標(biāo)題: Titlebook: Database Systems for Advanced Applications; 28th International C Xin Wang,Maria Luisa Sapino,Hongzhi Yin Conference proceedings 2023 The Ed [打印本頁] 作者: 使入伍 時(shí)間: 2025-3-21 17:12
書目名稱Database Systems for Advanced Applications影響因子(影響力)
書目名稱Database Systems for Advanced Applications影響因子(影響力)學(xué)科排名
書目名稱Database Systems for Advanced Applications網(wǎng)絡(luò)公開度
書目名稱Database Systems for Advanced Applications網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Database Systems for Advanced Applications被引頻次
書目名稱Database Systems for Advanced Applications被引頻次學(xué)科排名
書目名稱Database Systems for Advanced Applications年度引用
書目名稱Database Systems for Advanced Applications年度引用學(xué)科排名
書目名稱Database Systems for Advanced Applications讀者反饋
書目名稱Database Systems for Advanced Applications讀者反饋學(xué)科排名
作者: 信徒 時(shí)間: 2025-3-21 23:08
0302-9743 D consortium papers are included. The conference presents papers on subjects such as model, graph, learning, performance, knowledge, time, recommendation, representation, attention, prediction, and network..978-3-031-30671-6978-3-031-30672-3Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: 載貨清單 時(shí)間: 2025-3-22 04:25 作者: 壓迫 時(shí)間: 2025-3-22 05:08
Who Is That Man? Lad Trouble in ,, and d information aggregation module to accurately learn item-level relation features from a knowledge graph. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our KRec-C2 model over existing state-of-the-art methods.作者: 極端的正確性 時(shí)間: 2025-3-22 09:04
KRec-C2: A Knowledge Graph Enhanced Recommendation with?Context Awareness and?Contrastive Learningd information aggregation module to accurately learn item-level relation features from a knowledge graph. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our KRec-C2 model over existing state-of-the-art methods.作者: 都相信我的話 時(shí)間: 2025-3-22 16:20 作者: 都相信我的話 時(shí)間: 2025-3-22 18:49 作者: 墻壁 時(shí)間: 2025-3-23 01:14 作者: Culmination 時(shí)間: 2025-3-23 04:19
Thompson Sampling with?Time-Varying Reward for?Contextual Banditsalgorithm. Extensive empirical experiments on two real-world datasets show that our proposed algorithm outperforms state-of-the-art time-varying bandit algorithms. Furthermore, the designed reward mechanism can be flexibly configured to other bandit algorithms to improve them.作者: 善于 時(shí)間: 2025-3-23 09:08
Cold-Start Based Multi-scenario Ranking Model for?Click-Through Rate Predictionn attention mechanism; and 2) User Representation Memory Network (URMN), which benefits cold-start users from users with rich behaviors through a memory read and write mechanism. CSMN seamlessly integrates both components in an end-to-end learning framework. Extensive experiments on real-world offli作者: 臆斷 時(shí)間: 2025-3-23 11:53
Query2Trip: Dual-Debiased Learning for?Neural Trip Recommendationhe query provided by a user, Query2Trip designs a debiased adversarial learning module by conditional guidance to alleviate this selection bias from positives (visited). The latter happens as unvisited is not equivalent to negative. Query2Trip devises a debiased contrastive learning module by negati作者: 潰爛 時(shí)間: 2025-3-23 16:06
A New Reconstruction Attack: User Latent Vector Leakage in?Federated Recommendationgenerator is designed to take random vectors as inputs and outputs generated latent vectors. The generator is trained by the distance between the real victim’s gradient updates and the generated gradient updates. We explain that the generator will successfully learn the target latent vector distribu作者: ROOF 時(shí)間: 2025-3-23 21:13 作者: 跑過 時(shí)間: 2025-3-23 22:34 作者: Presbyopia 時(shí)間: 2025-3-24 04:06 作者: 華而不實(shí) 時(shí)間: 2025-3-24 10:28 作者: 撫慰 時(shí)間: 2025-3-24 14:35
Intention-Aware User Modeling for?Personalized News Recommendationerence for personalized next-news recommendations. In addition to modeling users’ reading preferences, our proposed model IPNR can also capture users’ reading intentions and the transitions over intentions for better predicting the next piece of news which may interest the user. Extensive experiment作者: 有權(quán) 時(shí)間: 2025-3-24 15:13
Deep User and?Item Inter-matching Network for?CTR Prediction by users’ historical behaviors, respectively. Then the User-to-User Network (UUN) is designed to mine user interests through the relationship between target users and similar users after representing the target users more accurately and richly. The experimental results show that the DUIIN model pro作者: ineptitude 時(shí)間: 2025-3-24 21:50
