论文检索

Jiahui Gong, Jingtao Ding, Fanjin Meng, Guilong Chen, Hong Chen, Shen Zhao, Haisheng Lu, Yong Li 0008

Mobile devices, especially smartphones, can support rich functions and have developed into indispensable tools in daily life. With the rise of generative AI services, smartphones can potentially transform into personalized assistants, anticipating user needs and scheduling services accordingly. Predicting user intents on smartphones, and reflecting anticipated activities based on past interactions and context, remains a pivotal step towards this vision. Existing research predominantly focuses on specific domains, neglecting the challenge of modeling diverse event sequences across dynamic contexts. Leveraging pre-trained language models (PLMs) offers a promising avenue, yet adapting PLMs to on-device user intent prediction presents significant challenges. To address these challenges, we propose PITuning, a Population-to-Individual Tuning framework. PITuning enhances common pattern extraction through dynamic event-to-intent transition modeling and addresses long-tailed preferences via adaptive unlearning strategies. Experimental results on real-world datasets demonstrate PITuning's superior intent prediction performance, highlighting its ability to capture long-tailed preferences and its practicality for on-device prediction scenarios.

Yong Liang Goh, Zhiguang Cao, Yining Ma 0001, Yanfei Dong, Mohammed Haroon Dupty, Wee Sun Lee

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on entirely random problem instances that inadequately capture real-world scenarios. In this paper, we introduce realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and derive the following insights: (1) The optimal next node (or city) to visit often lies within proximity to the current node, suggesting the potential benefits of biasing choices based on current locations. (2) Effectively solving the TSP requires robust tracking of unvisited nodes and warrants succinct grouping strategies. Building upon these insights, we propose integrating a learnable choice layer inspired by Hypernetworks to prioritize choices based on the current location, and a learnable approximate clustering algorithm inspired by the Expectation-Maximization algorithm to facilitate grouping the unvisited cities. Together, these two contributions form a hierarchical approach towards solving the realistic TSP by considering both immediate local neighbourhoods and learning an intermediate set of node representations. Our hierarchical approach yields superior performance compared to both classical and recent transformer models, showcasing the efficacy of the key designs.

Ramin Ghorbani, Marcel J. T. Reinders, David M. J. Tax

Evaluating anomaly detection algorithms in time series data is critical as inaccuracies can lead to flawed decision-making in various domains where real-time analytics and data-driven strategies are essential. Traditional performance metrics assume iid data and fail to capture the complex temporal dynamics and specific characteristics of time series anomalies, such as early and delayed detections. We introduce Proximity-Aware Time series anomaly Evaluation (PATE), a novel evaluation metric that incorporates the temporal relationship between prediction and anomaly intervals. PATE uses proximity-based weighting considering buffer zones around anomaly intervals, enabling a more detailed and informed assessment of a detection. Using these weights, PATE computes a weighted version of the area under the Precision and Recall curve. Our experiments with synthetic and real-world datasets show the superiority of PATE in providing more sensible and accurate evaluations than other evaluation metrics. We also tested several state-of-the-art anomaly detectors across various benchmark datasets using the PATE evaluation scheme. The results show that a common metric like Point-Adjusted F1 Score fails to characterize the detection performances well, and that PATE is able to provide a more fair model comparison. By introducing PATE, we redefine the understanding of model efficacy that steers future studies toward developing more effective and accurate detection models.

Yucen Gao, Zhehao Zhu, Mingqian Ma, Fei Gao, Hui Gao, Yangguang Shi, Xiaofeng Gao 0001

Car-hailing services play an important role in the modern transportation system, and the utilities of the service providers highly depend on the efficiency of route planning algorithms. A widely adopted route planning framework is to assign weights to roads and compute the routes with the shortest path algorithms. Existing techniques of weight-assigning often focus on the traveling time and length of the roads, but cannot incorporate with the preferences of the passengers (users). In this paper, a set of preference weight estimation models is employed to capture the users' preferences over paths in car-hailing with their historical choices. Since the user preferences may vary dynamically over time, it is a challenging task to make real-time decisions over the models. The main technical contribution of this paper is to propose an online learning-based preference weight chasing (PWC) algorithm to solve this problem. The worst-case performance of PWC is analyzed with the metric regret, and it is proved that PWC has a vanishing regret, which means that the time-averaged loss concerning the fixed in-hindsight best model tends to zero. Experiments based on real-world datasets are conducted to verify the effectiveness and efficiency of our algorithm. The code is available at https://github.com/GaoYucen/PWC.

