{"title":"Diversity-Promoting Recommendation With Dual-Objective Optimization and Dual Consideration","authors":"Yuli Liu;Yuan Zhang","doi":"10.1109/TKDE.2025.3543285","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543285","url":null,"abstract":"Diversifying recommendations to broaden user horizons and explore potential interests has become a prominent research area in recommender systems. Although numerous efforts have been made to enhance diverse recommendations, the trade-off between diversity and accuracy remains a significant challenge. The primary causes lie in the following two aspects: (<italic>i</i>) the inherent goals of diversity-promoting recommendation, which are to simultaneously deliver accurate recommendations and cater to a broader spectrum of users’ interests, have not been adequately explored; and (<italic>ii</i>) considering diversity only in the model training procedure cannot guarantee the provision of diversification services in recommender systems. In this work, we directly formulate the inherent goals of diversity-promoting recommendation as a dual-objective optimization problem by simultaneously minimizing the recommendation error and maximizing diversity. These proposed objectives are integrated into Generative Adversarial Nets (GANs) to guide the training process toward the orientation of boosting both diversification and accuracy. Additionally, we propose considering diversity in both training and serving phases. Experimental results demonstrate that our model outperforms others in both diversity and relevance. We extend DDPR to state-of-the-art CTR and re-ranking models, which also result in improved performance on these tasks, further demonstrating the applicability of our model in real-world scenarios.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2391-2404"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lei Guan;Dongsheng Li;Yongle Chen;Jiye Liang;Wenjian Wang;Xicheng Lu
{"title":"PipeOptim: Ensuring Effective 1F1B Schedule With Optimizer-Dependent Weight Prediction","authors":"Lei Guan;Dongsheng Li;Yongle Chen;Jiye Liang;Wenjian Wang;Xicheng Lu","doi":"10.1109/TKDE.2025.3543225","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543225","url":null,"abstract":"Asynchronous pipeline model parallelism with a “1F1B” (one forward, one backward) schedule generates little bubble overhead and always provides quite a high throughput. However, the “1F1B” schedule inevitably leads to weight inconsistency and weight staleness issues due to the cross-training of different mini-batches across GPUs. To simultaneously address these two problems, in this paper, we propose an optimizer-dependent weight prediction strategy (a.k.a PipeOptim) for asynchronous pipeline training. The key insight of our proposal is that we employ a weight prediction strategy in the forward pass to approximately ensure that each mini-batch uses consistent and staleness-free weights to compute the forward pass of the “1F1B” schedule. To be concrete, we first construct the weight prediction scheme based on the update rule of the used optimizer when training the deep neural network models. Then throughout the “1F1B” pipeline training, each mini-batch is mandated to execute weight prediction, subsequently employing the predicted weights to perform the forward pass. As a result, PipeOptim 1) inherits the advantage of the “1F1B” schedule and generates high throughput, and 2) can ensure effective parameter learning regardless of the type of the used optimizer. We conducted extensive experimental evaluations using nine different deep-learning models to verify the effectiveness of our proposal. The experiment results demonstrate that PipeOptim outperforms the other five popular pipeline approaches including GPipe, PipeDream, PipeDream-2BW, SpecTrain, and XPipe.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2831-2845"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Causal-Based Attribute Selection Strategy for Conversational Recommender Systems","authors":"Dianer Yu;Qian Li;Xiangmeng Wang;Guandong Xu","doi":"10.1109/TKDE.2025.3543112","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543112","url":null,"abstract":"Conversational recommender systems (CRSs) provide personalised recommendations by strategically querying attributes matching users’ preferences. However, this process suffers from confounding effects of time and user attributes, as users’ preferences naturally evolve over time and differ among similar users due to their unique attributes. These confounding effects distort user behaviors’ causal drivers, challenging CRSs in learning users’ true preferences and generalizable patterns. Recently, causal inference provides principled tools to clarify cause-effect relations in data, offering a promising way to address such confounding effects. In this context, we introduce <bold>C</b>ausal <bold>C</b>onversational <bold>R</b>ecommender (<bold>CCR</b>), which applies causal inference to model the causality between user behaviors and time/user attribute, enabling deeper understanding of user behaviors’ causal drivers. First, CCR employs stratification and matching to ensure attribute asked per round is independent from time and user attributes, mitigating their confounding effects. Following that, we apply the Average Treatment Effect (ATE) to quantify the unbiased causal impact of each unasked attribute on user preferences, identifying the attribute with the highest ATE per round as the causal-based attribute, i.e., causal driver of user behaviour. Finally, CCR iteratively refines user preferences through feedback on causal-based attributes. Extensive experiments verified CCR's robustness and personalization.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2169-2182"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jie Chen;Hua Mao;Wai Lok Woo;Chuanbin Liu;Zhu Wang;Xi Peng
{"title":"One-Step Adaptive Graph Learning for Incomplete Multiview Subspace Clustering","authors":"Jie Chen;Hua Mao;Wai Lok Woo;Chuanbin Liu;Zhu Wang;Xi Peng","doi":"10.1109/TKDE.2025.3543696","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543696","url":null,"abstract":"Incomplete multiview clustering (IMVC) optimally integrates complementary information within incomplete multiview data to improve clustering performance. Several one-step graph-based methods show great potential for IMVC. However, the low-rank structures of similarity graphs are neglected at the initialization stage of similarity graph construction. Moreover, further investigation into complementary information integration across incomplete multiple views is needed, particularly when considering the low-rank structures implied in high-dimensional multiview data. In this paper, we present one-step adaptive graph learning (OAGL) that adaptively performs spectral embedding fusion to achieve clustering assignments at the clustering indicator level. We first initiate affinity matrices corresponding to incomplete multiple views using spare representation under two constraints, i.e., the sparsity constraint on each affinity matrix corresponding to an incomplete view and the degree matrix of the affinity matrix approximating an identity matrix. This approach promotes exploring complementary information across incomplete multiple views. Subsequently, we perform an alignment of the spectral block-diagonal matrices among incomplete multiple views using low-rank tensor learning theory. This facilitates consistency information exploration across incomplete multiple views. Furthermore, we present an effective alternating iterative algorithm to solve the resulting optimization problem. Extensive experiments on benchmark datasets demonstrate that the proposed OAGL method outperforms several state-of-the-art approaches.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2771-2783"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang Yang;Wei Shen;Junfeng Shu;Yinan Liu;Edward Curry;Guoliang Li
{"title":"CMVC+: A Multi-View Clustering Framework for Open Knowledge Base Canonicalization Via Contrastive Learning","authors":"Yang Yang;Wei Shen;Junfeng Shu;Yinan Liu;Edward Curry;Guoliang Li","doi":"10.1109/TKDE.2025.3543423","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543423","url":null,"abstract":"Open information extraction (OIE) methods extract plenty of OIE triples <italic><inline-formula><tex-math>$< $</tex-math><alternatives><mml:math><mml:mo><</mml:mo></mml:math><inline-graphic></alternatives></inline-formula>noun phrase, relation phrase, noun phrase<inline-formula><tex-math>$> $</tex-math><alternatives><mml:math><mml:mo>></mml:mo></mml:math><inline-graphic></alternatives></inline-formula></i> from unstructured text, which compose large open knowledge bases (OKBs). Noun phrases and relation phrases in such OKBs are not canonicalized, which leads to scattered and redundant facts. It is found that two views of knowledge (i.e., a fact view based on the fact triple and a context view based on the fact triple's source context) provide complementary information that is vital to the task of OKB canonicalization, which clusters synonymous noun phrases and relation phrases into the same group and assigns them unique identifiers. In order to leverage these two views of knowledge jointly, we propose CMVC+, a novel unsupervised framework for canonicalizing OKBs without the need for manually annotated labels. Specifically, we propose a multi-view CHF K-Means clustering algorithm to mutually reinforce the clustering of view-specific embeddings learned from each view by considering the clustering quality in a fine-grained manner. Furthermore, we propose a novel contrastive learning module to refine the learned view-specific embeddings and further enhance the canonicalization performance. We demonstrate the superiority