Search Results for author: Ting Chen

Found 60 papers, 23 papers with code

Differentiable Product Quantization for Learning Compact Embedding Layers

no code implementations ICML 2020 Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.


A Unified Sequence Interface for Vision Tasks

no code implementations15 Jun 2022 Ting Chen, Saurabh Saxena, Lala Li, Tsung-Yi Lin, David J. Fleet, Geoffrey Hinton

Despite that, by formulating the output of each task as a sequence of discrete tokens with a unified interface, we show that one can train a neural network with a single model architecture and loss function on all these tasks, with no task-specific customization.

Image Captioning Instance Segmentation +4

Scalable Online Disease Diagnosis via Multi-Model-Fused Actor-Critic Reinforcement Learning

no code implementations8 Jun 2022 Weijie He, Ting Chen

In the critic network, a supervised diagnosis model for disease predictions is involved to precisely estimate the state-value function.


Decoder Denoising Pretraining for Semantic Segmentation

no code implementations23 May 2022 Emmanuel Brempong Asiedu, Simon Kornblith, Ting Chen, Niki Parmar, Matthias Minderer, Mohammad Norouzi

We propose a decoder pretraining approach based on denoising, which can be combined with supervised pretraining of the encoder.

Denoising Semantic Segmentation

From Heavy Rain Removal to Detail Restoration: A Faster and Better Network

1 code implementation7 May 2022 Tao Gao, Yuanbo Wen, Jing Zhang, Kaihao Zhang, Ting Chen

Firstly, a dilated dense residual block (DDRB) within the rain streaks removal network is presented to aggregate high/low level features of heavy rain.

Rain Removal

Auto robust relative radiometric normalization via latent change noise modelling

no code implementations24 Nov 2021 Shiqi Liu, Lu Wang, Jie Lian, Ting Chen, Cong Liu, Xuchen Zhan, Jintao Lu, Jie Liu, Ting Wang, Dong Geng, Hongwei Duan, Yuze Tian

Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.

Change Detection

Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling

1 code implementation NeurIPS 2021 Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang

Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.

Contrastive Learning

Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation

no code implementations15 Oct 2021 Yao Qin, Chiyuan Zhang, Ting Chen, Balaji Lakshminarayanan, Alex Beutel, Xuezhi Wang

We show that patch-based negative augmentation consistently improves robustness of ViTs across a wide set of ImageNet based robustness benchmarks.

Data Augmentation

TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations

1 code implementation9 Oct 2021 Shiyu Huang, Wenze Chen, Longfei Zhang, Shizhen Xu, Ziyang Li, Fengming Zhu, Deheng Ye, Ting Chen, Jun Zhu

To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios.

Starcraft Starcraft II

Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization

1 code implementation8 Oct 2021 Shiyu Huang, Bin Wang, Dong Li, Jianye Hao, Ting Chen, Jun Zhu

In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.

Improved Transformer for High-Resolution GANs

2 code implementations NeurIPS 2021 Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs).

Image Generation

Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding

3 code implementations26 May 2021 Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Sercan O. Arik, Tomas Pfister

Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well.

Image Classification Image Generation

Improving Contrastive Learning on Imbalanced Data via Open-World Sampling

1 code implementation NeurIPS 2021 Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang

Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.

Contrastive Learning

Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction

1 code implementation ICLR 2021 Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong

Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.

Translation Video Prediction

Big Self-Supervised Models Advance Medical Image Classification

no code implementations ICCV 2021 Shekoofeh Azizi, Basil Mustafa, Fiona Ryan, Zachary Beaver, Jan Freyberg, Jonathan Deaton, Aaron Loh, Alan Karthikesalingam, Simon Kornblith, Ting Chen, Vivek Natarajan, Mohammad Norouzi

Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis.

Contrastive Learning General Classification +3

Ranking Cost: One-Stage Circuit Routing by Directly Optimizing Global Objective Function

no code implementations1 Jan 2021 Shiyu Huang, Bin Wang, Dong Li, Jianye Hao, Jun Zhu, Ting Chen

In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.

Demystifying Loss Functions for Classification

no code implementations1 Jan 2021 Simon Kornblith, Honglak Lee, Ting Chen, Mohammad Norouzi

It is common to use the softmax cross-entropy loss to train neural networks on classification datasets where a single class label is assigned to each example.

Classification General Classification +1

BSODA: A Bipartite Scalable Framework for Online Disease Diagnosis

no code implementations2 Dec 2020 Weijie He, Xiaohao Mao, Chao Ma, Yu Huang, José Miguel Hernández-Lobato, Ting Chen

To address the challenge, we propose a non-RL Bipartite Scalable framework for Online Disease diAgnosis, called BSODA.