Towards Lightweight Cross-Domain Sequential Recommendation via?External Attention-Enhanced Graph Coniently to capture the collaborative filtering signals of the items from both domains. To further alleviate the framework structure and aggregate the user-specific sequential pattern, we devise a novel dual-channel External Attention (EA) component, which calculates the correlation among all items vi作者: 下船 時(shí)間: 2025-3-24 23:16 作者: Euthyroid 時(shí)間: 2025-3-25 05:38 作者: 薄荷醇 時(shí)間: 2025-3-25 09:25 作者: narcotic 時(shí)間: 2025-3-25 12:35
Temporal-Aware Multi-behavior Contrastive Recommendationt while preserving multi-behavioral information. In this work, we propose a Temporal-Aware Multi-Behavior Contrastive Learning (TMCL) framework to explore the patterns of multiple behaviors of individuals through temporal information, jointly capture the correlation of users’ preference evolution, a作者: 悶熱 時(shí)間: 2025-3-25 16:54
The Role of Familiarity in Implicit Learningex structure. To satisfy the equilibrium, we propose a corresponding hierarchical tree learning algorithm. Furthermore, for those items with a rare appearance in the training data, on which the learning algorithm would fail, we design a dedicated bandit layer to solve them. Extensive experiments on 作者: Liability 時(shí)間: 2025-3-25 23:33 作者: 價(jià)值在貶值 時(shí)間: 2025-3-26 03:17 作者: 大喘氣 時(shí)間: 2025-3-26 05:47 作者: Banister 時(shí)間: 2025-3-26 08:38
The Constructive Nature of Recollectionhe query provided by a user, Query2Trip designs a debiased adversarial learning module by conditional guidance to alleviate this selection bias from positives (visited). The latter happens as unvisited is not equivalent to negative. Query2Trip devises a debiased contrastive learning module by negati作者: epicondylitis 時(shí)間: 2025-3-26 16:19 作者: TAG 時(shí)間: 2025-3-26 19:11
Michael‘Malisoff,Frédéric Mazenc we first extract high-order collaborative user/item representations with GNNs. Next, we impose a discrepancy regularization term to augment the self-discrimination of the user/item representations. As for the structural view, we initially utilize GNNs to extract high-order features. Next, we utiliz作者: Forehead-Lift 時(shí)間: 2025-3-26 20:56 作者: Compassionate 時(shí)間: 2025-3-27 01:25 作者: foreign 時(shí)間: 2025-3-27 08:56 作者: 不開心 時(shí)間: 2025-3-27 10:20 作者: 色情 時(shí)間: 2025-3-27 14:37
Palgrave Studies in the History of Childhood by users’ historical behaviors, respectively. Then the User-to-User Network (UUN) is designed to mine user interests through the relationship between target users and similar users after representing the target users more accurately and richly. The experimental results show that the DUIIN model pro作者: Triglyceride 時(shí)間: 2025-3-27 20:33
https://doi.org/10.1007/978-3-642-61667-9iently to capture the collaborative filtering signals of the items from both domains. To further alleviate the framework structure and aggregate the user-specific sequential pattern, we devise a novel dual-channel External Attention (EA) component, which calculates the correlation among all items vi作者: archaeology 時(shí)間: 2025-3-28 00:43
On a Problem Transmitted by Doug McIlroyublic datasets demonstrate that the proposed method achieves remarkable training speedups over LightGCN and substantially outperforms the state-of-the-art GCN-based CF models. Our method also shows a great improvement in long-tail recommendation.作者: 預(yù)知 時(shí)間: 2025-3-28 03:32 作者: 愛社交 時(shí)間: 2025-3-28 07:14
Constructive Type Theory—An Introductione representations. Next, we obtain the final node representations through the signal integration strategy. Finally, the model is trained by the joint learning paradigm. The experimental results on three public datasets are better than the baseline models.作者: Culpable 時(shí)間: 2025-3-28 14:02 作者: 收集 時(shí)間: 2025-3-28 15:52
KRec-C2: A Knowledge Graph Enhanced Recommendation with?Context Awareness and?Contrastive Learningpplications: high-quality knowledge graphs and modeling user-item relationships. However, existing methods try to solve the above challenges by adopting unified relational rules and simple node aggregation, which cannot cope with complex structured graph data. In this paper, we propose a .nowledge g作者: Mortar 時(shí)間: 2025-3-28 21:15
