標題: Titlebook: Database Systems for Advanced Applications; 29th International C Makoto Onizuka,Jae-Gil Lee,Kejing Lu Conference proceedings 2024 The Edito [打印本頁] 作者: 大破壞 時間: 2025-3-21 19:33
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)學科排名
書目名稱Database Systems for Advanced Applications網(wǎng)絡公開度
書目名稱Database Systems for Advanced Applications網(wǎng)絡公開度學科排名
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讀者反饋學科排名
作者: 消極詞匯 時間: 2025-3-21 23:12 作者: 懦夫 時間: 2025-3-22 02:17
Higher-Order Graph Contrastive Learning for?Recommendationom the original graph to enhance supervisory signals. Specifically, we construct two contrasting views: higher-order and general views. In the higher-order view, we devise a high-order symmetric contrastive scheme to better explore higher-order dependencies. For the general view, the objective is to作者: 植物群 時間: 2025-3-22 06:53 作者: Individual 時間: 2025-3-22 11:44 作者: 轉(zhuǎn)折點 時間: 2025-3-22 13:39
Multi-level Contrastive Learning on?Weak Social Networks for?Information Diffusion Predictionn.?To facilitate user representation learning under sparse labels?and insufficient features, we further propose self-supervised training specifically tailored for social networks with weak information.?In the second stage, the cascade representations are learned using?the multi-head self-attention n作者: 轉(zhuǎn)折點 時間: 2025-3-22 17:17
BiasRec: A General Bias-Aware Social Recommendation Model initially constructs a bias matrix for each user and item, calculates bias scores, and removes them from the raw rating data. Subsequently, the debiased data is fed into a GNN to learn users’ genuine preferences. Last, it reasonably combines biases?and preferences to make predictions. We performed 作者: 生存環(huán)境 時間: 2025-3-23 01:01 作者: 激怒某人 時間: 2025-3-23 03:12 作者: 利用 時間: 2025-3-23 09:09
Learning Social Graph for?Inactive User Recommendationring model training,?which improves the construction of new edges for inactive users. Extensive experiments on real-world datasets demonstrate that LSIR achieves significant improvements of up to 129.58% on NDCG in inactive?user recommendation. Our code is available at?..作者: Notorious 時間: 2025-3-23 10:47
MANE: A Multi-cascade Adversarial Network Embedding Model for?Anchor Link Predictions for correspondence matching. Extensive experiments on real-world social network datasets demonstrate that our method can achieve the expected performance, especially in improving the top-1 precision and recall.作者: inclusive 時間: 2025-3-23 14:58 作者: Bucket 時間: 2025-3-23 20:27
GPSR: Graph Prompt for?Session-Based Recommendation. Specifically, we first study the item transition pattern by constructing session graphs, based on which the GNN?model is pretrained. Then, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF), for adapting?the pretrained GNN model to the downstream session-based re作者: 鋪子 時間: 2025-3-24 01:28 作者: INERT 時間: 2025-3-24 03:07
Global Route Planning for?Large-Scale Requests on Traffic-Aware Road Networkgroup them together. In this way, only the conflicts within each group need to be resolved in a local area, so the efficiency is improved. Additionally, several alternative paths are calculated and the global optimal routes are found in finite iterations. Extensive experiments conducted on real-worl作者: 打火石 時間: 2025-3-24 10:05 作者: 冒煙 時間: 2025-3-24 11:59 作者: 打包 時間: 2025-3-24 17:51 作者: 聯(lián)想 時間: 2025-3-24 19:09
,Verzweigter Stromübertritt in die Erde,. Specifically, We use LightGCN to learn user and item embeddings,?and then we combine multi-task learning with contrastive learning?to explicitly exploit behavioral dependence in embeddings learning?and capture differences between embeddings. We conduct comprehensive experiments on two real-world d作者: Emg827 時間: 2025-3-25 00:01
https://doi.org/10.1007/978-3-662-41795-9ified heterogeneous graph, creating the heterogeneous view. We?also construct the social relation enhanced view by resampling?the user-item interaction graph. In the learning process, we leverage meta-path based graph learning and graph diffusion with attention?to obtain multi-view embeddings for us作者: miracle 時間: 2025-3-25 04:12 作者: 轉(zhuǎn)折點 時間: 2025-3-25 09:54
https://doi.org/10.1007/978-3-642-86621-0on encoder to encode each propagation. . then employs a propagation transformer module to make every propagation embedding interact and obtain the importance score of each propagation. . achieves the best performance on three real-world datasets. Further experiments show the propagation transformer 作者: accomplishment 時間: 2025-3-25 12:28 作者: 規(guī)范要多 時間: 2025-3-25 16:45
n.?To facilitate user representation learning under sparse labels?and insufficient features, we further propose self-supervised training specifically tailored for social networks with weak information.?In the second stage, the cascade representations are learned using?the multi-head self-attention n作者: 拖網(wǎng) 時間: 2025-3-25 22:55
Positionen zu Arbeit und Technik, initially constructs a bias matrix for each user and item, calculates bias scores, and removes them from the raw rating data. Subsequently, the debiased data is fed into a GNN to learn users’ genuine preferences. Last, it reasonably combines biases?and preferences to make predictions. We performed 作者: Glower 時間: 2025-3-26 01:51
Handbuch der allgemeinen Pathologieferent classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling?label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show?the e作者: left-ventricle 時間: 2025-3-26 08:17