of our framework through extensive experiments on multiple real-world OKB data sets against state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2296-2310"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Rethinking Variational Bayes in Community Detection From Graph Signal Perspective","authors":"Junwei Cheng;Yong Tang;Chaobo He;Pengxing Feng;Kunlin Han;Quanlong Guan","doi":"10.1109/TKDE.2025.3543378","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543378","url":null,"abstract":"Methods based on variational bayes theorytare widely used to detect community structures in networks. In recent years, many related methods have emerged that provide valuable insights into variational bayes theory. Remarkably, a fundamental assumption remains incomprehensible. Variational bayes-based methods typically employ a posterior distribution that follows a gaussian distribution to approximate the unknown prior distribution. However, the complexity and irregularity of node distributions in real-world networks prompt us to consider what characteristics of network information are suitable for the posterior distribution. Mathematically, inappropriate low- and high-frequency signals in expectation inference and variance inference can intensify the adverse effects of community distortion and ambiguity. To analysis these two phenomena and propose reasonable countermeasures, we conduct an empirical study. It is found that appropriately compressing low-frequency signals during expectation inference and amplifying high-frequency signals during variance inference are effective strategies. Based on these two strategies, this paper proposes a novel variational bayes plug-in, namely VBPG, to boost the performance of existing variational bayes-based community detection methods. Specifically, we modulate the frequency signals during expectation and variance inference to generate a new gaussian distribution. This strategy improves the fitting accuracy between the posterior distribution and the unknown true distribution without altering the modules of existing methods. The comprehensive experimental results validate that methods using VBPG achieve competitive performance improvements in most cases.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2903-2917"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mouxiang Chen;Han Fu;Chenghao Liu;Xiaoyun Joy Wang;Zhuo Li;Jianling Sun
{"title":"Build a Good Human-Free Prompt Tuning: Jointly Pre-Trained Template and Verbalizer for Few-Shot Classification","authors":"Mouxiang Chen;Han Fu;Chenghao Liu;Xiaoyun Joy Wang;Zhuo Li;Jianling Sun","doi":"10.1109/TKDE.2025.3543422","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543422","url":null,"abstract":"Prompt tuning for pre-trained language models (PLMs) has been an effective approach for few-shot text classification. To make a prediction, a typical prompt tuning method employs a template wrapping the input text into a cloze question, and a verbalizer mapping the output embedding to labels. However, current methods typically depend on handcrafted templates and verbalizers, which require much domain-specific prior knowledge by human efforts. In this work, we investigate how to build a good human-free prompt tuning using soft prompt templates and soft verbalizers, which can be learned directly from data. To address the challenge of data scarcity, we integrate a set of trainable bases for sentence representation to transfer the contextual information into a low-dimensional space. By jointly pre-training the soft prompts and the bases using contrastive learning, the projection space can catch critical semantics at the sentence level, which could be transferred to various downstream tasks. To better bridge the gap between downstream tasks and the pre-training procedure, we formulate the few-shot classification tasks as another contrastive learning problem. We name this Jointly Pretrained Template and Verbalizer (JPTV). Extensive experiments show that this human-free prompt tuning can achieve comparable or even better performance than manual prompt tuning.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2253-2265"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders With Mutual Information Constraints","authors":"Suguru Yasutomi;Toshihisa Tanaka","doi":"10.1109/TKDE.2025.3543383","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543383","url":null,"abstract":"Extracting fine-grained features such as styles from unlabeled data is crucial for data analysis. Unsupervised methods such as variational autoencoders (VAEs) can extract styles that are usually mixed with other features. Conditional VAEs (CVAEs) can isolate styles using class labels; however, there are no established methods to extract only styles using unlabeled data. In this paper, we propose a CVAE-based method that extracts style features using only unlabeled data. The proposed model consists