Xinyi Gao 0001, Tong Chen 0005, Wentao Zhang 0001, Yayong Li, Xiangguo Sun, Hongzhi Yin

The burgeoning volume of graph data presents significant computational challenges in training graph neural networks (GNNs), critically impeding their efficiency in various applications. To tackle this challenge, graph condensation (GC) has emerged as a promising acceleration solution, focusing on the synthesis of a compact yet representative graph for efficiently training GNNs while retaining performance. Despite the potential to promote scalable use of GNNs, existing GC methods are limited to aligning the condensed graph with merely the observed static graph distribution. This limitation significantly restricts the generalization capacity of condensed graphs, particularly in adapting to dynamic distribution changes. In real-world scenarios, however, graphs are dynamic and constantly evolving, with new nodes and edges being continually integrated. Consequently, due to the limited generalization capacity of condensed graphs, applications that employ GC for efficient GNN training end up with sub-optimal GNNs when confronted with evolving graph structures and distributions in dynamic real-world situations. To overcome this issue, we propose open-world graph condensation (OpenGC), a robust GC framework that integrates structure-aware distribution shift to simulate evolving graph patterns and exploit the temporal environments for invariance condensation. This approach is designed to extract temporal invariant patterns from the original graph, thereby enhancing the generalization capabilities of the condensed graph and, subsequently, the GNNs trained on it. Furthermore, to support the periodic re-condensation and expedite condensed graph updating in life-long graph learning, OpenGC reconstructs the sophisticated optimization scheme with kernel ridge regression and non-parametric graph convolution, significantly accelerating the condensation process while ensuring the exact solutions. Extensive experiments on both real-world and synthetic evolving graphs demonstrate that OpenGC outperforms state-of-the-art (SOTA) GC methods in adapting to dynamic changes in open-world graph environments.

Heyang Gao, Zexu Sun, Hao Yang 0045, Xu Chen 0017

Causal discovery with observational and interventional data plays an important role in numerous fields. Due to the costly and potentially risky nature of intervention experiments, selecting informative interventions is critical in real-world situations. Several recent works introduce Bayesian active learning to select interventions that maximize the expected information gain about the underlying causal relationship at each optimization step. However, there are still some limitations within these methods: (1) Local optimality. With multiple intervention experiments, selecting optimal intervention myopically at each step may drop into the local optimal point. (2) Expensive time cost. Optimizing the most informative intervention at each step is time-consuming and not suitable for adaptive experiments with strict inference speed requirements. In this study, we propose a novel method called Reinforcement Learning-based Causal Bayesian Experimental Design (RL-CBED) to reduce the risk of local optimality and accelerate intervention selection inference. Specifically, we formulate the active causal discovery problem as a partially observable Markov decision process (POMDP). We design an information gain-based sparse reward function and then improve it to a dense reward function, providing fine-grained feedback to help the RL policy learn more quickly in complex environments. Moreover, we theoretically prove that the Q-function estimator can be learned using only trajectories sampled from the prior, which can significantly reduce the time cost of training process, enabling the real-world application of our method. Extensive experiments on both synthetic and real world-inspired semi-synthetic datasets demonstrate the effectiveness of our proposed method.

Xingbo Fu, Zihan Chen 0002, Binchi Zhang, Chen Chen 0022, Jundong Li

Federated Graph Learning (FGL) aims to learn graph learning models over graph data distributed in multiple data owners, which has been applied in various applications such as social recommendation and financial fraud detection. Inherited from generic Federated Learning (FL), FGL similarly has the data heterogeneity issue where the label distribution may vary significantly for distributed graph data across clients. For instance, a client can have the majority of nodes from a class, while another client may have only a few nodes from the same class. This issue results in divergent local objectives and impairs FGL convergence for node-level tasks, especially for node classification. Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs). To grapple with the challenge, we propose FedSpray, a novel FGL framework that learns local class-wise structure proxies in the latent space and aligns them to obtain global structure proxies in the server. Our goal is to obtain the aligned structure proxies that can serve as reliable, unbiased neighboring information for node classification. To achieve this, FedSpray trains a global feature-structure encoder and generates unbiased soft targets with structure proxies to regularize local training of GNN models in a personalized way. We conduct extensive experiments over four datasets, and experiment results validate the superiority of FedSpray compared with other baselines. Our code is available at https://github.com/xbfu/FedSpray.

