no code implementations • 4 Oct 2017 • Ming Yu, Addie M. Thompson, Karthikeyan Natesan Ramamurthy, Eunho Yang, Aurélie C. Lozano
Inferring predictive maps between multiple input and multiple output variables or tasks has innumerable applications in data science.
no code implementations • 18 Sep 2017 • Hajin Shim, Sung Ju Hwang, Eunho Yang
We consider the problem of active feature acquisition, where we sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way.
1 code implementation • 13 May 2017 • Meghana Kshirsagar, Eunho Yang, Aurélie C. Lozano
We further demonstrate that our proposed method recovers groups and the sparsity patterns in the task parameters accurately by extensive experiments.
no code implementations • 26 May 2016 • Eunho Yang, Aurelie Lozano, Aleksandr Aravkin
We consider the problem of robustifying high-dimensional structured estimation.
no code implementations • 12 Mar 2017 • Sejun Park, Eunho Yang, Jinwoo Shin
Learning parameters of latent graphical models (GM) is inherently much harder than that of no-latent ones since the latent variables make the corresponding log-likelihood non-concave.
1 code implementation • 31 Aug 2016 • David I. Inouye, Eunho Yang, Genevera I. Allen, Pradeep Ravikumar
The Poisson distribution has been widely studied and used for modeling univariate count-valued data.
no code implementations • NeurIPS 2015 • Eunho Yang, Aurélie C. Lozano
In this paper, we propose the Trimmed Graphical Lasso for robust estimation of sparse GGMs.
no code implementations • 17 Jan 2013 • Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Zhandong Liu
Undirected graphical models, or Markov networks, are a popular class of statistical models, used in a wide variety of applications.
no code implementations • 2 Nov 2014 • Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Yulia Baker, Ying-Wooi Wan, Zhandong Liu
"Mixed Data" comprising a large number of heterogeneous variables (e. g. count, binary, continuous, skewed continuous, among other data types) are prevalent in varied areas such as genomics and proteomics, imaging genetics, national security, social networking, and Internet advertising.
no code implementations • NeurIPS 2018 • Hajin Shim, Sung Ju Hwang, Eunho Yang
We consider the problem of active feature acquisition where the goal is to sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way at test time.
no code implementations • NeurIPS 2015 • Eunho Yang, Aurelie C. Lozano, Pradeep K. Ravikumar
We propose a class of closed-form estimators for GLMs under high-dimensional sampling regimes.
no code implementations • NeurIPS 2014 • Eunho Yang, Aurelie C. Lozano, Pradeep K. Ravikumar
We propose a class of closed-form estimators for sparsity-structured graphical models, expressed as exponential family distributions, under high-dimensional settings.
no code implementations • NeurIPS 2013 • Eunho Yang, Pradeep K. Ravikumar
We provide a unified framework for the high-dimensional analysis of “superposition-structured” or “dirty” statistical models: where the model parameters are a “superposition” of structurally constrained parameters.
no code implementations • NeurIPS 2013 • Eunho Yang, Pradeep K. Ravikumar, Genevera I. Allen, Zhandong Liu
We thus introduce a “novel subclass of CRFs”, derived by imposing node-wise conditional distributions of response variables conditioned on the rest of the responses and the covariates as arising from univariate exponential families.
no code implementations • NeurIPS 2013 • Eunho Yang, Pradeep K. Ravikumar, Genevera I. Allen, Zhandong Liu
Undirected graphical models, such as Gaussian graphical models, Ising, and multinomial/categorical graphical models, are widely used in a variety of applications for modeling distributions over a large number of variables.
no code implementations • NeurIPS 2012 • Eunho Yang, Genevera Allen, Zhandong Liu, Pradeep K. Ravikumar
Our models allow one to estimate networks for a wide class of exponential distributions, such as the Poisson, negative binomial, and exponential, by fitting penalized GLMs to select the neighborhood for each node.
no code implementations • ICML 2017 • Arun Sai Suggala, Eunho Yang, Pradeep Ravikumar
While there have been some work on tractable approximations, these do not come with strong statistical guarantees, and moreover are relatively computationally expensive.