Disease Prediction

CLUE: Towards Discovering Locked Cryptocurrencies in Ethereum

no code implementations2 Dec 2020 Xiaoqi Li, Ting Chen, Xiapu Luo, Chenxu Wang

Because the locked cryptocurrencies can never be controlled by users, avoid interacting with the accounts discovered by CLUE and repeating the same mistakes again can help users to save money.

Cryptography and Security

Intriguing Properties of Contrastive Losses

2 code implementations NeurIPS 2021 Ting Chen, Calvin Luo, Lala Li

We construct datasets with explicit and controllable competing features, and show that, for contrastive learning, a few bits of easy-to-learn shared features can suppress, and even fully prevent, the learning of other sets of competing features.

Contrastive Learning Data Augmentation

Why Do Better Loss Functions Lead to Less Transferable Features?

no code implementations NeurIPS 2021 Simon Kornblith, Ting Chen, Honglak Lee, Mohammad Norouzi

We show that many objectives lead to statistically significant improvements in ImageNet accuracy over vanilla softmax cross-entropy, but the resulting fixed feature extractors transfer substantially worse to downstream tasks, and the choice of loss has little effect when networks are fully fine-tuned on the new tasks.

General Classification Image Classification

Robust Pre-Training by Adversarial Contrastive Learning

1 code implementation NeurIPS 2020 Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang

Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations that are consistent under both data augmentations and adversarial perturbations.

Adversarial Robustness Contrastive Learning

Graph Contrastive Learning with Augmentations

2 code implementations NeurIPS 2020 Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang shen

In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data.

Contrastive Learning Representation Learning +2

Learning to Embed Categorical Features without Embedding Tables for Recommendation

no code implementations21 Oct 2020 Wang-Cheng Kang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Ting Chen, Lichan Hong, Ed H. Chi

Embedding learning of categorical features (e. g. user/item IDs) is at the core of various recommendation models including matrix factorization and neural collaborative filtering.

Collaborative Filtering Natural Language Understanding +2

Big Self-Supervised Models are Strong Semi-Supervised Learners

8 code implementations NeurIPS 2020 Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton

The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge.

Self-Supervised Image Classification Semi-Supervised Image Classification

Image Augmentations for GAN Training

no code implementations4 Jun 2020 Zhengli Zhao, Zizhao Zhang, Ting Chen, Sameer Singh, Han Zhang

We provide new state-of-the-art results for conditional generation on CIFAR-10 with both consistency loss and contrastive loss as additional regularizations.

Image Augmentation Image Generation

Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling

no code implementations8 May 2020 Manchao Zhang, Yi Xie, Jie Zhang, Weichen Wang, Chunwang Wu, Ting Chen, Wei Wu, Pingxing Chen

Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.

Quantum Physics

Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

no code implementations ICLR 2020 Jinlong Liu, Guoqing Jiang, Yunzhi Bai, Ting Chen, Huayan Wang

As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well.

SVQN: Sequential Variational Soft Q-Learning Networks

no code implementations ICLR 2020 Shiyu Huang, Hang Su, Jun Zhu, Ting Chen

Partially Observable Markov Decision Processes (POMDPs) are popular and flexible models for real-world decision-making applications that demand the information from past observations to make optimal decisions.

Decision Making Q-Learning +1

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

no code implementations NeurIPS 2020 Katherine L. Hermann, Ting Chen, Simon Kornblith

By taking less aggressive random crops at training time and applying simple, naturalistic augmentation (color distortion, noise, and blur), we train models that classify ambiguous images by shape a majority of the time, and outperform baselines on out-of-distribution test sets.

Data Augmentation

Enhancing Dialogue Symptom Diagnosis with Global Attention and Symptom Graph

no code implementations IJCNLP 2019 Xinzhu Lin, Xiahui He, Qin Chen, Huaixiao Tou, Zhongyu Wei, Ting Chen

In this paper, we first construct a dialogue symptom diagnosis dataset based on an online medical forum with a large amount of dialogues between patients and doctors.

Natural Language Processing

Learning Compact Embedding Layers via Differentiable Product Quantization

no code implementations25 Sep 2019 Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.


Differentiable Product Quantization for End-to-End Embedding Compression

1 code implementation26 Aug 2019 Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.


Few-Shot Representation Learning for Out-Of-Vocabulary Words

1 code implementation ACL 2019 Ziniu Hu, Ting Chen, Kai-Wei Chang, Yizhou Sun

Existing approaches for learning word embeddings often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts.

