A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Contrastive Cross-domain Recommendation in Matching
[article]
2022
arXiv
pre-print
contrastive learning (inter-CL) tasks for better representation learning and knowledge transfer. ...
Specifically, we build a huge diversified preference network to capture multiple information reflecting user diverse interests, and design an intra-domain contrastive learning (intra-CL) and three inter-domain ...
To strengthen the cross-domain knowledge transfer, we design the intra-domain contrastive learning (intra-CL) and inter-domain contrastive learning (inter-CL) in CCDR. ...
arXiv:2112.00999v2
fatcat:tmwwe3fo2zeknpevctteukgyx4
Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach
[article]
2023
arXiv
pre-print
This pioneering framework leverages attention mechanisms to discern information from both inter and intra-behaviors while employing a multi-task Hierarchical Bayesian Personalized Ranking (HBPR) for optimization ...
While recommender systems have significantly benefited from implicit feedback, they have often missed the nuances of multi-behavior interactions between users and items. ...
Conclusion In this paper, we devised two new graph attention-based frameworks called HMGN-intra and HMGN-inter for multi-behavior recommender systems. ...
arXiv:2309.03169v2
fatcat:dwbyz3eemfcxvbbkemyd65abfi
DRepMRec: A Dual Representation Learning Framework for Multimodal Recommendation
[article]
2024
arXiv
pre-print
and Behavior-Modal Alignment (BMA) for misalignment problem. ...
To address these challenges, in this paper, we propose a novel Dual Representation learning framework for Multimodal Recommendation called DRepMRec, which introduce separate dual lines for coupling problem ...
Inter-Alignment, in contrast to Intra-Alignment, focuses on aligning the behavioral and modality representations of users and items separately. ...
arXiv:2404.11119v1
fatcat:nhld3vdjjrbwjoydqmmfblqb54
MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
[article]
2022
arXiv
pre-print
dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). ...
CTR prediction is essential for modern recommender systems. ...
A click behavior sequence with multiple user interests. inter-item and intra-item correlations together. ...
arXiv:2111.15068v2
fatcat:blu7sutjcze7tn5xb7mhkm46za
Heterogeneous Information Crossing on Graphs for Session-based Recommender Systems
[article]
2022
arXiv
pre-print
(ii) HICG-CL further significantly improves the recommendation performance of HICG by the proposed contrastive learning module. ...
However, most existing studies are not well-designed for modeling heterogeneous user behaviors and capturing the relationships between them in practical scenarios. ...
ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China (No. 62172362), the Leading Expert of "Ten Thousands Talent Program" of Zhejiang Province (No.2021R52001), and ...
arXiv:2210.12940v1
fatcat:ipz4hw2bv5dgnmikjs4cbybqx4
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation
2022
Proceedings of the ACM Web Conference 2022
Empirical studies validate that Re4 helps to learn learning distinct and effective multi-interest representations. CCS CONCEPTS • Information systems → Recommender systems. ...
Since users' interests naturally exhibit multiple aspects, it is of increasing interest to develop multi-interest frameworks for recommendation, rather than represent each user with an overall embedding ...
LR19F020006), and Project by Shanghai AI Laboratory (No. P22KS00111). ...
doi:10.1145/3485447.3512094
fatcat:yfoyeulr3ffw7fppdzmljdbhnm
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation
[article]
2024
arXiv
pre-print
Empirical studies validate that Re4 helps to learn learning distinct and effective multi-interest representations. ...
Since users' interests naturally exhibit multiple aspects, it is of increasing interest to develop multi-interest frameworks for recommendation, rather than represent each user with an overall embedding ...
We have the following findings: CI K-means++ User Interests CM Metric Base Re4 Base Re4 K-means INTER INTRA 35.10 37.14 35.80 38.65 20.32 23.03 26.91 32.98 FCM INTER INTRA 36.47 38.14 37.84 39.48 84.50 ...
arXiv:2208.08011v2
fatcat:cixpuj5vlrawthtb3ghrilyctm
M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
[article]
2020
arXiv
pre-print
M2GRL chooses a multi-task learning paradigm to learn intra-view representations and cross-view relations jointly. ...
