Cross-market recommendation (CMR) involves selling the same set of items across multiple nations or regions within a transfer learning framework. However, CMR's distinctive characteristics, including limited data sharing due to privacy policies, absence of user overlap, and a shared item set between markets present challenges for traditional recommendation methods. Moreover, CMR experiences market shifts, leading to differences in item popularity and user preferences among different markets. This study focuses on cross-market sequential recommendation (CMSR) and proposes the Cross-market Attention Transferring with Sequential Recommendation (CAT-SR) framework to address these challenges and market shifts. CAT-SR incorporates a pre-training strategy emphasizing item-item correlation, selective self-attention transferring for effective transfer learning, and query and key adapters for market-specific user preferences. Experimental results on real-world cross-market datasets demonstrate the superiority of CAT-SR, and ablation studies validate the benefits of its components across different geographical continents. CAT-SR offers a robust and adaptable solution for cross-market sequential recommendation. The code is available at https://github.com/ChenMetanoia/CATSR-KDD/.
论文检索
输入标题、作者或关键词，从 642 篇学术成果中精准定位
Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Adam rely on the bounded smoothness assumption, referred to as the L-smooth condition. Unfortunately, this assumption does not hold for many deep learning tasks. Moreover, we believe that this assumption obscures the true benefit of Adam, as the algorithm can adapt its update magnitude according to local smoothness. This important feature of Adam becomes irrelevant when assuming globally bounded smoothness. This paper studies the convergence of randomly reshuffled Adam (RR Adam) with diminishing learning rate, which is the major version of Adam adopted in deep learning tasks. We present the first convergence analysis of RR Adam without the bounded smoothness assumption. We demonstrate that RR Adam can maintain its convergence properties when smoothness is linearly bounded by the gradient norm, referred to as the (L0, L1)-smooth condition. We further compare Adam to SGD when both methods use diminishing learning rate. We refine the existing lower bound of SGD and show that SGD can be slower than Adam. To our knowledge, this is the first time that Adam and SGD are rigorously compared in the same setting and the advantage of Adam is revealed.
Traffic prediction is a crucial task in the Intelligent Transportation System (ITS), receiving significant attention from both industry and academia. Numerous spatio-temporal graph convolutional networks have emerged for traffic prediction and achieved remarkable success. However, these models have limitations in terms of generalization and scalability when dealing with Out-of-Distribution (OOD) graph data with both structural and temporal shifts. To tackle the challenges of spatio-temporal shift, we propose a framework called STONE by learning invariable node dependencies, which achieve stable performance in variable environments. STONE initially employs gated-transformers to extract spatial and temporal semantic graphs. These two kinds of graphs represent spatial and temporal dependencies, respectively. Then we design three techniques to address spatio-temporal shifts. Firstly, we introduce a Fréchet embedding method that is insensitive to structural shifts, and this embedding space can integrate loose position dependencies of nodes within the graph. Secondly, we propose a graph intervention mechanism to generate multiple variant environments by perturbing two kinds of semantic graphs without any data augmentations, and STONE can explore invariant node representation from environments. Finally, we further introduce an explore-to-extrapolate risk objective to enhance the variety of generated environments. We conduct experiments on multiple traffic datasets, and the results demonstrate that our proposed model exhibits competitive performance in terms of generalization and scalability.
In existing graph data, the connection relationships often exhibit uniform weights, leading to the model aggregating neighboring nodes with equal weights across various connection types. However, this uniform aggregation of diverse information diminishes the discriminability of node representations, contributing significantly to the over-smoothing issue in models. In this paper, we propose the Flexible Graph Neural Diffusion (FGND) model, incorporating latent class representation to address the misalignment between graph topology and node features. In particular, we combine latent class representation learning with the inherent graph topology to reconstruct the diffusion matrix during the graph diffusion process. We introduce the sim metric to quantify the degree of mismatch between graph topology and node features. By flexibly adjusting the dependency level on node features through the hyperparameter, we accommodate diverse adjacency relationships. The effective filtering of noise in the topology also allows the model to capture higher order information, significantly alleviating the over-smoothing problem. Meanwhile, we model the graphical diffusion process as a set of differential equations and employ advanced partial differential equation tools to obtain more accurate solutions. Empirical evaluations on five benchmarks reveal that our FGND model outperforms existing popular GNN methods in terms of both overall performance and stability under data perturbations. Meanwhile, our model exhibits superior performance in comparison to models tailored for heterogeneous graphs and those designed to address oversmoothing issues.
Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era. However, data streams often do not conform to the same distribution over time, leading to a phenomenon called concept drift. Since a fixed static model is unreliable for inferring concept-drifted data streams, establishing an adaptive mechanism for detecting concept drift is crucial. Current methods for concept drift detection primarily assume that the labels or error rates of downstream models are given and/or underlying statistical properties exist in data streams. These approaches, however, struggle to address high-dimensional data streams with intricate irregular distribution shifts, which are more prevalent in real-world scenarios. In this paper, we propose MCD-DD, a novel concept drift detection method based on maximum concept discrepancy, inspired by the maximum mean discrepancy. Our method can adaptively identify varying forms of concept drift by contrastive learning of concept embeddings without relying on labels or statistical properties. With thorough experiments under synthetic and real-world scenarios, we demonstrate that the proposed method outperforms existing baselines in identifying concept drifts and enables qualitative analysis with high explainability.
Feature interaction learning (FIL) focuses on capturing the complex relationships among multiple features for building predictive models, which is widely used in real-world tasks. Despite the research progress, existing FIL methods suffer from two major limitations. Firstly, they mainly model the feature interactions within a bounded order (e.g., small integer order) due to the exponential growth of the interaction terms. Secondly, the interaction order of each feature is often independently learned, which lacks the flexibility to capture the feature dependencies in varying contexts. To address these issues, we present Rotative Factorization Machines (RFM), based on the key idea that represents each feature as a polar angle in the complex plane. As such, the feature interactions are converted into a series of complex rotations, where the orders are cast into the rotation coefficients, thereby allowing for the learning of arbitrarily large order. Further, we propose a novel self-attentive rotation function that models the rotation coefficients through a rotation-based attention mechanism, which can adaptively learn the interaction orders under different interaction contexts. Moreover, it incorporates a modulus amplification network to learn the modulus of the complex features, which further enhances the expressive capacity. Our proposed approach provides a general FIL framework, and many existing models can be instantiated in this framework, e.g., factorization machines. In theory, it possesses more strong capacities to model complex feature relationships, and can learn arbitrary features from varied contexts. Extensive experiments conducted on five widely used datasets have demonstrated the effectiveness of our approach.
Continuous-Time Dynamic Graph (CTDG) precisely models evolving real-world relationships, drawing heightened interest in dynamic graph learning across academia and industry. However, existing CTDG models encounter challenges stemming from noise and limited historical data. Graph Data Augmentation (GDA) emerges as a critical solution, yet current approaches primarily focus on static graphs and struggle to effectively address the dynamics inherent in CTDGs. Moreover, these methods often demand substantial domain expertise for parameter tuning and lack theoretical guarantees for augmentation efficacy. To address these issues, we propose Conda, a novel latent diffusion-based GDA method tailored for CTDGs. Conda features a sandwich-like architecture, incorporating a Variational Auto-Encoder (VAE) and a conditional diffusion model, aimed at generating enhanced historical neighbor embeddings for target nodes. Unlike conventional diffusion models trained on entire graphs via pre-training, Conda requires historical neighbor sequence embeddings of target nodes for training, thus facilitating more targeted augmentation. We integrate Conda into the CTDG model and adopt an alternating training strategy to optimize performance. Extensive experimentation across six widely used real-world datasets showcases the consistent performance improvement of our approach, particularly in scenarios with limited historical data.