no code implementations • ICML 2017 • Eunho Yang, Aurélie C. Lozano
Imposing sparse + group-sparse superposition structures in high-dimensional parameter estimation is known to provide flexible regularization that is more realistic for many real-world problems.
no code implementations • ICLR 2018 • Hae Beom Lee, Juho Lee, Eunho Yang, Sung Ju Hwang
Moreover, the learning of dropout probabilities for non-target classes on each instance allows the classifier to focus more on classification against the most confusing classes.
no code implementations • 14 May 2019 • Sejun Park, Eunho Yang, Se-Young Yun, Jinwoo Shin
Our contribution is two-fold: (a) we first propose a fully polynomial-time approximation scheme (FPTAS) for approximating the partition function of GM associating with a low-rank coupling matrix; (b) for general high-rank GMs, we design a spectral mean-field scheme utilizing (a) as a subroutine, where it approximates a high-rank GM into a product of rank-1 GMs for an efficient approximation of the partition function.
no code implementations • 26 May 2019 • Jihun Yun, Aurelie C. Lozano, Eunho Yang
Extensive experiments reveal that block-diagonal approaches achieve state-of-the-art results on several deep learning tasks, and can outperform adaptive diagonal methods, vanilla Sgd, as well as a modified version of full-matrix adaptation proposed very recently.
no code implementations • 7 Jun 2019 • Sungyub Kim, Yongsu Baek, Sung Ju Hwang, Eunho Yang
We also introduce an additional form of a regularizer from the perspective of understanding ITE in the semi-supervised learning framework to ensure more reliable representations.
Ranked #1 on Causal Inference on IDHP
no code implementations • 29 Nov 2019 • Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang
As a natural extension of DropBits, we further introduce the way of learning heterogeneous quantization levels to find proper bit-length for each layer using DropBits.
no code implementations • 22 Jun 2020 • Minyoung Song, Jaehong Yoon, Eunho Yang, Sung Ju Hwang
As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of a given network.
no code implementations • 25 Jun 2020 • Bruno Andreis, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang
Deep models are designed to operate on huge volumes of high dimensional data such as images.
no code implementations • 2 Jul 2020 • Kyung-Su Kim, Aurélie C. Lozano, Eunho Yang
(2) A generalization error bound invariant of network size was derived by using a data-dependent complexity measure (CMD).
no code implementations • 2 Jul 2020 • Kyung-Su Kim, Jung Hyun Lee, Eunho Yang
A pre-trained generator has been frequently adopted in compressed sensing (CS) due to its ability to effectively estimate signals with the prior of NNs.
no code implementations • 15 Jul 2020 • Jihun Yun, Aurelie C. Lozano, Eunho Yang
We propose a unified framework for stochastic proximal gradient descent, which we term ProxGen, that allows for arbitrary positive preconditioners and lower semi-continuous regularizers.
no code implementations • ICLR 2021 • Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
Experience replay, which enables the agents to remember and reuse experience from the past, has played a significant role in the success of off-policy reinforcement learning (RL).
no code implementations • NeurIPS 2020 • Youngsung Kim, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same task.
no code implementations • 1 Jan 2021 • Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang
As a natural extension of DropBits, we further introduce the way of learning heterogeneous quantization levels to find proper bit-length for each layer using DropBits.
no code implementations • 1 Jan 2021 • Minyoung Song, Jaehong Yoon, Eunho Yang, Sung Ju Hwang
As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of a given network.
no code implementations • 1 Jan 2021 • Geondo Park, Gyeongman Kim, Eunho Yang
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning.
no code implementations • 7 Feb 2021 • Youngmin Oh, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
We show that the proposed scheme, called Model-augmented $Q$-learning (MQL), obtains a policy-invariant solution which is identical to the solution obtained by learning with true reward.
no code implementations • 26 Mar 2021 • Jaeyun Song, Hajin Shim, Eunho Yang
Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods in machine translation and automatic speech recognition (ASR) tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 3 May 2021 • Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung-Ju Hwang, Jinwoo Shin
Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning.
