Search Results for author: Xi Liu

Found 36 papers, 6 papers with code

Exploration Through Bias: Revisiting Biased Maximum Likelihood Estimation in Stochastic Multi-Armed Bandits

no code implementations ICML 2020 Xi Liu, Ping-Chun Hsieh, Yu Heng Hung, Anirban Bhattacharya, P. Kumar

We propose a new family of bandit algorithms, that are formulated in a general way based on the Biased Maximum Likelihood Estimation (BMLE) method originally appearing in the adaptive control literature.

Multi-Armed Bandits

PingAnTech at SMM4H task1: Multiple pre-trained model approaches for Adverse Drug Reactions

no code implementations SMM4H (COLING) 2022 Xi Liu, Han Zhou, Chang Su

For task 1a, the system achieved an F1 score of 0. 68; for task 1b Overlapping F1 score of 0. 65 and a Strict F1 score of 0. 49.

Language Modelling

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

no code implementations1 Mar 2024 Xi Liu, Ying Guo, Cheng Zhen, Tong Li, Yingying Ao, Pengfei Yan

To achieve coherence between segments, we design a Past Guided Generation Module (PGG) to maintain the consistency of customized listener attributes through the motion prior, and utilize a diffusion-based structure conditioned on the portrait token and the motion prior to realize the controllable generation.

A GPU-based Hydrodynamic Simulator with Boid Interactions

1 code implementation25 Nov 2023 Xi Liu, Gizem Kayar, Ken Perlin

To enable realistic fluid rendering and simulation in a particle-based system, it is essential to construct a mesh from the particle attributes.

Surface Reconstruction

Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale

no code implementations14 Nov 2023 Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen

In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.

Neural Architecture Search

DistDNAS: Search Efficient Feature Interactions within 2 Hours

no code implementations1 Nov 2023 Tunhou Zhang, Wei Wen, Igor Fedorov, Xi Liu, Buyun Zhang, Fangqiu Han, Wen-Yen Chen, Yiping Han, Feng Yan, Hai Li, Yiran Chen

To optimize search efficiency, DistDNAS distributes the search and aggregates the choice of optimal interaction modules on varying data dates, achieving over 25x speed-up and reducing search cost from 2 days to 2 hours.

Recommendation Systems

AccFlow: Backward Accumulation for Long-Range Optical Flow

1 code implementation ICCV 2023 Guangyang Wu, Xiaohong Liu, Kunming Luo, Xi Liu, Qingqing Zheng, Shuaicheng Liu, Xinyang Jiang, Guangtao Zhai, Wenyi Wang

To train and evaluate the proposed AccFlow, we have constructed a large-scale high-quality dataset named CVO, which provides ground-truth optical flow labels between adjacent and distant frames.

Optical Flow Estimation

Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

no code implementations12 Jul 2023 Xuewei Wang, Qiang Jin, Shengyu Huang, Min Zhang, Xi Liu, Zhengli Zhao, Yukun Chen, Zhengyu Zhang, Jiyan Yang, Ellie Wen, Sagar Chordia, Wenlin Chen, Qin Huang

In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i. e. ads clicks and ads quality events) and their task relations.

Multi-Task Learning

AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations

1 code implementation11 Apr 2023 Danwei Li, Zhengyu Zhang, Siyang Yuan, Mingze Gao, Weilin Zhang, Chaofei Yang, Xi Liu, Jiyan Yang

However, MTL research faces two challenges: 1) effectively modeling the relationships between tasks to enable knowledge sharing, and 2) jointly learning task-specific and shared knowledge.

Multi-Task Learning

Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels

no code implementations31 Mar 2023 Ziheng Wang, Conor Perreault, Xi Liu, Anthony Jarc

Endoscopic video recordings are widely used in minimally invasive robot-assisted surgery, but when the endoscope is outside the patient's body, it can capture irrelevant segments that may contain sensitive information.

Self-Supervised Learning

Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees

no code implementations10 Dec 2022 Hsin-En Su, Yen-ju Chen, Ping-Chun Hsieh, Xi Liu

In this paper, we rethink off-policy learning via Coordinate Ascent Policy Optimization (CAPO), an off-policy actor-critic algorithm that decouples policy improvement from the state distribution of the behavior policy without using the policy gradient.


Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots

no code implementations6 Dec 2022 Wei Hung, Bo-Kai Huang, Ping-Chun Hsieh, Xi Liu

Many real-world continuous control problems are in the dilemma of weighing the pros and cons, multi-objective reinforcement learning (MORL) serves as a generic framework of learning control policies for different preferences over objectives.

Continuous Control Multi-Objective Reinforcement Learning

DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction

no code implementations11 Mar 2022 Buyun Zhang, Liang Luo, Xi Liu, Jay Li, Zeliang Chen, Weilin Zhang, Xiaohan Wei, Yuchen Hao, Michael Tsang, Wenjun Wang, Yang Liu, Huayu Li, Yasmine Badr, Jongsoo Park, Jiyan Yang, Dheevatsa Mudigere, Ellie Wen

To overcome the challenge brought by DHEN's deeper and multi-layer structure in training, we propose a novel co-designed training system that can further improve the training efficiency of DHEN.

Click-Through Rate Prediction

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales

1 code implementation27 Sep 2021 Tao Liu, P. R. Kumar, Ruida Zhou, Xi Liu

Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful.