Incomplete multi-view clustering (IMVC) aims to cluster multi-view data that are only partially available. This poses two main challenges: effectively leveraging multi-view information and mitigating the impact of missing views. Prevailing solutions employ cross-view contrastive learning and missing view recovery techniques. However, they either neglect valuable complementary information by focusing only on consensus between views or provide unreliable recovered views due to the absence of supervision. To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC). URRL-IMVC directly learns a unified embedding that is robust to view missing conditions by integrating information from multiple views and neighboring samples. Firstly, to overcome the limitations of cross-view contrastive learning, URRL-IMVC incorporates an attention-based auto-encoder framework to fuse multi-view information and generate unified embeddings. Secondly, URRL-IMVC directly enhances the robustness of the unified embedding against view-missing conditions through KNN imputation and data augmentation techniques, eliminating the need for explicit missing view recovery. Finally, incremental improvements are introduced to further enhance the overall performance, such as the Clustering Module and the customization of the Encoder. We extensively evaluate the proposed URRL-IMVC framework on various benchmark datasets, demonstrating its state-of-the-art performance. Furthermore, comprehensive ablation studies are performed to validate the effectiveness of our design.
A fundamental task in causal inference is estimating the effect of a distribution shift in the treatment variable. We refer to this problem as shift-response function (SRF) estimation. Existing neural network methods for causal inference lack theoretical guarantees and practical implementations for SRF estimation. In this paper, we introduce Targeted Regularization for Exposure Shifts with Neural Networks (TRESNET), a method to estimate SRFs with robustness and efficiency guarantees. Our contributions are twofold. First, we propose a targeted regularization loss for neural networks with theoretical properties that ensure double robustness and asymptotic efficiency specific to SRF estimation. Second, we extend targeted regularization to support loss functions from the exponential family to accommodate non-continuous outcome distributions (e.g., discrete counts). We conduct benchmark experiments demonstrating TRESNET's broad applicability and competitiveness. We then apply our method to a key policy question in public health to estimate the causal effect of revising the US National Ambient Air Quality Standards (NAAQS) for PM 2.5 from 12 μg/m3 to 9 μg/m3. This change has been recently proposed by the US Environmental Protection Agency (EPA). Our goal is to estimate the reduction in deaths that would result from this anticipated revision using data consisting of 68 million individuals across the U.S.
Quantifying the value of data within a machine learning workflow can play a pivotal role in making more strategic decisions in machine learning initiatives. The existing Shapley value based frameworks for data valuation in machine learning are computationally expensive as they require considerable amount of repeated training of the model to obtain the Shapley value. In this paper, we introduce an efficient data valuation framework EcoVal, to estimate the value of data for machine learning models in a fast and practical manner. Instead of directly working with individual data sample, we determine the value of a cluster of similar data points. This value is further propagated amongst all the member cluster points. We show that the overall value of the data can be determined by estimating the intrinsic and extrinsic value of each data. This is enabled by formulating the performance of a model as aproduction function, a concept which is popularly used to estimate the amount of output based on factors like labor and capital in a traditional free economic market. We provide a formal proof of our valuation technique and elucidate the principles and mechanisms that enable its accelerated performance. We demonstrate the real-world applicability of our method by showcasing its effectiveness for both in-distribution and out-of-sample data. This work addresses one of the core challenges of efficient data valuation at scale in machine learning models. The code is available at https://github.com/respai-lab/ecoval.
