Recently, Knowledge Graph Embedding (KGE) has attracted considerable research efforts, since it simplifies the manipulation while preserving the inherent structure of the KG. However to some extent, ...most existing KGE approaches ignore the historical changes of structural information involved in dynamic knowledge graphs (DKGs). To deal with this problem, this paper presents a Timespan-aware Dynamic knowledge Graph Embedding Evolution (TDG2E) method that considers temporal evolving process of DKGs. The major innovations of our paper are two-fold. Firstly, a Gated Recurrent Units (GRU) based model is utilized in TDG2E to deal with the dependency among sub-KGs that is inevitably involved in the learning process of the dynamic knowledge graph embedding. Furthermore, we incorporate an auxiliary loss to supervise the learning process of the next sub-KG by utilizing previous structural information (i.e., the hidden state of GRU). In contrast with existing approaches in the literature (e.g., HyTE and t-TransE), TDG2E preserves structural information of current sub-KG and the temporal evolving process of the DKG simultaneously. Secondly, to further deal with the time unbalance issue underlying the DKGs, a Timespan Gate is designed in GRU. It makes TDG2E possible to model the temporal evolving process of DKGs more effectively by incorporating the timespan between adjacent sub-KGs. Extensive experiments on two large temporal datasets (i.e., YAGO11k and Wikidata12k) extracted from real-world KGs validate that the proposed TDG2E significantly outperforms traditional KGE methods in terms of Mean Rank and Hit Rate.
Incorporating knowledge graphs (KGs) into recommender systems (knowledge-aware recommendation) to improve the recommendation accuracy and explainability has attracted considerable research efforts. ...However, existing methods largely assume that KGs are complete when transferring knowledge from them, which may lead to suboptimal performance for those KGs, can be hardly complete in real-life scenarios. In this paper, we present a robustly co-learning model (RCoLM) that takes the incompleteness nature of KGs into consideration when incorporating them into recommendation. The RCoLM aims at transferring knowledge between recommendation task and knowledge graph completion (KG completion) task by utilizing a transfer learning model. An earlier version of this paper appeared in KDD 2019. This version is an extension of the previous submission and two major innovations are presented here. At first, distinct from previous knowledge-aware recommendation methods, which mainly focus on transferring knowledge from KGs to item recommendations, the RCoLM attempts to exploit user-item interactions from recommendations for KG completion, and unifies the two tasks in a joint model for mutual enhancements. Second, the RCoLM provides a general task-oriented negative sampling strategy on KG completion task, which further improves the adaptive ability of the proposed algorithm and plays an essential role for obtaining superior performance in various sub-tasks of the KG completion. The extensive experiments on two real-world public datasets demonstrate that RCoLM outperforms not only state-of-the-art knowledge-aware recommendation methods but also existing KG completion methods.
In real-time bidding (RTB) systems for display advertising, a demand-side platform (DSP) serves as an agent for advertisers and plays an important role in competing for online advertising spaces by ...placing proper bidding prices. A critical function of the DSP is formulating proper bidding strategies to maximize key performance indicators, such as the number of clicks and conversions. However, many small and medium-sized advertisers' main goal is to maximize revenue with an acceptable return on investment (ROI), rather than simply increase clicks or conversions. Most existing approaches are inapplicable of satisfying the revenue-maximizing goals directly. To solve this problem, we first theoretically analyze the relationships among the conversion rate, ROI, and ad cost, and how they affect revenue. By doing so, we reveal that it is a challenge to increase revenue by relying solely on improving ROI without considering the impact of the ad cost. Based on this insight, the maximal revenue (MR) bidding strategy is proposed to maximize revenue by maximizing the ad cost with a desirable ROI constraint. Unlike previous studies, the proposed MR first distinguishes bid prices from ad costs explicitly, which makes it more applicable to the real second-price auction (GSP) auction mechanism in RTB systems. Then, the winning function is empirically defined in the form of tanh that provides a promising solution for estimating ad costs by jointly considering ad costs with the winning function. The experimental results based on two real-world public datasets demonstrate that the MR significantly outperforms five state-of-the-art models in terms of both revenue and ROI.