Kairui Fu, Shengyu Zhang 0001, Zheqi Lv, Jingyuan Chen 0003, Jiwei Li 0001

Due to the continuously improving capabilities of mobile edges, recommender systems start to deploy models on edges to alleviate network congestion caused by frequent mobile requests. Several studies have leveraged the proximity of edge-side to real-time data, fine-tuning them to create edge-specific models. Despite their significant progress, these methods require substantial on-edge computational resources and frequent network transfers to keep the model up to date. The former may disrupt other processes on the edge to acquire computational resources, while the latter consumes network bandwidth, leading to a decrease in user satisfaction. In response to these challenges, we propose a customizeD slImming framework for incompatiblE neTworks(DIET). DIET deploys the same generic backbone (potentially incompatible for a specific edge) to all devices. To minimize frequent bandwidth usage and storage consumption in personalization, DIET tailors specific subnets for each edge based on its past interactions, learning to generate slimming subnets(diets) within incompatible networks for efficient transfer. It also takes the inter-layer relationships into account, empirically reducing inference time while obtaining more suitable diets. We further explore the repeated modules within networks and propose a more storage-efficient framework, DIETING, which utilizes a single layer of parameters to represent the entire network, achieving comparably excellent performance. The experiments across four state-of-the-art datasets and two widely used models demonstrate the superior accuracy in recommendation and efficiency in transmission and storage of our framework.

Raphael Fischer 0001, Amal Saadallah

Automated machine learning (AutoML) streamlines the creation of ML models, but few specialized methods have approached the challenging domain of time series forecasting. Deep neural networks (DNNs) often deliver state-of-the-art predictive performance for forecasting data, however these models are also criticized for being computationally intensive black boxes. As a result, when searching for the "best" model, it is crucial to also acknowledge other aspects, such as interpretability and resource consumption. In this paper, we propose AutoXPCR - a novel method that produces DNNs for forecasting under consideration of multiple objectives in an automated and explainable fashion. Our approach leverages meta-learning to estimate any model's performance along PCR criteria, which encompass (P)redictive error, (C)omplexity, and (R)esource demand. Explainability is addressed on multiple levels, as AutoXPCR pro-vides by-product explanations of recommendations and allows to interactively control the desired PCR criteria importance and trade-offs. We demonstrate the practical feasibility AutoXPCR across 108 forecasting data sets from various domains. Notably, our method outperforms competing AutoML approaches - on average, it only requires 20% of computation costs for recommending highly efficient models with 85% of the empirical best quality.

Zhiying Feng, Qiong Wu 0009, Xu Chen 0004

Mobile traffic prediction plays a crucial role in enabling efficient network management and service provisioning. Traditional prediction approaches treat different mobile application services (such as Uber, Facebook, Twitter, etc) as isolated entities, neglecting potential correlation among them. Moreover, such isolated prediction methods necessitate the uploading of historical traffic data from all regions to forecast city-wide traffic, resulting in consuming substantial bandwidth resources and risking prediction failure in the event of data loss in specific regions. To address these challenges, we propose a novel Cross-service Attention-based Spatial-Temporal Graph Convolutional Network (CsASTGCN) for precise and communication-efficient multi-service mobile traffic prediction. Our methodology allows each mobile service to transmit the traffic data of only a fraction of regions for city-wide traffic prediction of all mobile services, which reduces the resource consumption caused by data transmission. Specifically, the sparse traffic data are initially transmitted to the cloud server and the masked graph autoencoder is utilized to roughly reconstruct the traffic volume for regions with missing data. Subsequently, a cross-service attention-based predictor is designed to calculate the data correlation among different mobile services within the same region. Considering the constantly emerging mobile services, we incorporate a novel model-based adaptive transfer learning scheme to extract valuable knowledge from the existing models and expedite the training of a new model for a new service without training from scratch, thereby enhancing the scalability of our framework. Extensive experiments conducted on a large-scale real-world mobile traffic dataset demonstrate that our model greatly outperforms the existing schemes, enhancing both the communication-efficiency and robustness of large-scale multi-service traffic prediction.