In recent years, graph contrastive learning (GCL) has received increasing attention in recommender systems due to its effectiveness in reducing bias caused by data sparsity. However, most existing GCL models rely on heuristic approaches and usually assume entity independence when constructing contrastive views. We argue that these methods struggle to strike a balance between semantic invariance and view hardness across the dynamic training process, both of which are critical factors in graph contrastive learning. To address the above issues, we propose a novel GCL-based recommendation framework RGCL, which effectively maintains the semantic invariance of contrastive pairs and dynamically adapts as the model capability evolves through the training process. Specifically, RGCL first introduces decision boundary-aware adversarial perturbations to constrain the exploration space of contrastive augmented views, avoiding the decrease of task-specific information. Furthermore, to incorporate global user-user and item-item collaboration relationships for guiding on the generation of hard contrastive views, we propose an adversarial-contrastive learning objective to construct a relation-aware view-generator. Besides, considering that unsupervised GCL could potentially narrower margins between data points and the decision boundary, resulting in decreased model robustness, we introduce the adversarial examples based on maximum perturbations to achieve margin maximization. We also provide theoretical analyses on the effectiveness of our designs. Through extensive experiments on five public datasets, we demonstrate the superiority of RGCL compared against twelve baseline models.
Heterogeneous graph learning aims to capture complex relationships and diverse relational semantics among entities in a heterogeneous graph to obtain meaningful representations for nodes and edges. Recent advancements in heterogeneous graph neural networks (HGNNs) have achieved state-of-the-art performance by considering relation heterogeneity and using specialized message functions and aggregation rules. However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets. Most of these frameworks follow the "pre-train" and "fine-tune" paradigm on the same dataset, which restricts their capacity to adapt to new and unseen data. This raises the question: "Can we generalize heterogeneous graph models to be well-adapted to diverse downstream learning tasks with distribution shifts in both node token sets and relation type heterogeneity?" To tackle those challenges, we propose HiGPT, a general large graph model with Heterogeneous graph instruction-tuning paradigm. Our framework enables learning from arbitrary heterogeneous graphs without the need for any fine-tuning process from downstream datasets. To handle distribution shifts in heterogeneity, we introduce an in-context heterogeneous graph tokenizer that captures semantic relationships in different heterogeneous graphs, facilitating model adaptation. We incorporate a large corpus of heterogeneity-aware graph instructions into our HiGPT, enabling the model to effectively comprehend complex relation heterogeneity and distinguish between various types of graph tokens. Furthermore, we introduce the Mixture-of-Thought (MoT) instruction augmentation paradigm to mitigate data scarcity by generating diverse and informative instructions. Through comprehensive evaluations conducted in various settings, our proposed framework demonstrates exceptional performance in terms of generalization performance, surpassing current leading benchmarks. We make our model implementation openly available, along with comprehensive details at: https://github.com/HKUDS/HiGPT.
The graph classification problem has been widely studied; however, achieving an interpretable model with high predictive performance remains a challenging issue. This paper proposes an interpretable classification algorithm for attributed graph data, called LAGRA (Learning Attributed GRAphlets). LAGRA learns importance weights for small attributed subgraphs, called attributed graphlets (AGs), while simultaneously optimizing their attribute vectors. This enables us to obtain a combination of subgraph structures and their attribute vectors that strongly contribute to discriminating different classes. A significant characteristics of LAGRA is that all the subgraph structures in the training dataset can be considered as a candidate structures of AGs. This approach can explore all the potentially important subgraphs exhaustively, but obviously, a naïve implementation can require a large amount of computations. To mitigate this issue, we propose an efficient pruning strategy by combining the proximal gradient descent and a graph mining tree search. Our pruning strategy can ensure that the quality of the solution is maintained compared to the result without pruning. We empirically demonstrate that LAGRA has superior or comparable prediction performance to the standard existing algorithms including graph neural networks, while using only a small number of AGs in an interpretable manner.