Multi-label learning deals with problems in which each instance is associated with a set of labels. Most multi-label learning algorithms ignore the potential distribution differences between the ...training domain and the test domain in the instance space and label space, as well as the intrinsic geometric information of the label space. These restrictive assumptions limit the ability of the existing multi-label learning algorithms to classify between domains. To solve this problem, in this paper, we propose a novel distribution-adaptation-based method, the multi-label metric transfer learning (MLMTL), to relax these two assumptions and handle more general multi-label learning tasks effectively. In particular, MLMTL extends the maximum mean discrepancy method into multi-label classification by learning and adjusting the weights for the multi-labeled training instances. In this way, MLMTL bridges the instance distribution and label distribution divergence between training and test datasets. In addition, based on the balanced multi-label training data, we explore the intrinsic geometric information of the label space by encoding it into a distance metric learning framework. Extensive experiments on five benchmark datasets show that the proposed approach significantly outperforms the state-of-the-art multi-label learning algorithms.
Learning the distribution of market prices is an important and challenging issue for demand-side platforms (DSPs) that serve as advertisers’ agents to compete for online advertising placements in ...real-time bidding (RTB) systems. Many existing approaches make an assumption that the market prices follow an unimodal distribution. However, based on analytical insights from real-world datasets, we found the distinct multimodal characteristics underlying the distribution of market prices. Moreover, the impression-level features for each ad are also ignored by these approaches in prediction, reducing the accuracy further. To address these problems, a Gaussian Mixture Model (GMM) is proposed in this paper to describe and discriminate the multimodal distribution of market price by utilizing the impression-level features. To further improve its robustness, GMM is extended into a censored version (CGMM) to handle the right-censored challenge in RTB systems (i.e., the market price is only visible to the winner of the ad auction. Thus, the dataset is always biased). Extensive experiments on two real-world public datasets demonstrate that GMM and CGMM significantly outperform 10 state-of-the-art baselines in terms of Wasserstein distance, KL-divergence, ANLP and MSE. To the best of our knowledge, this paper is the first work to simultaneously deal with the multimodal nature of market price distribution and the right-censored challenge in existing RTB systems. It will enable future RTB systems to develop more realistic bidding strategies to enhance the efficiency of online advertising placement auctioning.
Few-shot Knowledge Graph Completion (FKGC) has recently attracted significant research interest due to its ability to expand few-shot relation coverage in Knowledge Graphs. Prevailing FKGC approaches ...focus on exploiting the one-hop neighbor information of entities to enhance few-shot relation embedding. However, these methods select one-hop neighbors randomly and neglect the rich multi-aspect information of entities. Although some methods have attempted to leverage Long Short-Term Memory (LSTM) to learn few-shot relation embedding, they are sensitive to the input order. To address these limitations, we propose the Capsule Neural Tensor Networks with Multi-Aspect Information approach (short for InforMix-FKGC). InforMix-FKGC employs a one-hop neighbor selection strategy based on how valuable they are and encodes multi-aspect information of entities, including one-hop neighbors, attributes and literal description. Then, a capsule network is responsible for integrating the support set and deriving few-shot relation embedding. Moreover, a neural tensor network is used to match the query set with the support set. In this way, InforMix-FKGC can learn few-shot relation embedding more precisely so as to enhance the accuracy of FKGC. Extensive experiments on the NELL-One and Wiki-One datasets demonstrate that InforMix-FKGC significantly outperforms ten state-of-the-art methods in terms of Mean Reciprocal Rank and Hits@K.