Yuye Feng, Wei Zhang 0387, Yao Fu 0006, Weihao Jiang, Jiang Zhu, Wenqi Ren

Unsupervised anomaly detection in multivariate time series (MTS) has always been a challenging problem, and the modeling based on reconstruction has garnered significant attention. The insensitivity of these methods towards normal patterns poses challenges in distinguishing between normal and abnormal points. Firstly, the general reconstruction strategies may exhibit limited sensitivity to spatio-temporal dependencies, and their performance remains largely unaffected by such dependencies. Secondly, most methods fail to model the heteroscedastic uncertainty in MTS, hindering their abilities to derive a distinguishable criterion. For instance, normal data with high noise levels may lead to detection failure due to excessively high reconstruction errors. In this work, we emphasize the necessity of sensitivity to normal patterns, which could improve the discrimination between normal and abnormal points remarkably. To this end, we propose SensitiveHUE, a probabilistic network by implementing both reconstruction and heteroscedastic uncertainty estimation. Its core includes a statistical feature removal strategy to ensure the dependency sensitive property, and a novel MTS-NLL loss for modeling the normal patterns in important regions. Experimental results demonstrate that SensitiveHUE exhibits nontrivial sensitivity to normal patterns and outperforms the existing state-of-the-art alternatives by a large margin. Code is publicly available at this URL\footnotehttp://github.com/yuesuoqingqiu/SensitiveHUE.

Yuting Feng, Vincent Y. F. Tan, Bogdan Cautis

We consider a ubiquitous scenario in the study of Influence Maximization (IM), in which there is limited knowledge about the topology of the diffusion network. We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced. Leveraging the capability of bandit algorithms to effectively balance the objectives of exploration and exploitation, as well as the expressivity of neural networks, our study explores the application of neural bandit algorithms to the IM problem. We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced by influencers (also known as diffusion seeds). This initial estimate forms the basis for constructing both an exploitation graph and an exploration one. Subsequently, IM-GNB handles the exploration-exploitation tradeoff, by selecting seed nodes in real-time using Graph Convolutional Networks (GCN), in which the pre-estimated graphs are employed to refine the influencers' estimated rewards in each contextual setting. Through extensive experiments on two large real-world datasets, we demonstrate the effectiveness of IM-GNB compared with other baseline methods, significantly improving the spread outcome of such diffusion campaigns, when the underlying network is unknown.

Shanshan Feng 0001, Feiyu Meng, Lisi Chen 0001, Shuo Shang, Yew Soon Ong

The next Point-of-interest recommendation has attracted extensive research interest recently, which predicts users' subsequent movements. The main challenge is how to effectively capture users' personalized sequential transitions in check-in trajectory, and various methods have been developed. However, most existing studies ignore the temporal information when conducting the next POI recommendation. To fill this gap, we investigate a time-specific next POI recommendation task, which additionally incorporates the target time information. We propose a brand new Time2Rotation technique to capture the temporal information. Different from conventional methods, we represent timeslots as rotation vectors and then perform the rotation operations. Based on the Time2Rotation technique, we propose a novel rotation-based temporal attention network, namely ROTAN, for the time-specific next POI recommendation task. The ROTAN begins by building a collaborative POI transition graph, capturing the asymmetric temporal influence in sequential transitions. After that, it incorporates temporal information into the modeling of individual check-in trajectories, extracting separate representations for user preference and POI influence to reflect their distinct temporal patterns. Lastly, the target time is integrated to generate recommendations. Extensive experiments are conducted on three real-world datasets, which demonstrates the advantages of the proposed Time2Rotation technique and ROTAN recommendation model.