no code implementations • ICLR 2022 • Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang
We validate the effectiveness of our coreset selection mechanism over various standard, imbalanced, and noisy datasets against strong continual learning baselines, demonstrating that it improves task adaptation and prevents catastrophic forgetting in a sample-efficient manner.
no code implementations • ICCV 2021 • Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices.
no code implementations • ICLR 2022 • Hae Beom Lee, Hayeon Lee, Jaewoong Shin, Eunho Yang, Timothy Hospedales, Sung Ju Hwang
Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters.
no code implementations • 29 Sep 2021 • Juhyuk Lee, Min-Joong Lee, June Yong Yang, Eunho Yang
In this paper, we show that although existing extraction models are able to memorize and recall already seen triples, they cannot generalize effectively for unseen triples.
no code implementations • 29 Sep 2021 • Sungyub Kim, Sihwan Park, Yong-Deok Kim, Eunho Yang
To mitigate this issue, we propose simple bias decay methods including a novel adaptive one and found that this simple remedy can fill a large portion of the performance gaps that occur in large batch optimization.
no code implementations • ICLR 2022 • Youngmin Oh, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
Experience replay is an essential component in off-policy model-free reinforcement learning (MfRL).
no code implementations • 29 Sep 2021 • Andreis Bruno, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang
Deep Learning algorithms are designed to operate on huge volumes of high dimensional data such as images.
no code implementations • ICLR 2022 • Joonhyung Park, Jaeyun Song, Eunho Yang
In many real-world node classification scenarios, nodes are highly class-imbalanced, where graph neural networks (GNNs) can be readily biased to major class instances.
no code implementations • 10 Nov 2021 • Joonhyung Park, Hajin Shim, Eunho Yang
Graph-structured datasets usually have irregular graph sizes and connectivities, rendering the use of recent data augmentation techniques, such as Mixup, difficult.
no code implementations • NeurIPS 2021 • Jihun Yun, Aurelie C. Lozano, Eunho Yang
We consider the training of structured neural networks where the regularizer can be non-smooth and possibly non-convex.
no code implementations • 27 Sep 2018 • Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, Sung Ju Hwang
With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss.
no code implementations • 25 Sep 2019 • Nguyen Anh Tuan, Hyewon Jeong, Eunho Yang, Sungju Hwang
To capture such dynamically changing asymmetric relationships between tasks and long-range temporal dependencies in time-series data, we propose a novel temporal asymmetric multi-task learning model, which learns to combine features from other tasks at diverse timesteps for the prediction of each task.
no code implementations • 2 Dec 2021 • Yeonsung Jung, Hajin Shim, June Yong Yang, Eunho Yang
Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often rely heavily on malignant bias as shortcuts instead of task-related information for discriminative tasks.
no code implementations • 16 Dec 2021 • Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang, Eunho Yang
However, they now suffer from lack of sample diversification as they always deterministically select regions with maximum saliency, injecting bias into the augmented data.
no code implementations • NAACL 2022 • Juhyuk Lee, Min-Joong Lee, June Yong Yang, Eunho Yang
To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before.
no code implementations • 30 Sep 2022 • Sungyub Kim, Sihwan Park, KyungSu Kim, Eunho Yang
Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks.
no code implementations • CVPR 2023 • Gyeongman Kim, Hajin Shim, Hyunsu Kim, Yunjey Choi, Junho Kim, Eunho Yang
Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face video editing task.
no code implementations • CVPR 2023 • Jongin Lim, Youngdong Kim, Byungjai Kim, Chanho Ahn, Jinwoo Shin, Eunho Yang, Seungju Han
Our key idea is that an adversarial attack on a biased model that makes decisions based on spurious correlations may generate synthetic bias-conflicting samples, which can then be used as augmented training data for learning a debiased model.
no code implementations • 23 May 2023 • Minki Kang, Wooseok Han, Sung Ju Hwang, Eunho Yang
Emotional Text-To-Speech (TTS) is an important task in the development of systems (e. g., human-like dialogue agents) that require natural and emotional speech.
