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Phung
A minimax formulation is able to establish among a classifier, a discriminator, and a set of generators in a similar spirit with GAN.
1 code implementation • 22 Apr 2016 • Trung Le, Tu Dinh Nguyen, Vu Nguyen, Dinh Phung
One of the most challenging problems in kernel online learning is to bound the model size and to promote the model sparsity.