Models, code, and papers for "Yifeng Lu":

Transfer Learning with Neural AutoML

Sep 27, 2018
Catherine Wong, Neil Houlsby, Yifeng Lu, Andrea Gesmundo

We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost.To address this we propose Transfer Neural AutoML that uses knowledge from prior tasks to speed up network design. We extend RL-based architecture search methods to support parallel training on multiple tasks and then transfer the search strategy to new tasks. On language and image classification data, Transfer Neural AutoML reduces convergence time over single-task training by over an order of magnitude on many tasks.


  Click for Model/Code and Paper
Text Flow: A Unified Text Detection System in Natural Scene Images

Apr 23, 2016
Shangxuan Tian, Yifeng Pan, Chang Huang, Shijian Lu, Kai Yu, Chew Lim Tan

The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and text line verification. However, errors occur and accumulate throughout each of these sequential steps which often lead to low detection performance. To address these issues, we propose a unified scene text detection system, namely Text Flow, by utilizing the minimum cost (min-cost) flow network model. With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively. The proposed technique has been tested on three public datasets, i.e, ICDAR2011 dataset, ICDAR2013 dataset and a multilingual dataset and it outperforms the state-of-the-art methods on all three datasets with much higher recall and F-score. The good performance on the multilingual dataset shows that the proposed technique can be used for the detection of texts in different languages.

* 9 pages, ICCV 2015 

  Click for Model/Code and Paper
An Attention-Based Approach for Single Image Super Resolution

Jul 18, 2018
Yuan Liu, Yuancheng Wang, Nan Li, Xu Cheng, Yifeng Zhang, Yongming Huang, Guojun Lu

The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.


  Click for Model/Code and Paper
Towards a Human-like Open-Domain Chatbot

Jan 31, 2020
Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, Quoc V. Le

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated.

* 38 pages, 12 figures 

  Click for Model/Code and Paper
Epistemic Logic with Functional Dependency Operator

Jun 07, 2017
Yifeng Ding

Epistemic logic with non-standard knowledge operators, especially the "knowing-value" operator, has recently gathered much attention. With the "knowing-value" operator, we can express knowledge of individual variables, but not of the relations between them in general. In this paper, we propose a new operator Kf to express knowledge of the functional dependencies between variables. The semantics of this Kf operator uses a function domain which imposes a constraint on what counts as a functional dependency relation. By adjusting this function domain, different interesting logics arise, and in this paper we axiomatize three such logics in a single agent setting. Then we show how these three logics can be unified by allowing the function domain to vary relative to different agents and possible worlds. A multiagent axiomatization is given in this case.

* Studies in Logic, Vol. 9, No. 4 (2016): 55-84 

  Click for Model/Code and Paper
Discovering Subdimensional Motifs of Different Lengths in Large-Scale Multivariate Time Series

Nov 20, 2019
Yifeng Gao, Jessica Lin

Detecting repeating patterns of different lengths in time series, also called variable-length motifs, has received a great amount of attention by researchers and practitioners. Despite the significant progress that has been made in recent single dimensional variable-length motif discovery work, detecting variable-length \textit{subdimensional motifs}---patterns that are simultaneously occurring only in a subset of dimensions in multivariate time series---remains a difficult task. The main challenge is scalability. On the one hand, the brute-force enumeration solution, which searches for motifs of all possible lengths, is very time consuming even in single dimensional time series. On the other hand, previous work show that index-based fixed-length approximate motif discovery algorithms such as random projection are not suitable for detecting variable-length motifs due to memory requirement. In this paper, we introduce an approximate variable-length subdimensional motif discovery algorithm called \textbf{C}ollaborative \textbf{HI}erarchy based \textbf{M}otif \textbf{E}numeration (CHIME) to efficiently detect variable-length subdimensional motifs given a minimum motif length in large-scale multivariate time series. We show that the memory cost of the approach is significantly smaller than that of random projection. Moreover, the speed of the proposed algorithm is significantly faster than that of the state-of-the-art algorithms. We demonstrate that CHIME can efficiently detect meaningful variable-length subdimensional motifs in large real world multivariate time series datasets.

* Accepted by ICDM 2019 

  Click for Model/Code and Paper
Multi-Frequency Vector Diffusion Maps

Jun 06, 2019
Yifeng Fan, Zhizhen Zhao

We introduce multi-frequency vector diffusion maps (MFVDM), a new framework for organizing and analyzing high dimensional datasets. The new method is a mathematical and algorithmic generalization of vector diffusion maps (VDM) and other non-linear dimensionality reduction methods. MFVDM combines different nonlinear embeddings of the data points defined with multiple unitary irreducible representations of the alignment group that connect two nodes in the graph. We illustrate the efficacy of MFVDM on synthetic data generated according to a random graph model and cryo-electron microscopy image dataset. The new method achieves better nearest neighbor search and alignment estimation than the state-of-the-arts VDM and diffusion maps (DM) on extremely noisy data.