no code implementations • 21 Aug 2023 • Dongwook Lee, Wonjun Choi, Seohyung Lee, ByungIn Yoo, Eunho Yang, Seongju Hwang
An effective method to tackle these challenges is template update, which updates the template to reflect the change of appearance in the target object during tracking.
no code implementations • ICCV 2023 • Joonhyung Park, Hyunjin Seo, Eunho Yang
Understanding point clouds captured from the real-world is challenging due to shifts in data distribution caused by varying object scales, sensor angles, and self-occlusion.
no code implementations • 25 Sep 2023 • Minki Kang, Wooseok Han, Eunho Yang
The prosody encoder is specifically designed to model prosodic features that are not captured only with a face image, allowing the face encoder to focus solely on capturing the speaker identity from the face image.
no code implementations • 20 Feb 2024 • Gyeongman Kim, Doohyuk Jang, Eunho Yang
Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression.
no code implementations • 28 Feb 2024 • June Yong Yang, Byeongwook Kim, Jeongin Bae, Beomseok Kwon, Gunho Park, Eunho Yang, Se Jung Kwon, Dongsoo Lee
Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs).
1 code implementation • ICML 2020 • Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang, Sung Ju Hwang
Moreover, it is almost infeasible for the human annotators to examine attentions on tons of instances and features.
1 code implementation • 2 Feb 2024 • Hyunjin Seo, Jihun Yun, Eunho Yang
Since the pioneering work on the lottery ticket hypothesis for graph neural networks (GNNs) was proposed in Chen et al. (2021), the study on finding graph lottery tickets (GLT) has become one of the pivotal focus in the GNN community, inspiring researchers to discover sparser GLT while achieving comparable performance to original dense networks.
1 code implementation • 30 Mar 2024 • Sanghyun Jo, Soohyun Ryu, Sungyub Kim, Eunho Yang, KyungSu Kim
We identify a critical bias in contemporary CLIP-based models, which we denote as \textit{single tag bias}.
Ranked #1 on Open Vocabulary Semantic Segmentation on COCO-Stuff-171 (mIoU metric)
Multi-Label Text Classification Open Vocabulary Semantic Segmentation +3
1 code implementation • 1 Apr 2024 • Jungeun Kim, Hangyul Yoon, Geondo Park, KyungSu Kim, Eunho Yang
4D medical images, which represent 3D images with temporal information, are crucial in clinical practice for capturing dynamic changes and monitoring long-term disease progression.
1 code implementation • ICLR 2020 • Joonyoung Yi, Juhyuk Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang
Among many approaches, the simplest and most intuitive way is zero imputation, which treats the value of a missing entry simply as zero.
1 code implementation • NeurIPS 2020 • In Huh, Eunho Yang, Sung Ju Hwang, Jinwoo Shin
Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics.
1 code implementation • 7 Jul 2022 • Seongjun Yang, Hyeonji Hwang, Daeyoung Kim, Radhika Dua, Jong-Yeup Kim, Eunho Yang, Edward Choi
We evaluate six FL algorithms designed for addressing data heterogeneity among clients, and a hybrid algorithm combining the strengths of two representative FL algorithms.
1 code implementation • ICLR 2020 • Jaehong Yoon, Saehoon Kim, Eunho Yang, Sung Ju Hwang
First, a continual learning model should effectively handle catastrophic forgetting and be efficient to train even with a large number of tasks.
1 code implementation • NeurIPS 2020 • Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi
While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging.
1 code implementation • NeurIPS 2020 • Geondo Park, June Yong Yang, Sung Ju Hwang, Eunho Yang
Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing.
1 code implementation • ICLR 2021 • Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang
Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally.
2 code implementations • 9 Jun 2020 • Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang, Sung Ju Hwang
Moreover, it is almost infeasible for the human annotators to examine attentions on tons of instances and features.
