標題: Titlebook: Database Systems for Advanced Applications; 26th International C Christian S. Jensen,Ee-Peng Lim,Chih-Ya Shen Conference proceedings 2021 T [打印本頁] 作者: panache 時間: 2025-3-21 18:26
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(luò)公開度
書目名稱Database Systems for Advanced Applications網(wǎng)絡(luò)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: 單挑 時間: 2025-3-21 20:35
https://doi.org/10.1007/978-1-4757-4854-3nes BPR loss with adaptive margin and similarity loss for the similarities learning. Extensive experiments on three benchmarks show that our model is consistently better than the latest state-of-the-art models.作者: Glutinous 時間: 2025-3-22 03:09 作者: 豪華 時間: 2025-3-22 05:54 作者: heart-murmur 時間: 2025-3-22 11:48 作者: BYRE 時間: 2025-3-22 16:03 作者: BYRE 時間: 2025-3-22 18:37
Mau Mau Inventions and Reinventionsention module, temporal textual information is brought in as a clue to dynamically select friends that are helpful for contextual purchase intentions as an implicit combination. We validate our proposed method on two large subsets of real-world local business dataset Yelp, and our method outperforms作者: Laconic 時間: 2025-3-22 23:41
Mau Mau Inventions and Reinventionsmize their margin. This intense adversarial competition provides increasing learning difficulties and constantly pushes the boundaries of its performance. Extensive experiments on three real-world datasets demonstrate the superiority of our methods over some strong baselines and prove the effectiven作者: 跟隨 時間: 2025-3-23 05:25
https://doi.org/10.1057/978-1-137-53913-7ve subsequence selection strategy to update model. Moreover, to improve the effectiveness and efficiency of online model training, we propose a novel negative sampling strategy based on GAN to generate the most informative negative samples and use Gumble-Softmax to overcome the gradient block proble作者: 壯觀的游行 時間: 2025-3-23 09:14
The State and New Religious Movementsr, referred to as recurrent tree transformer, and utilize this new transformer to generate a unified user interest representation. The last fully connected layer is utilized to model the interaction between this unified representation and item embedding. Comprehensive experiments are conducted on tw作者: CRUC 時間: 2025-3-23 11:46
https://doi.org/10.1057/978-1-137-53913-7aptive weight to emphasize the importance of few-shot users. We simulate the few-shot recommendation problem on three real-world datasets and extensive results show that SANS can outperform the state-of-the-art recommendation algorithms in few-shot recommendation.作者: babble 時間: 2025-3-23 16:31 作者: 許可 時間: 2025-3-23 20:00
Introduction: American Fiction Abroad,s. Moreover, to better capture user preference and model news lifecycle, we present a User Preference LSTM and a News Lifecycle LSTM to extract sequential correlations from news representations and additional features. Extensive experimental results on two real-world news datasets demonstrate the si作者: phlegm 時間: 2025-3-24 01:19
Introduction: American Fiction Abroad,references that can be hit more quickly and accurately. Finally, SeqCR utilizes the policy network to decide whether to recommend or ask. We conduct extensive experiments on two datasets from MovieLens 10M and Yelp in multi-round conversational recommendation scenarios. Empirical results demonstrate作者: CODE 時間: 2025-3-24 03:07
https://doi.org/10.1007/978-3-030-94166-6based neighbors in hyperedge efficiently. Moreover, it can conduct the embedding propagation of high-order correlations explicitly and efficiently in knowledge-aware hypergraph. Finally, we apply the proposed model on three real-world datasets, and the empirical results demonstrate that KHNN can ach作者: Tonometry 時間: 2025-3-24 09:21 作者: Evocative 時間: 2025-3-24 11:09 作者: Culmination 時間: 2025-3-24 18:04 作者: SOBER 時間: 2025-3-24 20:41 作者: lymphoma 時間: 2025-3-25 01:21
Contemporary American Memoirs in Actionork to capture user interest drift across sessions. The other is a Multi-user Identification (MI) module, which draws on the attention mechanism to distinguish behaviors of different users under the same account. To verify the effectiveness of MISS, we construct two data sets with shared account cha作者: arrhythmic 時間: 2025-3-25 04:16
Contemporary American Memoirs in Actionot reflect the realistic scenarios of visualization recommendation completely, a new benchmark for visualization recommendation is designed and constructed by collecting real public datasets. Extensive experiments on both the public benchmark and the new benchmark demonstrate that the VizGRank can b作者: 卵石 時間: 2025-3-25 08:23
Once Upon a Time in Performance Arttem for different users, which may limit the expressiveness and further improvement of the models. In this paper, we propose Deep User Representation Construction Model (DURCM) to construct user presentations in a more effective and robust way. Specially, different from existing item-item methods th作者: triptans 時間: 2025-3-25 14:30