  Click for Model/Code and Paper
Cryo-Electron Microscopy Image Analysis Using Multi-Frequency Vector Diffusion Maps

Apr 16, 2019
Yifeng Fan, Zhizhen Zhao

Cryo-electron microscopy (EM) single particle reconstruction is an entirely general technique for 3D structure determination of macromolecular complexes. However, because the images are taken at low electron dose, it is extremely hard to visualize the individual particle with low contrast and high noise level. In this paper, we propose a novel approach called multi-frequency vector diffusion maps (MFVDM) to improve the efficiency and accuracy of cryo-EM 2D image classification and denoising. This framework incorporates different irreducible representations of the estimated alignment between similar images. In addition, we propose a graph filtering scheme to denoise the images using the eigenvalues and eigenvectors of the MFVDM matrices. Through both simulated and publicly available real data, we demonstrate that our proposed method is efficient and robust to noise compared with the state-of-the-art cryo-EM 2D class averaging and image restoration algorithms.


  Click for Model/Code and Paper
Exploiting Model Equivalences for Solving Interactive Dynamic Influence Diagrams

Jan 18, 2014
Yifeng Zeng, Prashant Doshi

We focus on the problem of sequential decision making in partially observable environments shared with other agents of uncertain types having similar or conflicting objectives. This problem has been previously formalized by multiple frameworks one of which is the interactive dynamic influence diagram (I-DID), which generalizes the well-known influence diagram to the multiagent setting. I-DIDs are graphical models and may be used to compute the policy of an agent given its belief over the physical state and others models, which changes as the agent acts and observes in the multiagent setting. As we may expect, solving I-DIDs is computationally hard. This is predominantly due to the large space of candidate models ascribed to the other agents and its exponential growth over time. We present two methods for reducing the size of the model space and stemming its exponential growth. Both these methods involve aggregating individual models into equivalence classes. Our first method groups together behaviorally equivalent models and selects only those models for updating which will result in predictive behaviors that are distinct from others in the updated model space. The second method further compacts the model space by focusing on portions of the behavioral predictions. Specifically, we cluster actionally equivalent models that prescribe identical actions at a single time step. Exactly identifying the equivalences would require us to solve all models in the initial set. We avoid this by selectively solving some of the models, thereby introducing an approximation. We discuss the error introduced by the approximation, and empirically demonstrate the improved efficiency in solving I-DIDs due to the equivalences.

* Journal Of Artificial Intelligence Research, Volume 43, pages 211-255, 2012 

  Click for Model/Code and Paper
Ensemble Grammar Induction For Detecting Anomalies in Time Series

Jan 29, 2020
Yifeng Gao, Jessica Lin, Constantin Brif

Time series anomaly detection is an important task, with applications in a broad variety of domains. Many approaches have been proposed in recent years, but often they require that the length of the anomalies be known in advance and provided as an input parameter. This limits the practicality of the algorithms, as such information is often unknown in advance, or anomalies with different lengths might co-exist in the data. To address this limitation, previously, a linear time anomaly detection algorithm based on grammar induction has been proposed. While the algorithm can find variable-length patterns, it still requires preselecting values for at least two parameters at the discretization step. How to choose these parameter values properly is still an open problem. In this paper, we introduce a grammar-induction-based anomaly detection method utilizing ensemble learning. Instead of using a particular choice of parameter values for anomaly detection, the method generates the final result based on a set of results obtained using different parameter values. We demonstrate that the proposed ensemble approach can outperform existing grammar-induction-based approaches with different criteria for selection of parameter values. We also show that the proposed approach can achieve performance similar to that of the state-of-the-art distance-based anomaly detection algorithm.

* 12 pages 

  Click for Model/Code and Paper
Representation Theoretic Patterns in Multi-Frequency Class Averaging for Three-Dimensional Cryo-Electron Microscopy

May 31, 2019
Tingran Gao, Yifeng Fan, Zhizhen Zhao

We develop in this paper a novel intrinsic classification algorithm -- multi-frequency class averaging (MFCA) -- for clustering noisy projection images obtained from three-dimensional cryo-electron microscopy (cryo-EM) by the similarity among their viewing directions. This new algorithm leverages multiple irreducible representations of the unitary group to introduce additional redundancy into the representation of the transport data, extending and outperforming the previous class averaging algorithm of Hadani and Singer [Foundations of Computational Mathematics, 11 (5), pp. 589--616 (2011)] that uses only a single representation. The formal algebraic model and representation theoretic patterns of the proposed MFCA algorithm extend the framework of Hadani and Singer to arbitrary irreducible representations of the unitary group. We conceptually establish the consistency and stability of MFCA by inspecting the spectral properties of a generalized localized parallel transport operator on the two-dimensional unit sphere through the lens of Wigner matrices. We demonstrate the efficacy of the proposed algorithm with numerical experiments.

