Search Results for author: Fuyuan Lyu

Found 19 papers, 8 papers with code

Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models

1 code implementation24 Nov 2024 Kexin Zhang, Fuyuan Lyu, Xing Tang, Dugang Liu, Chen Ma, Kaize Ding, Xiuqiang He, Xue Liu

To bridge this gap, we introduce OptFusion, a method that automates the learning of fusion, encompassing both the connection learning and the operation selection.

Click-Through Rate Prediction Neural Architecture Search +1

Comprehending Knowledge Graphs with Large Language Models for Recommender Systems

no code implementations16 Oct 2024 Ziqiang Cui, Yunpeng Weng, Xing Tang, Fuyuan Lyu, Dugang Liu, Xiuqiang He, Chen Ma

Furthermore, to utilize the global information of the KG, we construct an item-item graph using these semantic embeddings, which can directly capture higher-order associations between items.

Knowledge-Aware Recommendation Knowledge Graphs +2

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

no code implementations7 Oct 2024 Qiyuan Zhang, YuFei Wang, Tiezheng Yu, Yuxin Jiang, Chuhan Wu, Liangyou Li, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Fuyuan Lyu, Chen Ma

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing the text generation quality in a wide range of tasks.

Instruction Following Text Generation

OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction

no code implementations16 Aug 2024 Yunpeng Weng, Xing Tang, Zhenhao Xu, Fuyuan Lyu, Dugang Liu, Zexu Sun, Xiuqiang He

In this paper, we propose a novel optimal distribution selection model OptDist for CLTV prediction, which utilizes an adaptive optimal sub-distribution selection mechanism to improve the accuracy of complex distribution modeling.

Marketing Value prediction

Collaborative Performance Prediction for Large Language Models

1 code implementation1 Jul 2024 Qiyuan Zhang, Fuyuan Lyu, Xue Liu, Chen Ma

The pioneering scaling law on downstream works demonstrated intrinsic similarities within model families and utilized such similarities for performance prediction.

Touch the Core: Exploring Task Dependence Among Hybrid Targets for Recommendation

1 code implementation26 Mar 2024 Xing Tang, Yang Qiao, Fuyuan Lyu, Dugang Liu, Xiuqiang He

In this paper, we study the MTL problem with hybrid targets for the first time and propose the model named Hybrid Targets Learning Network (HTLNet) to explore task dependence and enhance optimization.

Multi-Task Learning Recommendation Systems

ICE-SEARCH: A Language Model-Driven Feature Selection Approach

no code implementations28 Feb 2024 Tianze Yang, Tianyi Yang, Fuyuan Lyu, Shaoshan Liu, Xue, Liu

This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, which is among the first works that melds large language models (LLMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications.

Diabetes Prediction Disease Prediction +5

Towards Automated Negative Sampling in Implicit Recommendation

no code implementations6 Nov 2023 Fuyuan Lyu, Yaochen Hu, Xing Tang, Yingxue Zhang, Ruiming Tang, Xue Liu

Hence, we propose a hypothesis that the negative sampler should align with the capacity of the recommendation models as well as the statistics of the datasets to achieve optimal performance.

AutoML

Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

1 code implementation NeurIPS 2023 Fuyuan Lyu, Xing Tang, Dugang Liu, Chen Ma, Weihong Luo, Liang Chen, Xiuqiang He, Xue Liu

In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks.

OptMSM: Optimizing Multi-Scenario Modeling for Click-Through Rate Prediction

no code implementations23 Jun 2023 Xing Tang, Yang Qiao, Yuwen Fu, Fuyuan Lyu, Dugang Liu, Xiuqiang He

Existing approaches for multi-scenario CTR prediction generally consist of two main modules: i) a scenario-aware learning module that learns a set of multi-functional representations with scenario-shared and scenario-specific information from input features, and ii) a scenario-specific prediction module that serves each scenario based on these representations.

Click-Through Rate Prediction Disentanglement

Explicit Feature Interaction-aware Uplift Network for Online Marketing

no code implementations1 Jun 2023 Dugang Liu, Xing Tang, Han Gao, Fuyuan Lyu, Xiuqiang He

Our EFIN includes four customized modules: 1) a feature encoding module encodes not only the user and contextual features, but also the treatment features; 2) a self-interaction module aims to accurately model the user's natural response with all but the treatment features; 3) a treatment-aware interaction module accurately models the degree to which a particular treatment motivates a user through interactions between the treatment features and other features, i. e., ITE; and 4) an intervention constraint module is used to balance the ITE distribution of users between the control and treatment groups so that the model would still achieve a accurate uplift ranking on data collected from a non-random intervention marketing scenario.

Marketing

Optimizing Feature Set for Click-Through Rate Prediction

1 code implementation26 Jan 2023 Fuyuan Lyu, Xing Tang, Dugang Liu, Liang Chen, Xiuqiang He, Xue Liu

Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates.

Click-Through Rate Prediction

Result Diversification in Search and Recommendation: A Survey

1 code implementation29 Dec 2022 Haolun Wu, Yansen Zhang, Chen Ma, Fuyuan Lyu, Bowei He, Bhaskar Mitra, Xue Liu

Diversifying return results is an important research topic in retrieval systems in order to satisfy both the various interests of customers and the equal market exposure of providers.

Diversity Retrieval +1

OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction

1 code implementation9 Aug 2022 Fuyuan Lyu, Xing Tang, Hong Zhu, Huifeng Guo, Yingxue Zhang, Ruiming Tang, Xue Liu

To this end, we propose an optimal embedding table learning framework OptEmbed, which provides a practical and general method to find an optimal embedding table for various base CTR models.

Click-Through Rate Prediction Recommendation Systems

Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey

no code implementations20 Mar 2022 Yuecai Zhu, Fuyuan Lyu, Chengming Hu, Xi Chen, Xue Liu

However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them.

Decoder Graph Learning +1

Cross-filter compression for CNN inference acceleration

no code implementations18 May 2020 Fuyuan Lyu, Shien Zhu, Weichen Liu

However, these filter-wise quantification methods exist a natural upper limit, caused by the size of the kernel.

Image Classification

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