Elizabeth LeCompte and the Wooster Group before convolution to generate attention maps for adaptive feature refinement. Experiments on several public datasets verify the superiority of DiCGAN over several baselines in terms of top-. recommendation. Further more, our experimental results show that when the dataset is more large and sparse,作者: Hamper 時間: 2025-3-25 19:31 作者: rectum 時間: 2025-3-25 19:59
SRecGAN: Pairwise Adversarial Training for Sequential Recommendationmize their margin. This intense adversarial competition provides increasing learning difficulties and constantly pushes the boundaries of its performance. Extensive experiments on three real-world datasets demonstrate the superiority of our methods over some strong baselines and prove the effectiven作者: CUB 時間: 2025-3-26 00:33 作者: LVAD360 時間: 2025-3-26 08:05 作者: Plaque 時間: 2025-3-26 10:05
SANS: Setwise Attentional Neural Similarity Method for Few-Shot Recommendationaptive weight to emphasize the importance of few-shot users. We simulate the few-shot recommendation problem on three real-world datasets and extensive results show that SANS can outperform the state-of-the-art recommendation algorithms in few-shot recommendation.作者: 灌輸 時間: 2025-3-26 15:01
Semi-supervised Factorization Machines for Review-Aware Recommendationwo predictors. Furthermore, to exploit unlabeled data safely, the labeling confidence is estimated through validating the influence of the labeling of unlabeled examples on the labeled ones. The final prediction is made by linearly blending the outputs of two predictors. Extensive experiments on thr作者: llibretto 時間: 2025-3-26 20:25 作者: Stagger 時間: 2025-3-27 00:41 作者: 可卡 時間: 2025-3-27 01:08
Knowledge-Aware Hypergraph Neural Network for Recommender Systemsbased neighbors in hyperedge efficiently. Moreover, it can conduct the embedding propagation of high-order correlations explicitly and efficiently in knowledge-aware hypergraph. Finally, we apply the proposed model on three real-world datasets, and the empirical results demonstrate that KHNN can ach作者: Concrete 時間: 2025-3-27 06:57
Personalized Dynamic Knowledge-Aware Recommendation with Hybrid Explanations novel interval-aware Gated Recurrent Unit (GRU). Furthermore, by leveraging self-attention mechanism, we can not only learn each review’s user-specific importance, but also provide tailored explanations for each user at both feature level and review level. We conduct extensive experiments on three 作者: 友好關(guān)系 時間: 2025-3-27 12:17
Learning Disentangled User Representation Based on Controllable VAE for Recommendationon related to the real-world concepts using a factorized Gaussian distribution. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines. We further evaluate our model’s effectiveness to control the trade-off between reconstruction error and disentanglem作者: Unsaturated-Fat 時間: 2025-3-27 15:05 作者: venous-leak 時間: 2025-3-27 19:39
Tell Me Where to Go Next: Improving POI Recommendation via Conversationat the next turn to achieve successful POI recommendation within as few turns as possible. Finally, our extensive experiments on two real-world datasets demonstrate significant improvements over the state-of-the-art methods.作者: 調(diào)整 時間: 2025-3-28 01:55
MISS: A Multi-user Identification Network for Shared-Account Session-Aware Recommendationork to capture user interest drift across sessions. The other is a Multi-user Identification (MI) module, which draws on the attention mechanism to distinguish behaviors of different users under the same account. To verify the effectiveness of MISS, we construct two data sets with shared account cha作者: dowagers-hump 時間: 2025-3-28 05:43
VizGRank: A Context-Aware Visualization Recommendation Method Based on Inherent Relations Between Viot reflect the realistic scenarios of visualization recommendation completely, a new benchmark for visualization recommendation is designed and constructed by collecting real public datasets. Extensive experiments on both the public benchmark and the new benchmark demonstrate that the VizGRank can b作者: Contort 時間: 2025-3-28 06:55
Deep User Representation Construction Model for Collaborative Filteringtem for different users, which may limit the expressiveness and further improvement of the models. In this paper, we propose Deep User Representation Construction Model (DURCM) to construct user presentations in a more effective and robust way. Specially, different from existing item-item methods th作者: BOOM 時間: 2025-3-28 11:19
DiCGAN: A Dilated Convolutional Generative Adversarial Network for Recommender Systems before convolution to generate attention maps for adaptive feature refinement. Experiments on several public datasets verify the superiority of DiCGAN over several baselines in terms of top-. recommendation. Further more, our experimental results show that when the dataset is more large and sparse,作者: paltry 時間: 2025-3-28 16:12