HIT: Learning a?Hierarchical Tree-Based Model with?Variable-Length Layers for?Recommendation Systemsng structure is a practical solution to retrieve and recommend the most relevant items within a limited response time. The existing approaches that adopted embedding or tree-based index structures cannot handle the long-tail phenomenon. To address this issue, we propose a .erarchical .ree-based mode作者: 強(qiáng)所 時(shí)間: 2025-3-29 00:13 作者: 咯咯笑 時(shí)間: 2025-3-29 04:07
Thompson Sampling with?Time-Varying Reward for?Contextual Banditsorithms utilize a fixed reward mechanism, which makes it difficult to accurately capture the preference changes of users in non-stationary environments, thus affecting recommendation performance. In this paper, we formalize the online recommendation task as a contextual bandit problem and propose a 作者: 食草 時(shí)間: 2025-3-29 07:16 作者: 拾落穗 時(shí)間: 2025-3-29 11:35
Query2Trip: Dual-Debiased Learning for?Neural Trip Recommendation-specific query. Recent neural TripRec methods with sequence-to-sequence models have achieved remarkable performance. However, alongside the exposure bias in general recommender systems, the selection bias caused by the lack of explicit feedback (e.g., ratings) from the trip data exacerbates the ten作者: Cubicle 時(shí)間: 2025-3-29 18:00
A New Reconstruction Attack: User Latent Vector Leakage in?Federated Recommendationre kept on its local device and thus are private to others. However, keeping the training data locally can not ensure the user’s privacy is compromised. In this paper, we show that the existing FR is vulnerable to a new reconstruction attack in which the attacker leverages the semi-trusted FR server作者: affluent 時(shí)間: 2025-3-29 20:27
Dual-View Self-supervised Co-training for?Knowledge Graph Recommendationly improve model performance, has attracted considerable interest. Currently, KGR community has focused on designing Graph Neural Networks (GNNs)-based end-to-end KGR models. Unfortunately, existing GNNs-based KGR models are focused on extracting high-order attributes (knowledge) but suffer from res作者: 急急忙忙 時(shí)間: 2025-3-30 01:20 作者: fulcrum 時(shí)間: 2025-3-30 04:24 作者: 稱贊 時(shí)間: 2025-3-30 11:23
Disentangled Contrastive Learning for?Cross-Domain Recommendationecent research reveals that identifying domain-invariant and domain-specific features behind interactions aids in generating comprehensive user and item representations. However, we argue that existing methods fail to separate domain-invariant and domain-specific representations from each other, whi作者: 硬化 時(shí)間: 2025-3-30 15:08 作者: MUMP 時(shí)間: 2025-3-30 18:46
Deep User and?Item Inter-matching Network for?CTR Predictionser interest. There are two main problems with previous works: (1) When most previous works mined interests from users’ historical behaviors, they only focus on implicit or explicit interests. (2) When most previous works mined user interests through the relationship between target users and similar作者: condone 時(shí)間: 2025-3-30 21:40 作者: LEER 時(shí)間: 2025-3-31 03:29 作者: SCORE 時(shí)間: 2025-3-31 05:21 作者: Suppository 時(shí)間: 2025-3-31 10:36 作者: 星球的光亮度 時(shí)間: 2025-3-31 15:46
Temporal-Aware Multi-behavior Contrastive Recommendation has attracted increasing attention recently. However, most existing multi-behavior recommendations only focus on the behavioral interaction itself, attempting to extract user preferences merely by modeling behaviors, while ignoring the properties of the interaction (e.g., the temporal information).作者: 認(rèn)識(shí) 時(shí)間: 2025-3-31 20:16 作者: patriot 時(shí)間: 2025-3-31 22:39
Who Is That Man? Lad Trouble in ,, and pplications: high-quality knowledge graphs and modeling user-item relationships. However, existing methods try to solve the above challenges by adopting unified relational rules and simple node aggregation, which cannot cope with complex structured graph data. In this paper, we propose a .nowledge g作者: 良心 時(shí)間: 2025-4-1 01:56
The Role of Familiarity in Implicit Learningng structure is a practical solution to retrieve and recommend the most relevant items within a limited response time. The existing approaches that adopted embedding or tree-based index structures cannot handle the long-tail phenomenon. To address this issue, we propose a .erarchical .ree-based mode作者: DEMUR 時(shí)間: 2025-4-1 09:36 作者: 帶子 時(shí)間: 2025-4-1 14:04
