Search Results for author: Lidan Shou

Found 16 papers, 9 papers with code

SkipBERT: Efficient Inference with Shallow Layer Skipping

1 code implementation ACL 2022 Jue Wang, Ke Chen, Gang Chen, Lidan Shou, Julian McAuley

In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.

FloE: On-the-Fly MoE Inference on Memory-constrained GPU

no code implementations9 May 2025 Yuxin Zhou, Zheng Li, Jun Zhang, Jue Wang, Yiping Wang, Zhongle Xie, Ke Chen, Lidan Shou

With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices.

Mixture-of-Experts

CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning

no code implementations24 Apr 2025 Jun Zhang, Jue Wang, Huan Li, Zhongle Xie, Ke Chen, Lidan Shou

Active learning (AL) reduces human annotation costs for machine learning systems by strategically selecting the most informative unlabeled data for annotation, but performing it individually may still be insufficient due to restricted data diversity and annotation budget.

Active Learning

NLCTables: A Dataset for Marrying Natural Language Conditions with Table Discovery

1 code implementation22 Apr 2025 Lingxi Cui, Huan Li, Ke Chen, Lidan Shou, Gang Chen

With the growing abundance of repositories containing tabular data, discovering relevant tables for in-depth analysis remains a challenging task.

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

1 code implementation19 Feb 2025 Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Yang You, Guiming Xie, Xuejian Gong, Kunlong Zhou

For a model with 70 billion parameters, LoRAM enables training on a GPU with only 20G HBM, replacing an A100-80G GPU for LoRA training and 15 GPUs for full fine-tuning.

Quantization

Preventing the Popular Item Embedding Based Attack in Federated Recommendations

no code implementations18 Feb 2025 Jun Zhang, Huan Li, Dazhong Rong, Yan Zhao, Ke Chen, Lidan Shou

The PIECKUEA further enhances the robustness of the attack by using a user embedding approximation module, which approximates private user embeddings using mined popular items.

Recommendation Systems

A Comprehensive Study of Shapley Value in Data Analytics

2 code implementations2 Dec 2024 Hong Lin, Shixin Wan, Zhongle Xie, Ke Chen, Meihui Zhang, Lidan Shou, Gang Chen

Over the recent years, Shapley value (SV), a solution concept from cooperative game theory, has found numerous applications in data analytics (DA).

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

no code implementations16 Oct 2024 Yongqin Xu, Huan Li, Ke Chen, Lidan Shou

This study presents the Knowledge-Compliant Matching Framework (KcMF), an LLM-based approach that addresses these issues without the need for domain-specific fine-tuning.

Data Integration

FL-GUARD: A Holistic Framework for Run-Time Detection and Recovery of Negative Federated Learning

no code implementations7 Mar 2024 Hong Lin, Lidan Shou, Ke Chen, Gang Chen, Sai Wu

Federated learning (FL) is a promising approach for learning a model from data distributed on massive clients without exposing data privacy.

Federated Learning

CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition

1 code implementation15 Dec 2023 Cheng Peng, Ke Chen, Lidan Shou, Gang Chen

The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data.

Emotion Recognition Specificity

Effective Slot Filling via Weakly-Supervised Dual-Model Learning

1 code implementation AAAI 2021 Jue Wang, Ke Chen, Lidan Shou, Sai Wu, Gang Chen

By using some particular weakly-labeled data, namely the plain phrases included in sentences, we propose a weaklysupervised slot filling approach.

slot-filling Slot Filling +1

LINDT: Tackling Negative Federated Learning with Local Adaptation

no code implementations23 Nov 2020 Hong Lin, Lidan Shou, Ke Chen, Gang Chen, Sai Wu

On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model.

Federated Learning

An Experimental Analysis of Indoor Spatial Queries: Modeling, Indexing, and Processing

1 code implementation8 Oct 2020 Tiantian Liu, Huan Li, Hua Lu, Muhammad Aamir Cheema, Lidan Shou

Indoor location-based services (LBS), such as POI search and routing, are often built on top of typical indoor spatial queries.

Databases Data Structures and Algorithms

Pyramid: A Layered Model for Nested Named Entity Recognition

2 code implementations ACL 2020 Jue Wang, Lidan Shou, Ke Chen, Gang Chen

Its hidden state at layer l represents an l-gram in the input text, which is labeled only if its corresponding text region represents a complete entity mention.

named-entity-recognition Named Entity Recognition +2

Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction

no code implementations8 Apr 2019 Jue Wang, Ke Chen, Lidan Shou, Sai Wu, Sharad Mehrotra

In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself.

Clustering Few-Shot Learning +1

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