Search Results for author: Jiayi Chen

Found 18 papers, 5 papers with code

Accelerating Distributed Deep Learning using Lossless Homomorphic Compression

1 code implementation12 Feb 2024 Haoyu Li, Yuchen Xu, Jiayi Chen, Rohit Dwivedula, Wenfei Wu, Keqiang He, Aditya Akella, Daehyeok Kim

As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.

Computational Efficiency

Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts

no code implementations5 Dec 2023 Jiayi Chen, Benteng Ma, Hengfei Cui, Yong Xia, Kwang-Ting Cheng

To mitigate this issue, federated active learning methods suggest leveraging local and global model predictions to select a relatively small amount of informative local data for annotation.

Active Learning Federated Learning +1

On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval

no code implementations1 Nov 2023 Jiayi Chen, Hanjun Dai, Bo Dai, Aidong Zhang, Wei Wei

However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn't account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents.

Contrastive Learning Entity Retrieval +2

MCRAGE: Synthetic Healthcare Data for Fairness

1 code implementation27 Oct 2023 Keira Behal, Jiayi Chen, Caleb Fikes, Sophia Xiao

Machine learning models trained on class-imbalanced EHR datasets perform significantly worse in deployment for individuals of the minority classes compared to those from majority classes, which may lead to inequitable healthcare outcomes for minority groups.

Denoising Fairness +1

DocumentNet: Bridging the Data Gap in Document Pre-Training

no code implementations15 Jun 2023 Lijun Yu, Jin Miao, Xiaoyu Sun, Jiayi Chen, Alexander G. Hauptmann, Hanjun Dai, Wei Wei

Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI.

document understanding Entity Retrieval +3

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

no code implementations CVPR 2023 Yinzhen Xu, Weikang Wan, Jialiang Zhang, Haoran Liu, Zikang Shan, Hao Shen, Ruicheng Wang, Haoran Geng, Yijia Weng, Jiayi Chen, Tengyu Liu, Li Yi, He Wang

Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud. For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution.

Motion Planning

Self-Attentive Sequential Recommendation with Cheap Causal Convolutions

no code implementations2 Nov 2022 Jiayi Chen, Wen Wu, Liye Shi, Yu Ji, Wenxin Hu, Xi Chen, Wei Zheng, Liang He

We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation.

Sequential Recommendation

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

no code implementations6 Oct 2022 Ruicheng Wang, Jialiang Zhang, Jiayi Chen, Yinzhen Xu, Puhao Li, Tengyu Liu, He Wang

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology.

Object

Teaching Neural Module Networks to Do Arithmetic

no code implementations COLING 2022 Jiayi Chen, Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning.

Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild

no code implementations24 Sep 2022 Jiayi Chen, Mi Yan, Jiazhao Zhang, Yinzhen Xu, Xiaolong Li, Yijia Weng, Li Yi, Shuran Song, He Wang

We for the first time propose a point cloud based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion.

hand-object pose Object +2

DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation

no code implementations22 Apr 2022 Jiayi Chen, Wen Wu, Liye Shi, Yu Ji, Wenxin Hu, Wei Zheng, Liang He

In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity.

Fairness Sequential Recommendation

Long-Tail Session-based Recommendation from Calibration

no code implementations5 Dec 2021 Jiayi Chen, Wen Wu, Wei Zheng, Liang He

Accurate predictions in session-based recommendations have progressed, but a few studies have focused on skewed recommendation lists caused by popularity bias.

Session-Based Recommendations

HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities

no code implementations17 May 2021 Jiayi Chen, Aidong Zhang

To deal with task heterogeneity and promote fast within-task adaptions for each type of tasks, in this paper, we propose HetMAML, a task-heterogeneous model-agnostic meta-learning framework, which can capture both the type-specific and globally shared knowledge and can achieve the balance between knowledge customization and generalization.

Few-Shot Learning Vocal Bursts Type Prediction

Towards a Unified Evaluation of Explanation Methods without Ground Truth

no code implementations20 Nov 2019 Hao Zhang, Jiayi Chen, Haotian Xue, Quanshi Zhang

This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges.

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