Learning Word Embeddings Meta-Learning

Pre-Training Graph Neural Networks for Generic Structural Feature Extraction

no code implementations31 May 2019 Ziniu Hu, Changjun Fan, Ting Chen, Kai-Wei Chang, Yizhou Sun

With the proposed pre-training procedure, the generic structural information is learned and preserved, thus the pre-trained GNN requires less amount of labeled data and fewer domain-specific features to achieve high performance on different downstream tasks.


Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

1 code implementation11 May 2019 Ting Chen, Song Bian, Yizhou Sun

In this work, we propose a dissection of GNNs on graph classification into two parts: 1) the graph filtering, where graph-based neighbor aggregations are performed, and 2) the set function, where a set of hidden node features are composed for prediction.

Classification General Classification +1

Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity

1 code implementation1 Apr 2019 Yunsheng Bai, Hao Ding, Yang Qiao, Agustin Marinovic, Ken Gu, Ting Chen, Yizhou Sun, Wei Wang

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.

General Classification Graph Classification +2

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

no code implementations ICLR 2019 Shun Liao, Ting Chen, Tian Lin, Denny Zhou, Chong Wang

In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes.

Image Classification Language Modelling +2

Self-Supervised GANs via Auxiliary Rotation Loss

4 code implementations CVPR 2019 Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby

In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs.

Image Generation Representation Learning

Self-Supervised GAN to Counter Forgetting

no code implementations27 Oct 2018 Ting Chen, Xiaohua Zhai, Neil Houlsby

To counter forgetting, we encourage the discriminator to maintain useful representations by adding a self-supervision.

Continual Learning General Classification

Adaptive Mixture of Low-Rank Factorizations for Compact Neural Modeling

no code implementations NIPS Workshop CDNNRIA 2018 Ting Chen, Ji Lin, Tian Lin, Song Han, Chong Wang, Denny Zhou

Modern deep neural networks have a large amount of weights, which make them difficult to deploy on computation constrained devices such as mobile phones.

Image Classification Language Modelling

Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations

no code implementations ICML 2018 Ting Chen, Martin Renqiang Min, Yizhou Sun

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols.

Natural Language Processing

HeteroMed: Heterogeneous Information Network for Medical Diagnosis

no code implementations22 Apr 2018 Anahita Hosseini, Ting Chen, Wenjun Wu, Yizhou Sun, Majid Sarrafzadeh

To the best of our knowledge, this is the first study to use Heterogeneous Information Network for modeling clinical data and disease diagnosis.

Medical Diagnosis

Learning K-way D-dimensional Discrete Code For Compact Embedding Representations

no code implementations8 Nov 2017 Ting Chen, Martin Renqiang Min, Yizhou Sun

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols.

Language Modelling

On Sampling Strategies for Neural Network-based Collaborative Filtering

no code implementations23 Jun 2017 Ting Chen, Yizhou Sun, Yue Shi, Liangjie Hong

In this paper, we propose a general neural network-based recommendation framework, which subsumes several existing state-of-the-art recommendation algorithms, and address the efficiency issue by investigating sampling strategies in the stochastic gradient descent training for the framework.

Collaborative Filtering

Joint Text Embedding for Personalized Content-based Recommendation

no code implementations4 Jun 2017 Ting Chen, Liangjie Hong, Yue Shi, Yizhou Sun

While latent factors of items can be learned effectively from user interaction data, in many cases, such data is not available, especially for newly emerged items.

News Recommendation Recommendation Systems

Ideology Detection for Twitter Users with Heterogeneous Types of Links

no code implementations24 Dec 2016 Yupeng Gu, Ting Chen, Yizhou Sun, Bingyu Wang

The problem of ideology detection is to study the latent (political) placement for people, which is traditionally studied on politicians according to their voting behaviors.

Social and Information Networks

Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification

1 code implementation8 Dec 2016 Ting Chen, Yizhou Sun

To address the challenges, we propose a task-guided and path-augmented heterogeneous network embedding model.

Feature Engineering Network Embedding

Entity Embedding-based Anomaly Detection for Heterogeneous Categorical Events

no code implementations26 Aug 2016 Ting Chen, Lu-An Tang, Yizhou Sun, Zhengzhang Chen, Kai Zhang

Anomaly detection plays an important role in modern data-driven security applications, such as detecting suspicious access to a socket from a process.

Anomaly Detection

Dropout Training for SVMs with Data Augmentation

no code implementations10 Aug 2015 Ning Chen, Jun Zhu, Jianfei Chen, Ting Chen

Empirical results on several real datasets demonstrate the effectiveness of dropout training on significantly boosting the classification accuracy of both linear and nonlinear SVMs.

Data Augmentation Representation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.