Yi Fang 0011, Dongzhe Fan, Daochen Zha, Qiaoyu Tan

This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods that perturb the numerical feature space and alter the graph's topological structure, we aim to improve view generation through language supervision. This is driven by the prevalence of textual attributes in real applications, which complement graph structures with rich semantic information. However, this presents challenges because of two major reasons. First, text attributes often vary in length and quality, making it difficulty to perturb raw text descriptions without altering their original semantic meanings. Second, although text attributes complement graph structures, they are not inherently well-aligned. To bridge the gap, we introduce GAugLLM, a novel framework for augmenting TAGs. It leverages advanced large language models like Mistral to enhance self-supervised graph learning. Specifically, we introduce a mixture-of-prompt-expert technique to generate augmented node features. This approach adaptively maps multiple prompt experts, each of which modifies raw text attributes using prompt engineering, into numerical feature space. Additionally, we devise a collaborative edge modifier to leverage structural and textual commonalities, enhancing edge augmentation by examining or building connections between nodes. Empirical results across five benchmark datasets spanning various domains underscore our framework's ability to enhance the performance of leading contrastive methods (e.g., BGRL, GraphCL, and GBT) as a plug-in tool. Notably, we observe that the augmented features and graph structure can also enhance the performance of standard generative methods (e.g., GraphMAE and S2GAE), as well as popular graph neural networks (e.g., GCN and GAT). The open-sourced implementation of our GAugLLM is available at https://github.com/NYUSHCS/GAugLLM.

Ruidong Fan, Xiao Ouyang, Hong Tao, Chenping Hou

Due to the timeliness and uncertainty of data acquisition, label shift, which assumes that the source (training) and target (test) label distributions differ, occurs with the changing environment and reduces the generalization ability of traditional models. To correct the label shift, existing methods estimate the true label distribution by prediction of target data from a source classifier, which results in high variance, especially with large label shift. In this paper, we tackle this problem by proposing a novel approach termed as Label Shift Correction via Bidirectional Marginal Distribution Matching (BMDM). Our approach matchs the label and feature marginal distributions simultaneously to ensure the stability of estimated class proportions. We prove theoretically that there is a unique optimal solution, i.e., true target label distribution, for our approach under mild conditions, and an efficient optimization strategy is also proposed. On this basis, in multi-shot scenario where label distribution changes continuously, we extend BMDM by designing a new distribution matching mechanism and constructing a regularization term that constrains the direction of label distribution change. Extensive experimental results validate the effectiveness of our approach over existing state-of-the-arts methods.

Viet Duong, Qiong Wu 0008, Zhengyi Zhou, Hongjue Zhao, Chenxiang Luo, Eric Zavesky, Huaxiu Yao, Huajie Shao

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although GAMs can explain deep neural networks (DNNs) at the feature level, they require large numbers of model parameters and are prone to overfitting, making them hard to train and scale. Additionally, in real-world datasets with many features, the interpretability of feature-based explanations diminishes for humans. To tackle these issues, recent research has shifted towards concept-based interpretable methods. These approaches try to integrate concept learning as an intermediate step before making predictions, explaining the predictions in terms of human-understandable concepts. However, these methods require domain experts to extensively label concepts with relevant names and their ground-truth values. In response, we propose CAT, a novel interpretable Concept-bAsed Taylor additive model to simplify this process. CAT does not require domain experts to annotate concepts and their ground-truth values. Instead, it only requires users to simply categorize input features into broad groups, which can be easily accomplished through a quick metadata review. Specifically, CAT first embeds each group of input features into one-dimensional high-level concept representation, and then feeds the concept representations into a new white-box Taylor Neural Network (TaylorNet). The TaylorNet aims to learn the non-linear relationship between the inputs and outputs using polynomials. Evaluation results across multiple benchmarks demonstrate that CAT can outperform or compete with the baselines while reducing the need of extensive model parameters. Importantly, it can effectively explain model predictions through high-level concepts. Source code is available at github.com/vduong143/CAT-KDD-2024.

Avinava Dubey, Zhe Feng 0004, Rahul Kidambi, Aranyak Mehta, Di Wang 0005

We study an auction setting in which bidders bid for placement of their content within a summary generated by a large language model (LLM), e.g., an ad auction in which the display is a summary paragraph of multiple ads. This generalizes the classic ad settings such as position auctions to an LLM generated setting, which allows us to handle general display formats. We propose a novel factorized framework in which an auction module and an LLM module work together via a prediction model to provide welfare maximizing summary outputs in an incentive compatible manner. We provide a theoretical analysis of this framework and synthetic experiments to demonstrate the feasibility and validity of the system together with welfare comparisons.