A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

no code implementations17 Aug 2021 Xi Liu, Xiabi Liu, Huiyu Li, Xiaopeng Gong

In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps.

Decoder Segmentation

Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization

no code implementations NeurIPS 2021 Bing-Jing Hsieh, Ping-Chun Hsieh, Xi Liu

While it serves as a natural idea to combine DQN and an existing few-shot learning method, we identify that such a direct combination does not perform well due to severe overfitting, which is particularly critical in BO due to the need of a versatile sampling policy.

Bayesian Optimization Few-Shot Learning

Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization

no code implementations22 Feb 2021 Jyun-Li Lin, Wei Hung, Shang-Hsuan Yang, Ping-Chun Hsieh, Xi Liu

Action-constrained reinforcement learning (RL) is a widely-used approach in various real-world applications, such as scheduling in networked systems with resource constraints and control of a robot with kinematic constraints.

Reinforcement Learning (RL) Scheduling

Reward Biased Maximum Likelihood Estimation for Reinforcement Learning

no code implementations16 Nov 2020 Akshay Mete, Rahul Singh, Xi Liu, P. R. Kumar

The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the "dual control problem", or, contemporaneously, the "exploration vs. exploitation problem".

Multi-Armed Bandits reinforcement-learning +2

Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits

no code implementations8 Oct 2020 Yu-Heng Hung, Ping-Chun Hsieh, Xi Liu, P. R. Kumar

Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems.

Computational Efficiency

Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning

no code implementations27 Jan 2020 Xi Liu, Li Li, Ping-Chun Hsieh, Muhe Xie, Yong Ge, Rui Chen

With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue.

Knowledge Distillation Multi-Task Learning +2

Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits

no code implementations2 Jul 2019 Xi Liu, Ping-Chun Hsieh, Anirban Bhattacharya, P. R. Kumar

To choose the bias-growth rate $\alpha(t)$ in RBMLE, we reveal the nontrivial interplay between $\alpha(t)$ and the regret bound that generally applies in both the Exponential Family as well as the sub-Gaussian/Exponential family bandits.

Multi-Armed Bandits

Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Games

no code implementations14 Jan 2019 Xi Liu, Muhe Xie, Xidao Wen, Rui Chen, Yong Ge, Nick Duffield, Na Wang

In this paper, we present the first large-scale churn analysis for mobile games that supports both micro-level churn prediction and macro-level churn ranking.


Streaming Network Embedding through Local Actions

no code implementations14 Nov 2018 Xi Liu, Ping-Chun Hsieh, Nick Duffield, Rui Chen, Muhe Xie, Xidao Wen

Thus the approach of adapting the existing methods to the streaming environment faces non-trivial technical challenges.

Clustering Multi-class Classification +1

Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging

1 code implementation29 Oct 2018 Ping-Chun Hsieh, Xi Liu, Anirban Bhattacharya, P. R. Kumar

Sequential decision making for lifetime maximization is a critical problem in many real-world applications, such as medical treatment and portfolio selection.

Decision Making Multi-Armed Bandits

A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games

no code implementations20 Aug 2018 Xi Liu, Muhe Xie, Xidao Wen, Rui Chen, Yong Ge, Nick Duffield, Na Wang

To evaluate the performance of our solution, we collect real-world data from the Samsung Game Launcher platform that includes tens of thousands of games and hundreds of millions of user-app interactions.


A Graph Signal Processing Approach For Real-Time Traffic Prediction In Transportation Networks

no code implementations19 Nov 2017 Arman Hasanzadeh, Xi Liu, Nick Duffield, Krishna R. Narayanan, Byron Chigoy

Building a prediction model for transportation networks is challenging because spatio-temporal dependencies of traffic data in different roads are complex and the graph constructed from road networks is very large.

Clustering Management +3

Adaptive Neighboring Selection Algorithm Based on Curvature Prediction in Manifold Learning

no code implementations13 Apr 2017 Lin Ma, Caifa Zhou, Xi Liu, Yubin Xu

By verifying the proposed algorithm on embedding Swiss roll from R3 to R2 based on LLE and ISOMAP algorithm, the simulation results show that the proposed adaptive neighboring selection algorithm is feasible and able to find the optimal value of K, making the residual variance relatively small and better visualization of the results.

Dimensionality Reduction

Full-reference image quality assessment-based B-mode ultrasound image similarity measure

no code implementations10 Jan 2017 Kele Xu, Xi Liu, Hengxing Cai, Zhifeng Gao

During the last decades, the number of new full-reference image quality assessment algorithms has been increasing drastically.

Image Quality Assessment

Maximum Correntropy Unscented Filter

no code implementations26 Aug 2016 Xi Liu, Badong Chen, Bin Xu, Zongze Wu, Paul Honeine

To improve the robustness of the UKF against impulsive noises, a new filter for nonlinear systems is proposed in this work, namely the maximum correntropy unscented filter (MCUF).

Maximum Correntropy Kalman Filter

no code implementations15 Sep 2015 Badong Chen, Xi Liu, Haiquan Zhao, José C. Príncipe

Traditional Kalman filter (KF) is derived under the well-known minimum mean square error (MMSE) criterion, which is optimal under Gaussian assumption.

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