,The Era of the Pioneers (1882 – 1898),ctive approach called RAP, which employs a two-stage learning framework. Specifically, in the first stage, we construct a weighted bipartite graph to model interaction’s confidence-score, which effectively blocks the spread of noise information in GNN. Furthermore, in?the second stage, RAP introduce作者: incredulity 時間: 2025-3-26 11:39
https://doi.org/10.1007/978-3-642-75757-0ring model training,?which improves the construction of new edges for inactive users. Extensive experiments on real-world datasets demonstrate that LSIR achieves significant improvements of up to 129.58% on NDCG in inactive?user recommendation. Our code is available at?..作者: 直覺好 時間: 2025-3-26 12:48 作者: 重力 時間: 2025-3-26 18:27 作者: Obvious 時間: 2025-3-26 22:59 作者: –DOX 時間: 2025-3-27 05:05 作者: 擔心 時間: 2025-3-27 07:32 作者: licence 時間: 2025-3-27 10:36
https://doi.org/10.1007/978-3-322-92904-4ormer-based autoencoder. Treating each node as a sequence?and its neighborhood as tokens in the sequence, this autoencoder captures both local and global information. We incorporate cosine positional encoding and masking strategy to obtain more informative node representations and leverage reconstru作者: 波動 時間: 2025-3-27 17:14
Environmental Quality of the Po River Delta,?that are less effective for contrastive learning. Inspired?by counterfactual augmentation, we instead sample competitive negative node relations by creating virtual nodes that inherit (in?a self-supervised fashion) .,?while altering ., creating contrasting pairs that lie closer to the boundary and 作者: armistice 時間: 2025-3-27 17:56
Conference proceedings 2024 DASFAA 2024, held in Gifu, Japan, in July 2024...The total of 147 full papers, along with 85 short papers, presented together in this seven-volume set was carefully reviewed and selected from 722 submissions...Additionally, 14 industrial papers, 18 demo papers and 6 tutorials are included...The con作者: Constant 時間: 2025-3-27 22:56 作者: 鳴叫 時間: 2025-3-28 06:10 作者: 四目在模仿 時間: 2025-3-28 10:07 作者: 不舒服 時間: 2025-3-28 10:36 作者: 性上癮 時間: 2025-3-28 16:13 作者: STELL 時間: 2025-3-28 22:24
Social Relation Enhanced Heterogeneous Graph Contrastive Learning for?Recommendationsers’ interests. These systems have showcased their significance in diverse scenarios, with particular prominence observed in applications related to social networks. Heterogeneous Graph Neural Networks (HGNNs) have shown success in recommendation tasks by embedding rich semantics from different rel作者: Missile 時間: 2025-3-29 00:21
Higher-Order Graph Contrastive Learning for?Recommendation-item). However, the graph-based model struggles to mitigate the impact of data sparsity. Recent studies have attempted to tackle this problem by utilizing contrastive learning. Nevertheless, most of these methods rely on augmenting the data based on the original graph to construct contrastive views作者: endure 時間: 2025-3-29 04:14
: Evaluating the?Importance of?Propagations during Fake News Spread content, which may fail to determine fake news with disguised content. Graph-based models adopt extra media to construct graphs, which provide social context to identify fake news. However, existing graph-based models treat each media equally, neglecting the echo chamber phenomenon where most media作者: output 時間: 2025-3-29 07:15 作者: 健壯 時間: 2025-3-29 12:03 作者: placebo-effect 時間: 2025-3-29 18:06 作者: 表皮 時間: 2025-3-29 22:03
Beyond the?Known: Novel Class Discovery for?Open-World Graph Learningnarios, novel classes can emerge?on unlabeled testing nodes. However, little attention has been paid?to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated?by edges, which makes their representations indistinguishable?when applying 作者: 昆蟲 時間: 2025-3-30 00:47 作者: 針葉 時間: 2025-3-30 05:30 作者: 獨特性 時間: 2025-3-30 09:03
MANE: A Multi-cascade Adversarial Network Embedding Model for?Anchor Link Predictionf user-generated content or network structure to create latent representations. These representations are then used to determine user correspondences by mapping users between different network representation spaces. However, most studies still face some challenges such as independent representation 作者: narcotic 時間: 2025-3-30 14:06
uTransfer: Unified Transferability Metric Incorporating Heterogeneous User Data in?Social Networkitional similarity metrics?often yield redundant neighbor information and fail to adequately consider the scarcity of user behaviors, thereby diminishing?their effectiveness. This study endeavors to delve into?the transferability between users by analyzing their heterogeneous data, to identify the m作者: assail 時間: 2025-3-30 20:14
GPSR: Graph Prompt for?Session-Based Recommendationg is typically confined to pure?graph learning tasks, such as node classification or link prediction.?So far, graph prompt learning has been scarcely applied to recommender system, particularly in sequential recommendation. In this paper,?we propose a pioneering approach, Graph Prompt for Session-ba作者: Nomadic 時間: 2025-3-30 23:26 作者: Acclaim 時間: 2025-3-31 02:12 作者: fibroblast 時間: 2025-3-31 05:56
Global Route Planning for?Large-Scale Requests on Traffic-Aware Road Networkdestination queries arrive, these queries themselves will affect road congestion. Therefore, it is necessary to plan different routes in advance for these queries to avoid simultaneous occupation of the same roads, thereby reducing congestion and global travel time. Nevertheless, this is not trivial