* 31 pages, 10 figures 

  Click for Model/Code and Paper
A Novel and Robust Evolution Algorithm for Optimizing Complicated Functions

Aug 17, 2011
Yifeng Gao, Shuhong Gong, Ge Zhao

In this paper, a novel mutation operator of differential evolution algorithm is proposed. A new algorithm called divergence differential evolution algorithm (DDEA) is developed by combining the new mutation operator with divergence operator and assimilation operator (divergence operator divides population, and, assimilation operator combines population), which can detect multiple solutions and robustness in noisy environment. The new algorithm is applied to optimize Michalewicz Function and to track changing of rain-induced-attenuation process. The results based on DDEA are compared with those based on Differential Evolution Algorithm (DEA). It shows that DDEA algorithm gets better results than DEA does in the same premise. The new algorithm is significant for optimizing and tracking the characteristics of MIMO (Multiple Input Multiple Output) channel at millimeter waves.

* 4papers 

  Click for Model/Code and Paper
Data-Augmented Contact Model for Rigid Body Simulation

Sep 23, 2018
Yifeng Jiang, Jiazheng Sun, C. Karen Liu

Accurately modeling contact behaviors for real-world, near-rigid materials remains a grand challenge for existing rigid-body physics simulators. This paper introduces a data-augmented contact model that incorporates analytical solutions with observed data to predict the 3D contact impulse which could result in rigid bodies bouncing, sliding or spinning in all directions. Our method enhances the expressiveness of the standard Coulomb contact model by learning the contact behaviors from the observed data, while preserving the fundamental contact constraints whenever possible. For example, a classifier is trained to approximate the transitions between static and dynamic frictions, while non-penetration constraint during collision is enforced analytically. Our method computes the aggregated effect of contact for the entire rigid body, instead of predicting the contact force for each contact point individually, removing the exponential decline in accuracy as the number of contact points increases.

* 7 pages, 7 figures. Submitted to ICRA 2019. Added video attachment with full 3D experiments: https://youtu.be/AKSD8TabDV8 

  Click for Model/Code and Paper
Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams

Sep 01, 2014
Muthukumaran Chandrasekaran, Prashant Doshi, Yifeng Zeng, Yingke Chen

Planning for ad hoc teamwork is challenging because it involves agents collaborating without any prior coordination or communication. The focus is on principled methods for a single agent to cooperate with others. This motivates investigating the ad hoc teamwork problem in the context of individual decision making frameworks. However, individual decision making in multiagent settings faces the task of having to reason about other agents' actions, which in turn involves reasoning about others. An established approximation that operationalizes this approach is to bound the infinite nesting from below by introducing level 0 models. We show that a consequence of the finitely-nested modeling is that we may not obtain optimal team solutions in cooperative settings. We address this limitation by including models at level 0 whose solutions involve learning. We demonstrate that the learning integrated into planning in the context of interactive dynamic influence diagrams facilitates optimal team behavior, and is applicable to ad hoc teamwork.

* 8 pages, Appeared in the MSDM Workshop at AAMAS 2014, Extended Abstract version appeared at AAMAS 2014, France 

  Click for Model/Code and Paper
Exploring Deep Anomaly Detection Methods Based on Capsule Net

Jul 15, 2019
Xiaoyan Li, Iluju Kiringa, Tet Yeap, Xiaodan Zhu, Yifeng Li

In this paper, we develop and explore deep anomaly detection techniques based on the capsule network (CapsNet) for image data. Being able to encoding intrinsic spatial relationship between parts and a whole, CapsNet has been applied as both a classifier and deep autoencoder. This inspires us to design a prediction-probability-based and a reconstruction-error-based normality score functions for evaluating the "outlierness" of unseen images. Our results on three datasets demonstrate that the prediction-probability-based method performs consistently well, while the reconstruction-error-based approach is relatively sensitive to the similarity between labeled and unlabeled images. Furthermore, both of the CapsNet-based methods outperform the principled benchmark methods in many cases.

