Adamerging: Adaptive model merging for multi-task learning

E Yang, Z Wang, L Shen, S Liu, G Guo, X Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Multi-task learning (MTL) aims to empower a model to tackle multiple tasks simultaneously.
A recent development known as task arithmetic has revealed that several models, each fine …

Contrastive Learning and Deep Fusion Recommendation Model based on ID Features

B Li, X Wang, J Dong, Y Hou, B Yang - IEEE Access, 2024 - ieeexplore.ieee.org
In recent years, the application of deep learning in recommendation systems has achieved
breakthrough progress. Neural networks have captured the complex nonlinear relationships …

Representation Surgery for Multi-Task Model Merging

E Yang, L Shen, Z Wang, G Guo, X Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Multi-task learning (MTL) compresses the information from multiple tasks into a unified
backbone to improve computational efficiency and generalization. Recent work directly …

Deconfounding User Preference in Recommendation Systems through Implicit and Explicit Feedback

Y Liang, E Yang, G Guo, W Cai, L Jiang… - ACM Transactions on …, 2024 - dl.acm.org
Recommender systems are influenced by many confounding factors (ie, confounders) which
result in various biases (eg, popularity biases) and inaccurate user preference. Existing …

Collaborative Knowledge Fusion: A Novel Approach for Multi-task Recommender Systems via LLMs

C Zhao, X Su, M He, H Zhao, J Fan, X Li - arxiv preprint arxiv:2410.20642, 2024 - arxiv.org
Owing to the impressive general intelligence of large language models (LLMs), there has
been a growing trend to integrate them into recommender systems to gain a more profound …

LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System

F Li, Y Li, Y Liu, C Zhou, Y Wang, X Deng… - arxiv preprint arxiv …, 2024 - arxiv.org
Display advertising provides significant value to advertisers, publishers, and users.
Traditional display advertising systems utilize a multi-stage architecture consisting of …

Feature Interaction Fusion Self-Distillation Network For CTR Prediction

L Sang, Q Ru, H Li, Y Zhang, Q Cao, X Wu - arxiv preprint arxiv …, 2024 - arxiv.org
Click-Through Rate (CTR) prediction plays a vital role in recommender systems, online
advertising, and search engines. Most of the current approaches model feature interactions …

NeSHFS: Neighborhood Search with Heuristic-based Feature Selection for Click-Through Rate Prediction

D Aksu, IH Toroslu, H Davulcu - arxiv preprint arxiv:2409.08703, 2024 - arxiv.org
Click-through-rate (CTR) prediction plays an important role in online advertising and ad
recommender systems. In the past decade, maximizing CTR has been the main focus of …