As a revolutionary auction mechanism for display advertising, real-time bidding (RTB) allows advertisers to purchase individual ad impressions through real-time auctions. In RTB, the demand-side ...platform (DSP) acts as advertisers' bidding agent and aims at developing appropriate bidding strategies to maximize their specific key performance indicators (KPIs). Existing bidding strategies perform well for optimizing profits when the ad budget severely limited. However, when there is sufficient budget, their performance deteriorates. This results in added complexity for advertisers when applying these approaches in practice, hindering wider adoption. To address this challenging limitation, we propose the Adaptive ROI-Aware Bidding (ARAB) approach. It intelligently analyzes the budget setting and auction market conditions, and adjusts the bidding function accordingly to optimize profits. Different from previous studies that only bid based on the ad revenue, our proposed ROI-aware bidding function also takes into account the ad cost at impression-level. By doing so, ARAB dynamically allocates the budget on more cost-effective impressions to increase profits. Through extensive offline experiments on two real-world public datasets, we demonstrate that the proposed ARAB has achieved significant improvements in terms of both profit and ROI compared to state-of-the-art approaches.
With the rapid development of real-time bidding (RTB) in online advertising, learning the distribution of market price has attracted wide attention, since it plays a critical role in designing ...bidding strategies. One important problem is the right-censored issue in which the true market price can only be observed by the winner of the auction. To address this, existing studies often use Kaplan–Meier estimation (KM), which is one of the best options for survival analysis. However, these approaches depend on counting sample segments and cannot provide accurate predictions for each individual bid request. To enhance the prediction ability, we propose an original method to build the KM for each bid request by predicting (1) the probability of winning an auction at a specific market price, and (2) the probability of losing an auction at a certain bid price. To deal with the high-dimensional sample data common in RTB scenarios, we design a Markov network to calculate these two probabilities. Extensive experiments on two public datasets demonstrate that the proposed approach significantly outperforms state-of-the-art baselines in terms of various metrics, including Wasserstein distance, KL-divergence, average negative log probability and mean squared error.
Based on data analysis, survey and summary, multi-disciplinary integration and other means, training methods for inter-disciplinary elderly care workers in the new era are put forward, including ...enhancing multi-disciplinary theoretical knowledge reserve, improving professional skills and psychological communication skills and improving nursing ability of elderly care workers. According to the physical condition and psychological characteristics of the elderly, multiple disciplines such as community rehabilitation , food and nutrition, medicine, and elderly care should be integrated effectively to build a multi-disciplinary knowledge theoretical framework. ...elderly care workers need to master the common fitnes exercises in Chinese medicine, including Tai Chi, Qigong, Baduanjin, etc. If elderly care workers can master key skils, it can greatly help the elderly to resist serious diseasesand sudden diseases. 2.3 Strengthening the training of psychological communication skills to improve the ability of psychological comfort Public health emergencies such as the novel coronavirus pneumonia epidemic are so harmful, causing a strong psychological impact on Chinese people.
AKUPM Tang, Xiaoli; Wang, Tengyun; Yang, Haizhi ...
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,
07/2019
Conference Proceeding
Recently, much attention has been paid to the usage of knowledge graph within the context of recommender systems to alleviate the data sparsity and cold-start problems. However, when incorporating ...entities from a knowledge graph to represent users, most existing works are unaware of the relationships between these entities and users. As a result, the recommendation results may suffer a lot from some unrelated entities.
In this paper, we investigate how to explore these relationships which are essentially determined by the interactions among entities. Firstly, we categorize the interactions among entities into two types: inter-entity-interaction and intra-entity-interaction. Inter-entity-interaction is the interactions among entities that affect their importances to represent users. And intra-entity-interaction is the interactions within an entity that describe the different characteristics of this entity when involved in different relations.
Then, considering these two types of interactions, we propose a novel model named Attention-enhanced Knowledge-aware User Preference Model (AKUPM) for click-through rate (CTR) prediction. More specifically, a self-attention network is utilized to capture the inter-entity-interaction by learning appropriate importance of each entity w.r.t the user. Moreover, the intra-entity-interaction is modeled by projecting each entity into its connected relation spaces to obtain the suitable characteristics. By doing so, AKUPM is able to figure out the most related part of incorporated entities (i.e., filter out the unrelated entities). Extensive experiments on two real-world public datasets demonstrate that AKUPM achieves substantial gains in terms of common evaluation metrics (e.g., AUC, ACC and Recall@top-K) over several state-of-the-art baselines.
PDF