Wenying Duan, Tianxiang Fang, Hong Rao, Xiaoxi He

In this paper, we present a novel method to significantly enhance the computational efficiency of Adaptive Spatial-Temporal Graph Neural Networks (ASTGNNs) by introducing the concept of the Graph Winning Ticket (GWT), derived from the Lottery Ticket Hypothesis (LTH). By adopting a pre-determined star topology as a GWT prior to training, we balance edge reduction with efficient information propagation, reducing computational demands while maintaining high model performance. Both the time and memory computational complexity of generating adaptive spatial-temporal graphs is significantly reduced from O(N2) to O(N). Our approach streamlines the ASTGNN deployment by eliminating the need for exhaustive training, pruning, and retraining cycles, and demonstrates empirically across various datasets that it is possible to achieve comparable performance to full models with substantially lower computational costs. Specifically, our approach enables training ASTGNNs on the largest scale spatial-temporal dataset using a single A6000 equipped with 48 GB of memory, overcoming the out-of-memory issue encountered during original training and even achieving state-of-the-art performance. Furthermore, we delve into the effectiveness of the GWT from the perspective of spectral graph theory, providing substantial theoretical support. This advancement not only proves the existence of efficient sub-networks within ASTGNNs but also broadens the applicability of the LTH in resource-constrained settings, marking a significant step forward in the field of graph neural networks. Code is available at https://anonymous.4open.science/r/paper-1430.

Haoran Duan 0002, Cheng Xie 0001, Linyu Li 0001

Self-supervised Heterogeneous Graph Representation (SSHGRL) learning is widely used in data mining. The latest SSHGRL methods normally use metapaths to describe the heterogeneous information (multiple relations and node types) to learn the heterogeneous graph representation and achieve impressive results. However, establishing metapaths requires lofty computational costs that are too high for the medium and large graphs. To this end, this paper proposes a Reserving-Masking-Reconstruction (RMR) model that can fully consider heterogeneous information without relying on the metapaths. In detail, we propose a reserving method to reserve to-be-masked nodes' (target nodes) information before graph masking. Second, we split the reserved graph into relation subgraphs according to the type of relations that require much less computational overheads than metapath. Then, the target nodes in each relation subgraph are randomly masked with minimal topology information loss. After, a novel reconstruction method is proposed to reconstruct the masked nodes on different relation subgraphs to establish the self-supervised signal. The proposed method requires low computational complexity and can establish a self-supervised signal without deeply changing the graph topology. Experimental results show the proposed method achieves state-of-the-art records on medium and large-scale heterogeneous graphs and competitive records on small-scale heterogeneous graphs. The code is available at https://github.com/DuanhaoranCC/RMR.

Yingpeng Du, Ziyan Wang, Zhu Sun 0001, Yining Ma 0001, Hongzhi Liu 0001, Jie Zhang 0002

Recently, much effort has been devoted to modeling users' multi-interests (aka multi-faceted preferences) based on their behaviors, aiming to accurately capture users' complex preferences. Existing methods attempt to model each interest of users through a distinct representation, but these multi-interest representations easily collapse into similar ones due to a lack of effective guidance. In this paper, we propose a generic multi-interest method for sequential recommendation, achieving disentangled representation learning of diverse interests technically and theoretically. To alleviate the collapse issue of multi-interests, we propose to conduct item partition guided by their likelihood of being co-purchased in a global view. It can encourage items in each group to focus on a discriminated interest, thus achieving effective disentangled learning of multi-interests. Specifically, we first prove the theoretical connection between item partition and spectral clustering, demonstrating its effectiveness in alleviating item-level and facet-level collapse issues that hinder existing disentangled methods. To efficiently optimize this problem, we then propose a Markov Random Field (MRF)-based method that samples small-scale sub-graphs from two separate MRFs, thus it can be approximated with a cross-entropy loss and optimized through contrastive learning. Finally, we perform multi-task learning to seamlessly align item partition learning with multi-interest modeling for more accurate recommendation. Experiments on three real-world datasets show that our method significantly outperforms state-of-the-art methods and can flexibly integrate with existing multi-interest models as a plugin to enhance their performances.