Search Results for author: Zhao Yang

Found 17 papers, 5 papers with code

Logic Traps in Evaluating Attribution Scores

no code implementations ACL 2022 Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu, Jun Zhao

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features on model predictions.

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation

no code implementations29 Mar 2022 Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat

Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards.

On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR

no code implementations26 Jan 2022 Zhao Yang, Dianwen Ng, Xiao Fu, Liping Han, Wei Xi, Rui Wang, Rui Jiang, Jizhong Zhao

Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character.

Automatic Speech Recognition

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

2 code implementations4 Dec 2021 Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image.

Referring Expression Referring Expression Segmentation +1

The Logic Traps in Evaluating Post-hoc Interpretations

no code implementations12 Sep 2021 Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu, Jun Zhao

Post-hoc interpretation aims to explain a trained model and reveal how the model arrives at a decision.

Potential-based Reward Shaping in Sokoban

no code implementations10 Sep 2021 Zhao Yang, Mike Preuss, Aske Plaat

While previous work has investigated the use of expert knowledge to generate potential functions, in this work, we study whether we can use a search algorithm(A*) to automatically generate a potential function for reward shaping in Sokoban, a well-known planning task.

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback

1 code implementation13 Aug 2021 Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.

online learning

Alignment Rationale for Natural Language Inference

1 code implementation ACL 2021 Zhongtao Jiang, Yuanzhe Zhang, Zhao Yang, Jun Zhao, Kang Liu

Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors.

Natural Language Inference

Transfer Learning and Curriculum Learning in Sokoban

no code implementations25 May 2021 Zhao Yang, Mike Preuss, Aske Plaat

In reinforcement learning, learning actions for a behavior policy that can be applied to new environments is still a challenge, especially for tasks that involve much planning.

reinforcement-learning Transfer Learning

Explore User Neighborhood for Real-time E-commerce Recommendation

no code implementations28 Feb 2021 Xu Xie, Fei Sun, Xiaoyong Yang, Zhao Yang, Jinyang Gao, Wenwu Ou, Bin Cui

On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information.

Collaborative Filtering Recommendation Systems

Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration

no code implementations3 Dec 2019 Zirui Xu, Zhao Yang, JinJun Xiong, Jianlei Yang, Xiang Chen

In this paper, we propose Helios, a heterogeneity-aware FL framework to tackle the straggler issue.

Distributed, Parallel, and Cluster Computing

Anchor Diffusion for Unsupervised Video Object Segmentation

1 code implementation ICCV 2019 Zhao Yang, Qiang Wang, Luca Bertinetto, Weiming Hu, Song Bai, Philip H. S. Torr

Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.

Ranked #7 on Unsupervised Video Object Segmentation on DAVIS 2016 (using extra training data)

Frame Optical Flow Estimation +3

Hetero-Center Loss for Cross-Modality Person Re-Identification

no code implementations22 Oct 2019 Yuanxin Zhu, Zhao Yang, Li Wang, Sai Zhao, Xiao Hu, Dapeng Tao

With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible.

Cross-Modality Person Re-identification Person Re-Identification

Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling

no code implementations25 Jun 2019 Guorui Zhou, Kailun Wu, Weijie Bian, Zhao Yang, Xiaoqiang Zhu, Kun Gai

In this paper, we model user behavior using an interest delay model, study carefully the embedding mechanism, and obtain two important results: (i) We theoretically prove that small aggregation radius of embedding vectors of items which belongs to a same user interest domain will result in good generalization performance of deep CTR model.

Click-Through Rate Prediction

Learn to Interpret Atari Agents

1 code implementation29 Dec 2018 Zhao Yang, Song Bai, Li Zhang, Philip H. S. Torr

In contrast to previous a-posteriori methods of visualizing DeepRL policies, we propose an end-to-end trainable framework based on Rainbow, a representative Deep Q-Network (DQN) agent.

Decision Making

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