Gated Sequential Recommendation System with Social and Textual Information Under Dynamic Contextspapers leverage abundant data from heterogeneous information sources to grasp diverse preferences and improve overall accuracy. Some noticeable papers proposed to extract users’ preference from information along with ratings such as reviews or social relations. However, their combinations are genera作者: 暗諷 時間: 2025-3-28 20:25
SRecGAN: Pairwise Adversarial Training for Sequential Recommendationectiveness for such a task by maximizing the margin between observed and unobserved interactions. However, there exist unobserved positive items that are very likely to be selected in the future. Treating those items as negative leads astray and poses a limitation to further exploiting its potential作者: Carbon-Monoxide 時間: 2025-3-29 01:55
SSRGAN: A Generative Adversarial Network for Streaming Sequential Recommendationonological order. Although a few streaming update strategies have been developed, they cannot be applied in sequential recommendation, because they can hardly capture the long-term user preference only by updating the model with random sampled new instances. Besides, some latent information is ignor作者: Respond 時間: 2025-3-29 04:42
Topological Interpretable Multi-scale Sequential Recommendation, short or mid-term interest. The multi-scale modeling of user interest in an interpretable way poses a great challenge in sequential recommendation. Hence, we propose a topological data analysis based framework to model target items’ explicit dependency on previous items or item chunks with differe作者: Maximizer 時間: 2025-3-29 08:50 作者: 不能仁慈 時間: 2025-3-29 14:34
Semi-supervised Factorization Machines for Review-Aware Recommendation when the interaction data is sparse. However, existing solutions to review-aware recommendation only focus on learning more informative features from reviews, yet ignore the insufficient number of training examples, resulting in limited performance improvements. To this end, we propose a co-trainin作者: engrossed 時間: 2025-3-29 17:10 作者: STRIA 時間: 2025-3-29 23:23 作者: GET 時間: 2025-3-30 02:19
Knowledge-Aware Hypergraph Neural Network for Recommender Systemsfiltering in recommender systems. However, most of the existing KG-based recommendation models suffer from the following drawbacks, i.e., insufficient modeling of high-order correlations among users, items, and entities, and simple aggregation strategies which fail to preserve the relational informa作者: Hot-Flash 時間: 2025-3-30 06:58 作者: Accomplish 時間: 2025-3-30 08:30 作者: 名次后綴 時間: 2025-3-30 14:08
Learning Disentangled User Representation Based on Controllable VAE for Recommendationepresentation of users can uncover user intentions behind the observed data (i.e. user-item interaction) and improve the robustness and interpretability of the recommender system. However, existing collaborative filtering methods learning disentangled representation face problems of balancing the tr作者: CRAMP 時間: 2025-3-30 18:49
DFCN: An Effective Feature Interactions Learning Model for Recommender Systemsance of recommendation, which is of great significance. Manual feature engineering is no longer applicable due to its high cost and low efficiency. Factorization machines introduce the second-order feature interactions to enhance learning ability. Deep neural networks (DNNs) have good nonlinear comb作者: Cholesterol 時間: 2025-3-30 23:18 作者: 現(xiàn)實 時間: 2025-3-31 02:05
MISS: A Multi-user Identification Network for Shared-Account Session-Aware Recommendationct the next interaction based on user’s historical sessions and current session. Though existing methods have achieved promising results, they still have drawbacks in some aspects. First, most existing deep learning methods model a session as a sequence, but neglect the complex transition relationsh作者: 混雜人 時間: 2025-3-31 06:03 作者: Iniquitous 時間: 2025-3-31 10:25
Deep User Representation Construction Model for Collaborative Filteringas modeling the user-item interaction and the only difference between them is that they adopt different ways to build user representations. User-item methods obtain user representations by directly assigning each user a real-valued vector and do not consider users’ historical item information. Howev作者: 確定的事 時間: 2025-3-31 14:46
DiCGAN: A Dilated Convolutional Generative Adversarial Network for Recommender Systems users’ preferences. However, most existing GAN-based recommendation methods only exploit the user-item interactions, while ignoring to leverage the information between user’s interacted items. On the other hand, Convolutional Neural Network (CNN) has shown its power in learning high-order correlati作者: LIEN 時間: 2025-3-31 18:20
Mau Mau Inventions and Reinventionspapers leverage abundant data from heterogeneous information sources to grasp diverse preferences and improve overall accuracy. Some noticeable papers proposed to extract users’ preference from information along with ratings such as reviews or social relations. However, their combinations are genera作者: 閑逛 時間: 2025-4-1 01:16 作者: 不容置疑 時間: 2025-4-1 02:32 作者: 闡明 時間: 2025-4-1 06:44