* Presented in the "ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning", June 14, Long Beach, California, USA 

  Click for Model/Code and Paper
Multi-granularity Generator for Temporal Action Proposal

Nov 28, 2018
Yuan Liu, Lin Ma, Yifeng Zhang, Wei Liu, Shih-Fu Chang

Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information. First, we propose to use a bilinear matching model to exploit the rich local information within the video sequence. Afterwards, two components, namely segment proposal generator (SPG) and frame actionness generator (FAG), are combined to perform the task of temporal action proposal at two distinct granularities. SPG considers the whole video in the form of feature pyramid and generates segment proposals from one coarse perspective, while FAG carries out a finer actionness evaluation for each video frame. Our proposed MGG can be trained in an end-to-end fashion. Through temporally adjusting the segment proposals with fine-grained information based on frame actionness, MGG achieves the superior performance over state-of-the-art methods on the public THUMOS-14 and ActivityNet-1.3 datasets. Moreover, we employ existing action classifiers to perform the classification of the proposals generated by MGG, leading to significant improvements compared against the competing methods for the video detection task.


  Click for Model/Code and Paper
Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation

Apr 30, 2019
Yifeng Jiang, Tom Van Wouwe, Friedl De Groote, C. Karen Liu

Using joint actuators to drive the skeletal movements is a common practice in character animation, but the resultant torque patterns are often unnatural or infeasible for real humans to achieve. On the other hand, physiologically-based models explicitly simulate muscles and tendons and thus produce more human-like movements and torque patterns. This paper introduces a technique to transform an optimal control problem formulated in the muscle-actuation space to an equivalent problem in the joint-actuation space, such that the solutions to both problems have the same optimal value. By solving the equivalent problem in the joint-actuation space, we can generate human-like motions comparable to those generated by musculotendon models, while retaining the benefit of simple modeling and fast computation offered by joint-actuation models. Our method transforms constant bounds on muscle activations to nonlinear, state-dependent torque limits in the joint-actuation space. In addition, the metabolic energy function on muscle activations is transformed to a nonlinear function of joint torques, joint configuration and joint velocity. Our technique can also benefit policy optimization using deep reinforcement learning approach, by providing a more anatomically realistic action space for the agent to explore during the learning process. We take the advantage of the physiologically-based simulator, OpenSim, to provide training data for learning the torque limits and the metabolic energy function. Once trained, the same torque limits and the energy function can be applied to drastically different motor tasks formulated as either trajectory optimization or policy learning.

* 12 pages, 8 figures 

  Click for Model/Code and Paper
LoAdaBoost:Loss-Based AdaBoost Federated Machine Learning on medical Data

Nov 30, 2018
Li Huang, Yifeng Yin, Zeng Fu, Shifa Zhang, Hao Deng, Dianbo Liu

Medical data are valuable for improvement of health care, policy making and many other purposes. Vast amount of medical data are stored in different locations ,on many different devices and in different data silos. Sharing medical data among different sources is a big challenge due to regulatory , operational and security reasons. One potential solution is federated machine learning ,which a method that sends machine learning algorithms simultaneously to all data sources ,train models in each source and aggregates the learned models. This strategy allows utilization of valuable data without moving them. In this article, we proposed an adaptive boosting method that increases the efficiency of federated machine learning. Using intensive care unit data from hospital, we showed that LoAdaBoost federated learning outperformed baseline method and increased communication efficiency at negligible additional cost.


  Click for Model/Code and Paper
A Novel Approach for Stable Selection of Informative Redundant Features from High Dimensional fMRI Data

May 25, 2016
Yilun Wang, Zhiqiang Li, Yifeng Wang, Xiaona Wang, Junjie Zheng, Xujuan Duan, Huafu Chen

Feature selection is among the most important components because it not only helps enhance the classification accuracy, but also or even more important provides potential biomarker discovery. However, traditional multivariate methods is likely to obtain unstable and unreliable results in case of an extremely high dimensional feature space and very limited training samples, where the features are often correlated or redundant. In order to improve the stability, generalization and interpretations of the discovered potential biomarker and enhance the robustness of the resultant classifier, the redundant but informative features need to be also selected. Therefore we introduced a novel feature selection method which combines a recent implementation of the stability selection approach and the elastic net approach. The advantage in terms of better control of false discoveries and missed discoveries of our approach, and the resulted better interpretability of the obtained potential biomarker is verified in both synthetic and real fMRI experiments. In addition, we are among the first to demonstrate the robustness of feature selection benefiting from the incorporation of stability selection and also among the first to demonstrate the possible unrobustness of the classical univariate two-sample t-test method. Specifically, we show the robustness of our feature selection results in existence of noisy (wrong) training labels, as well as the robustness of the resulted classifier based on our feature selection results in the existence of data variation, demonstrated by a multi-center attention-deficit/hyperactivity disorder (ADHD) fMRI data.


  Click for Model/Code and Paper