of a contrastive learning (CL) part that extracts style-independent features and a CVAE part that extracts style features. The CL model learns representations independent of data augmentation, which can be viewed as a perturbation in styles, in a self-supervised manner. Considering the style-independent features from the pretrained CL model as a condition, the CVAE learns to extract only styles. Additionally, we introduce a constraint based on mutual information between the CL and VAE features to prevent the CVAE from ignoring the condition. Experiments conducted using two simple datasets, MNIST and an original dataset based on Google Fonts, demonstrate that the proposed method can efficiently extract style features. Further experiments using real-world natural image datasets were also conducted to illustrate the method’s extendability.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"3001-3014"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891874","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cross-Graph Interaction Networks","authors":"Qihang Guo;Xibei Yang;Weiping Ding;Yuhua Qian","doi":"10.1109/TKDE.2025.3543377","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543377","url":null,"abstract":"Graph neural networks (GNNs) are recognized as a significant methodology for handling graph-structure data. However, with the increasing prevalence of learning scenarios involving multiple graphs, traditional GNNs mostly overlook the relationships between nodes across different graphs, mainly due to their limitation of traditional message passing within each graph. In this paper, we propose a novel GNN architecture called cross-graph interaction networks (GInterNet) to enable inter-graph message passing. Specifically, we develop a cross-graph topology construction module to uncover and learn the potential topologies between nodes across different graphs. Furthermore, we establish inter-graph message passing based on the learned cross-graph topologies, achieving cross-graph interaction by aggregating information from different graphs. Finally, we employ cross-graph construction functions involving the relationships between contextual information and cross-graph topology structure to iteratively update the cross-graph topologies. Different to existing related approaches, GInterNet is designed as a cross-graph interaction paradigm for inter-graph message passing. It enables multi-graph interaction during the message passing process. Additionally, it is a plug-and-play framework that can be easily embedded into other models. We evaluate its performance in semi-supervised and unsupervised learning scenarios involving multiple graphs. A detailed theoretical analysis and extensive experiment results have shown that GInterNet improves the performance and robustness of the base models.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2341-2355"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"REP: An Interpretable Robustness Enhanced Plugin for Differentiable Neural Architecture Search","authors":"Yuqi Feng;Yanan Sun;Gary G. Yen;Kay Chen Tan","doi":"10.1109/TKDE.2025.3543503","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3543503","url":null,"abstract":"Neural architecture search (NAS) is widely used to automate the design of high-accuracy deep architectures, which are often vulnerable to adversarial attacks in practice due to the lack of adversarial robustness. Existing methods focus on the direct utilization of regularized optimization process to address this critical issue, which causes the lack of interpretability for the end users to learn how the robust architecture is constructed. In this paper, we introduce a robust enhanced plugin (REP) method for differentiable NAS to search for robust neural architectures. Different from existing peer methods, REP focuses on the robust search primitives in the search space of NAS methods, and naturally has the merit of contributing to understanding how the robust architectures are progressively constructed. Specifically, we first propose an effective sampling strategy to sample robust search primitives in the search space. In addition, we also propose a probabilistic enhancement method to guarantee natural accuracy and adversarial robustness simultaneously during the search process. We conduct experiments on both convolutional neural networks and graph neural networks with widely used benchmarks against state of the arts. The results reveal that REP can achieve superiority in terms of both the adversarial robustness to popular adversarial attacks and the natural accuracy of original data. REP is flexible and can be easily used by any existing differentiable NAS methods to enhance their robustness without much additional effort.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 5","pages":"2888-2902"},"PeriodicalIF":8.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}