Traditional Neural Processes (NPs) and their variants aim to learn relationships between context sample points but do not consider multi-level information, resulting in a limited ability to learn complex distributions.This paper draws inspiration from features such as the hierarchical nature and interpretability of tree-like structures. This paper proposes a Hierarchical Linear Symbolized Tree-structured Neural Processes (HLNPs) architecture. This framework utilizes variables to build a top-down hierarchical linear symbolized tree-structured network architecture, enhancing positional representation information in a hierarchical manner along the deterministic path. In the latent distribution, the hierarchical linear symbolized tree-structured network approximates functions discretely through a layered approach. By decomposing the latent complex distribution into several simpler sub-problems using sum and product symbols, the upper bound of optimization is thereby increased. The tree structure discretizes variables to capture model uncertainty in the form of entropy. This approach also imparts a causal effect to the HLNPs model. Finally, we demonstrate the effectiveness of the HLNPs models for 1D data, Bayesian optimization, and 2D data.
Social Recommendation (SR) typically exploits neighborhood influence in the social network to enhance user preference modeling. However, users' intricate social behaviors may introduce noisy social connections for user modeling and harm the models' robustness. Existing solutions to alleviate social noise either filter out the noisy connections or generate new potential social connections. Due to the absence of labels, the former approaches may retain uncertain connections for user preference modeling while the latter methods may introduce additional social noise. Through data analysis, we discover that (1) social noise likely comes from the connected users with low preference similarity; and (2) Opinion Leaders (OLs) play a pivotal role in influence dissemination, surpassing high-similarity neighbors, regardless of their preference similarity with trusting peers. Guided by these observations, we propose a novel Self-Supervised Denoising approach through Independent Cascade Graph Augmentation, for more robust SR. Specifically, we employ the independent cascade diffusion model to generate an augmented graph view, which traverses the social graph and activates the edges in sequence to simulate the cascading influence spread. To steer the augmentation towards a denoised social graph, we (1) introduce a hierarchical contrastive loss to prioritize the activation of OLs first, followed by high-similarity neighbors, while weakening the low-similarity neighbors; and (2) integrate an information bottleneck based contrastive loss, aiming to minimize mutual information between original and augmented graphs yet preserve sufficient information for improved SR. Experiments conducted on two public datasets demonstrate that our model outperforms the state-of-the-art while also exhibiting higher robustness to different extents of social noise.
This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions. Traditional graph learning algorithms, based on the assumption of uniform distribution between training and test data, falter in real-world scenarios where this assumption fails, resulting in suboptimal performance. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks trained through Stochastic Gradient Descent (SGD), which prefer simpler features over more complex yet equally or more predictive ones. This bias leads to a reliance on spurious correlations, adversely affecting OOD performance in various tasks such as image recognition, natural language understanding, and graph classification. Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, our study introduces a new learning paradigm for graph OOD issue. We propose DIVE, training a collection of models to focus on all label-predictive subgraphs by encouraging the models to foster divergence on the subgraph mask, which circumvents the limitation of a model solely focusing on the subgraph corresponding to simple structural patterns. Specifically, we employs a regularizer to punish overlap in extracted subgraphs across models, thereby encouraging different models to concentrate on distinct structural patterns. Model selection for robust OOD performance is achieved through validation accuracy. Tested across four datasets from GOOD benchmark and one dataset from DrugOOD benchmark, our approach demonstrates significant improvement over existing methods, effectively addressing the simplicity bias and enhancing generalization in graph machine learning.
Next location prediction is a crucial task in human mobility modeling, and is pivotal for many downstream applications like location-based recommendation and transportation planning. Although there has been a large body of research tackling this problem, the usefulness of user preference and temporal regularity remains underrepresented. Specifically, previous studies usually neglect the explicit user preference information entailed from human trajectories and fall short in utilizing the arrival time of next location, as a key determinant on next location. To address these limitations, we propose a Multi-Context aware Location Prediction model (MCLP) to predict next locations for individuals, where it explicitly models user preference and the next arrival time as context. First, we utilize a topic model to extract user preferences for different types of locations from historical human trajectories. Second, we develop an arrival time estimator to construct a robust arrival time embedding based on the multi-head attention mechanism. The two components provide pivotal contextual information for the subsequent prediction. Finally, we utilize the Transformer architecture to mine sequential patterns and integrate multiple contextual information to predict the next locations. Experimental results on two real-world mobility datasets show that our proposed MCLP outperforms baseline methods.
