1 code implementation • 19 Feb 2024 • Zhongzheng Qiao, Quang Pham, Zhen Cao, Hoang H Le, P. N. Suganthan, Xudong Jiang, Ramasamy Savitha
Real-world environments are inherently non-stationary, frequently introducing new classes over time.
no code implementations • 4 Feb 2024 • Quang Pham, Giang Do, Huy Nguyen, TrungTin Nguyen, Chenghao Liu, Mina Sartipi, Binh T. Nguyen, Savitha Ramasamy, XiaoLi Li, Steven Hoi, Nhat Ho
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width.
1 code implementation • 12 Dec 2023 • Giang Do, Khiem Le, Quang Pham, TrungTin Nguyen, Thanh-Nam Doan, Bint T. Nguyen, Chenghao Liu, Savitha Ramasamy, XiaoLi Li, Steven Hoi
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models.
no code implementations • 18 Nov 2023 • Duy Minh Ho Nguyen, Tan Ngoc Pham, Nghiem Tuong Diep, Nghi Quoc Phan, Quang Pham, Vinh Tong, Binh T. Nguyen, Ngan Hoang Le, Nhat Ho, Pengtao Xie, Daniel Sonntag, Mathias Niepert
Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging.
1 code implementation • ICLR 2023 Tiny Paper Track 2023 • Khoi Minh Nguyen-Duy, Quang Pham, Binh T. Nguyen
Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs).
Ranked #15 on Sequential Image Classification on Sequential MNIST
1 code implementation • 6 Sep 2022 • Quang Pham, Chenghao Liu, Steven C. H. Hoi
Motivated by this theory, we propose \emph{DualNets} (for Dual Networks), a general continual learning framework comprising a fast learning system for supervised learning of pattern-separated representation from specific tasks and a slow learning system for representation learning of task-agnostic general representation via Self-Supervised Learning (SSL).
1 code implementation • ICLR 2022 • Quang Pham, Chenghao Liu, Steven Hoi
Existing continual learning methods use Batch Normalization (BN) to facilitate training and improve generalization across tasks.
1 code implementation • 23 Feb 2022 • Quang Pham, Chenghao Liu, Doyen Sahoo, Steven C. H. Hoi
The fast adaptation capability of deep neural networks in non-stationary environments is critical for online time series forecasting.
1 code implementation • NeurIPS 2021 • Quang Pham, Chenghao Liu, Steven Hoi
According to Complementary Learning Systems (CLS) theory~\citep{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for rapid learning of the specifics and individual experiences, and a slow learning system located in the neocortex for the gradual acquisition of structured knowledge about the environment.
1 code implementation • IEA/AIE 2021 • Hieu Tran, Cuong V. Dinh, Quang Pham, Binh T. Nguyen
In both formal and informal texts, missing punctuation marks make the texts confusing and challenging to read.
no code implementations • 4 Apr 2021 • Duy M. H. Nguyen, Thu T. Nguyen, Huong Vu, Quang Pham, Manh-Duy Nguyen, Binh T. Nguyen, Daniel Sonntag
Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task.
no code implementations • ICLR 2021 • Quang Pham, Chenghao Liu, Doyen Sahoo, Steven Hoi
Continual learning methods with fixed architectures rely on a single network to learn models that can perform well on all tasks.
no code implementations • 1 Jan 2021 • Quang Pham, Chenghao Liu, Steven Hoi
CIER employs an adversarial training to correct the shift in $P(X, Y)$ by matching $P(X|Y)$, which results in an invariant representation that can generalize to unseen domains during inference.
1 code implementation • 30 Jul 2020 • Quang Pham, Doyen Sahoo, Chenghao Liu, Steven C. H. Hoi
Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well on the previous tasks.
1 code implementation • 3 May 2020 • Quang Pham, Marija Stanojevic, Zoran Obradovic
The goal of this paper is to summarize methodologies used in extracting entities and topics from a database of criminal records and from a database of newspapers.
3 code implementations • 9 Feb 2018 • Hung Le, Quang Pham, Doyen Sahoo, Steven C. H. Hoi
This approach allows the model to capture several types of semantic information, which was not possible by the existing models.
4 code implementations • 10 Nov 2017 • Doyen Sahoo, Quang Pham, Jing Lu, Steven C. H. Hoi
Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning setting, which requires the entire training data to be made available prior to the learning task.