2 code implementations • 23 Jun 2020 • A. Tuan Nguyen, Hyewon Jeong, Eunho Yang, Sung Ju Hwang
Existing asymmetric multi-task learning methods tackle this negative transfer problem by performing knowledge transfer from tasks with low loss to tasks with high loss.
1 code implementation • ICML 2018 • Hae Beom Lee, Eunho Yang, Sung Ju Hwang
We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process.
1 code implementation • 28 May 2018 • Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, Sung Ju Hwang
With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss.
1 code implementation • NeurIPS 2020 • Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh
While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable, which potentially limits the flexibility.
1 code implementation • 30 May 2019 • Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang
Specifically, we meta-learn a noise generator which outputs a multiplicative noise distribution for latent features, to obtain low errors on the test instances in an input-dependent manner.
2 code implementations • ICLR 2020 • Hae Beom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang
Specifically, we meta-learn a noise generator which outputs a multiplicative noise distribution for latent features, to obtain low errors on the test instances in an input-dependent manner.
Ranked #1 on Meta-Learning on OMNIGLOT - 1-Shot, 20-way
1 code implementation • 26 Feb 2023 • Yoonjeon Kim, Hyunsu Kim, Junho Kim, Yunjey Choi, Eunho Yang
With the advantages of fast inference and human-friendly flexible manipulation, image-agnostic style manipulation via text guidance enables new applications that were not previously available.
1 code implementation • 3 Jun 2023 • Changhun Kim, Joonhyung Park, Hajin Shim, Eunho Yang
Automatic speech recognition (ASR) models are frequently exposed to data distribution shifts in many real-world scenarios, leading to erroneous predictions.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • EMNLP 2021 • Geondo Park, Gyeongman Kim, Eunho Yang
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning.
2 code implementations • 5 Jun 2018 • Ingyo Chung, Saehoon Kim, Juho Lee, Kwang Joon Kim, Sung Ju Hwang, Eunho Yang
We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention.
1 code implementation • NeurIPS 2021 • Youngkyu Hong, Eunho Yang
In such a biased dataset, models are susceptible to making predictions based on the biased features of the data.
2 code implementations • NeurIPS 2018 • Jay Heo, Hae Beom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, Sung Ju Hwang
Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them.
4 code implementations • NeurIPS 2018 • Hae Beom Lee, Juho Lee, Saehoon Kim, Eunho Yang, Sung Ju Hwang
Moreover, the learning of dropout rates for non-target classes on each instance allows the classifier to focus more on classification against the most confusing classes.
1 code implementation • 26 Jun 2022 • Jaeyun Song, Joonhyung Park, Eunho Yang
Learning unbiased node representations under class-imbalanced graph data is challenging due to interactions between adjacent nodes.
1 code implementation • NeurIPS 2020 • Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang, Sung Ju Hwang, Jinwoo Shin
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced.
1 code implementation • ICLR 2021 • Wonyong Jeong, Jaehong Yoon, Eunho Yang, Sung Ju Hwang
Through extensive experimental validation of our method in the two different scenarios, we show that our method outperforms both local semi-supervised learning and baselines which naively combine federated learning with semi-supervised learning.
1 code implementation • 6 Mar 2020 • Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang
There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios.
1 code implementation • ICLR 2020 • Hae Beom Lee, Hayeon Lee, Donghyun Na, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang
While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed.
3 code implementations • ICLR 2018 • Jaehong Yoon, Eunho Yang, Jeongtae Lee, Sung Ju Hwang
We propose a novel deep network architecture for lifelong learning which we refer to as Dynamically Expandable Network (DEN), that can dynamically decide its network capacity as it trains on a sequence of tasks, to learn a compact overlapping knowledge sharing structure among tasks.
2 code implementations • 6 Jun 2021 • Dongchan Min, Dong Bok Lee, Eunho Yang, Sung Ju Hwang
In this work, we propose StyleSpeech, a new TTS model which not only synthesizes high-quality speech but also effectively adapts to new speakers.
2 code implementations • ICLR 2019 • Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, Yi Yang
The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class.