Large Language Models (LLMs) have demonstrated efficacy in various domains, but deploying these models is economically challenging due to extensive parameter counts. Numerous efforts have been dedicated to reducing the parameter count of these models without compromising performance, employing a technique known as model pruning. Conventional pruning methods assess the significance of weights within individual layers and typically apply uniform sparsity levels across all layers, potentially neglecting the varying significance of each layer. To address this oversight, we first propose a dual-assessment driven pruning strategy that employs both intra-layer metric and global performance metric to comprehensively evaluate the impact of pruning. Then our method leverages an iterative optimization algorithm to find the optimal layer-wise sparsity distribution, thereby minimally impacting model performance. Extensive benchmark evaluations on state-of-the-art LLM architectures such as LLaMAv2 and OPT across a variety of NLP tasks demonstrate the effectiveness of our approach. When applied to the LLaMaV2-7B model with an overall pruning sparsity of 80%, our method achieves a 50% reduction in perplexity compared to the benchmark. The results indicate that our method significantly outperforms existing state-of-the-art methods in preserving performance after pruning.
The recent advancements in Traffic Signal Control (TSC) have highlighted the potential of Reinforcement Learning (RL) as a promising solution to alleviate traffic congestion. Current research in this area primarily concentrates on either online or offline learning strategies, aiming to create optimized policies for specific cities. Nevertheless, the transferability of these policies to new cities is impeded by constraints such as the limited availability of high-quality data and the expensive and risky exploration process. To this end, in this paper, we present an innovative cross-city Traffic Signal Control (TSC) paradigm called CrossLight. Our approach involves meta training using offline data from source cities and adaptively fine-tuning in the target city. This novel methodology aims to address the challenges of transferring TSC policies across different cities effectively. In our proposed approach, we start by acquiring meta-decision pattern knowledge through trajectory dynamics reconstruction via pre-training in source cities. To address disparities in road network topologies between cities, we dynamically construct city topological structures based on the extracted meta-knowledge during the offline meta-training phase. These structures are then used to distill pattern-structure aware representations of decision trajectories from the source cities. To identify effective initial parameters for the learnable components, we employ the Model-Agnostic Meta-Learning (MAML) framework, a popular meta-learning approach. During adaptive fine-tuning in the target city, we introduce a replay buffer that is iteratively updated using online interactions with a rank and filter mechanism. This mechanism, along with a carefully designed exploration strategy, ensures a balance between exploitation and exploration, thereby fostering both the diversity and quality of the trajectories for fine-tuning. Finally, extensive experiments across four cities validate that CrossLight achieves comparable performance in new cities with minimal fine-tuning iterations, surpassing both existing online and offline methods. This success underscores that our CrossLight framework emerges as a groundbreaking and potent paradigm, offering a feasible and effective solution to the intelligent transportation community.
The forest matrix plays a crucial role in network science, opinion dynamics, and machine learning, offering deep insights into the structure of and dynamics on networks. In this paper, we study the problem of querying entries of the forest matrix in evolving graphs, which more accurately represent the dynamic nature of real-world networks compared to static graphs. To address the unique challenges posed by evolving graphs, we first introduce two approximation algorithms, SFQ and SFQPlus, for static graphs. SFQ employs a probabilistic interpretation of the forest matrix, while SFQPlus incorporates a novel variance reduction technique and is theoretically proven to offer enhanced accuracy. Based on these two algorithms, we further devise two dynamic algorithms centered around efficiently maintaining a list of spanning converging forests. This approach ensures O(1) runtime complexity for updates, including edge additions and deletions, as well as for querying matrix elements, and provides an unbiased estimation of forest matrix entries. Finally, through extensive experiments on various real-world networks, we demonstrate the efficiency and effectiveness of our algorithms. Particularly, our algorithms are scalable to massive graphs with more than forty million nodes.