Combining graph representation learning with multi-view data (side information) for recommendation is a trend in industry. ...
In Section 2, we introduce the related works, including graph representation learning for recommendation and recommendation with multi-view data. ...
arXiv:2005.10110v1
fatcat:2sbn4z6w25cangokcx3uy7d54m
A Multi-view Graph Contrastive Learning Framework for Cross-Domain Sequential Recommendation
2023
Proceedings of the 17th ACM Conference on Recommender Systems
Specifically, we adopt the contrastive mechanism in an intra-domain item representation view and an inter-domain user preference view. ...
To address these issues, in this paper we propose a generic framework named multi-view graph contrastive learning (MGCL). ...
ACKNOWLEDGMENTS We thank the support of National Natural Science Foundation of China No. 62172283, No. 61836005 and No. 62272315. ...
doi:10.1145/3604915.3608785
fatcat:wztgnd4ezvck3lfpxji7ssdjgi
Coupling learning of complex interactions
2015
Information Processing & Management
, coupled recommender algorithms and coupled behavior analysis for groups. ...
Coupling learning has great potential for building a deep understanding of the essence of business problems and handling challenges that have not been addressed well by existing learning theories and tools ...
Such relationships are embodied through intra-behavior couplings for one actor and inter-behavior couplings between multiple actors. ...
doi:10.1016/j.ipm.2014.08.007
fatcat:yrwlzqu4mrg3xkumjlcbrhhzuq
Multi-view Multi-aspect Neural Networks for Next-basket Recommendation
2023
Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
behaviors, leading to suboptimal user interest learning. ...
To address these limitations, we propose a novel solution named Multi-view Multi-aspect Neural Recommendation (MMNR) for NBR, which first normalizes the interactions from both the user-side and item-side ...
We would like to thank the anonymous reviewers for their valuable comments. ...
doi:10.1145/3539618.3591738
fatcat:dw7mtg4gmrbdrbrexqx447mzcm
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation
[article]
2021
arXiv
pre-print
In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic ...
The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space. ...
Acknowledgments We thank the anonymous reviewers for their constructive feedback and comments. ...
arXiv:2110.03996v1
fatcat:qp5o3osmofgttnnas7r6b6lowu
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation
2021
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic ...
The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space. ...
Acknowledgments We thank the anonymous reviewers for their constructive feedback and comments. ...
doi:10.1609/aaai.v35i5.16534
fatcat:655b5cvipfdspcb4qtaj5uigeu
A Comprehensive Survey on Self-Supervised Learning for Recommendation
[article]
2024
arXiv
pre-print
For each domain, we elaborate on different self-supervised learning paradigms, namely contrastive learning, generative learning, and adversarial learning, so as to present technical details of how SSL ...
Deep learning techniques, such as RNNs, GNNs, and Transformer architectures, have significantly propelled the advancement of recommender systems by enhancing their comprehension of user behaviors and preferences ...
IICL uses intra-and inter-behavior contrastive learning, where even-layered embeddings are positive pairs in intra-behavior CL, and different behaviors for the same user are positive pairs in inter-behavior ...
arXiv:2404.03354v2
fatcat:xu37ncxb45cd7jwahaqigpe4bi
Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
[article]
2023
arXiv
pre-print
However, this approach lacks a global perspective, failing to account for users' hidden motivations and behaviors beyond semantic information. ...
Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. ...
It is also partially supported by the Initiative on Recommendation Program for Young Researchers and Woman Researchers, Information Technology Center, The University of Tokyo. ...
arXiv:2307.06576v4
fatcat:fpjdcmwltzcvbh6gqkgoi7e46m
« Previous
Showing results 1 — 15 out of 22,600 results