In this paper, we introduce and study a novel cohesive subgraph model, named k-trine, to address the defects in the classical k-core and k-truss models. Our analysis shows that the k-trine is a more feasible model for capturing cohesive subgraphs by containing the strongly connected vertices. We analyze the theoretical properties of k-trine and propose efficient algorithms to compute the k-trine. Particularly, we design batch processing algorithms to update the decomposition of k-trine against highly dynamic graphs. Extensive experiments on real-world networks validate the effectiveness of the k-trine model and the efficiency of our algorithms.
论文检索
输入标题、作者或关键词，从 844 篇学术成果中精准定位
已筛选
KDD 2025
844篇论文
第 42 / 43 页
Modeling opinion dynamics in social networks has been the focus of multiple disciplines in recent decades. Previous studies have often modeled the opinion dynamics as a discrete and homogeneous process, neglecting its continuous and complex nature. To fill this gap, we propose a Bi-Dynamics Graph Ordinary Differential Equation (BDG-ODE) framework, which models complex opinion dynamics as the result of two dynamical processes: the evolution of positive and negative opinions. The proposed model incorporates a dual opinion encoder that processes positive and negative opinions independently. Furthermore, the temporal opinion evolution is modeled through bidirectional graph ordinary differential equations, which allows the model to capture the changes in opinion in continuous time. We introduce an opinion synthesis decoder that effectively maps the evolved representations from the latent space back to the opinion space. Extensive experiments conducted on six datasets with varying characteristics highlight the superiority of BDG-ODE in forecasting opinion evolution within social networks. It achieved an average accuracy improvement of 23.16%, an average enhancement of 29.46% in the F1 score, and an average mean square error of difference improvement of 90. 30%, and an average correlation coefficient improvement of 45.93%, significantly outperforming eight state-of-the-art models. The code for reproduction is available: https://github.com/tsinghua-fib-lab/Bi-Dynamic-Graph-ODE-for-Opinion-Evolution.
Point processes offer a versatile framework for sequential event modeling. However, the computational challenges and constrained representational power of the existing point process models have impeded their potential for wider applications. This limitation becomes especially pronounced when dealing with event data that is associated with multi-dimensional or high-dimensional marks such as texts or images. To address this challenge, this study proposes a novel event-generation framework for modeling point processes with high-dimensional marks. We aim to capture the distribution of events without explicitly specifying the conditional intensity or probability density function. Instead, we use a conditional generator that takes the history of events as input and generates the high-quality subsequent event that is likely to occur given the prior observations. The proposed framework offers a host of benefits, including considerable representational power to capture intricate dynamics in multi- or even high-dimensional event space, as well as exceptional efficiency in learning the model and generating samples. Our numerical results demonstrate superior performance compared to other state-of-the-art baselines.
Contemporary Vision-Language Models (VLMs) such as CLIP offer an attractive zero-shot classification functionality facilitated by large-scale vision-language pre-training. However, they remain vulnerable to adversarial attacks, a critical security threat in realistic deployment. Adversarially robust fine-tuning provides generalizable robustness on new datasets while preserving natural performance by fine-tuning the pre-trained models. Fine-tuning robust CLIP typically relies on adversaries generated solely from the vision branch. However, this singular focus on the vision modality, coupled with static text prompts used as fixed category prototypes, limits the robustness achieved through dual-modality fine-tuning. We observe for CLIP fine-tuning that zero-shot adversarial robustness improves when we (i) stabilize the modality gap (a phenomenon where image and text features occupy different feature space regions) and (ii) lower/stabilize gradient norms. Both these steps enjoy further improvement of robustness if one fine-tunes with both visual and text adversaries. For both modalities, we leverage (i) the maximization of an effective rank of features and (ii) noise modulation of features. We show that maximizing the effective rank helps lower and stabilize the modality gap over adversaries with varying perturbation radii. The noise modulation of features, achieved by the so-called count sketching, lowers/stabilizes gradient norms. We outperform the state of the art on 15 datasets. We provide the first insights into the effects of modality gap & gradient norms in VLM fine-tuning.
In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers. However, the absence of user identifiers restricts the ability of cloud-based language models to provide personalized services, which are essential for catering to diverse user needs. The trivial method of replacing an explicit user identifier with a static user embedding as model input still compromises data anonymization. In this work, we propose to let each mobile device maintain a user-specific distribution to dynamically generate user embeddings, thereby breaking the one-to-one mapping between an embedding and a specific user. We further theoretically demonstrate that to prevent the cloud from tracking users via uploaded embeddings, the local distributions of different users should either be derived from a linearly dependent space to avoid identifiability or be close to each other to prevent accurate attribution. Evaluation on both public and industrial datasets using different language models reveals a remarkable improvement in accuracy from incorporating anonymous user embeddings, while preserving real-time inference requirement.
Graph Neural Networks (GNNs) play a pivotal role in graph-based tasks for their proficiency in representation learning. Among the various GNN methods, spectral GNNs employing polynomial filters have shown promising performance on tasks involving both homophilous and heterophilous graph structures. However, The scalability of spectral GNNs on large graphs is limited because they learn the polynomial coefficients through multiple forward propagation executions during forward propagation. Existing works have attempted to scale up spectral GNNs by eliminating the linear layers on the input node features, a change that can disrupt end-to-end training, potentially impact performance, and become impractical with high-dimensional input features. To address the above challenges, we propose ''Spectral Graph Neural Networks with Laplacian Sparsification (SGNN-LS)'', a novel graph spectral sparsification method to approximate the propagation patterns of spectral GNNs. We prove that our proposed method generates Laplacian sparsifiers that can approximate both fixed and learnable polynomial filters with theoretical guarantees. Our method allows the application of linear layers on the input node features, enabling end-to-end training as well as the handling of raw text features. We conduct an extensive experimental analysis on datasets spanning various graph scales and properties to demonstrate the superior efficiency and effectiveness of our method. The results show that our method yields superior results in comparison with the corresponding approximated base models, especially on dataset Ogbn-papers100M(111M nodes, 1.6B edges) and MAG-scholar-C (2.8M features).
Human trajectory data, which plays a crucial role in various applications such as crowd management and epidemic prevention, is challenging to obtain due to practical constraints and privacy concerns. In this context, synthetic human trajectory data is generated to simulate as close as possible to real-world human trajectories, often under summary statistics and distributional similarities. However, these similarities oversimplify complex human mobility patterns (a.k.a. ''Datasaurus''), resulting in intrinsic biases in both generative model design and benchmarks of the generated trajectories. Against this background, we propose MIRAGE, a huMan-Imitative tRAjectory GenErative model designed as a neural Temporal Point Process integrating an Exploration and Preferential Return model. It imitates the human decision-making process in trajectory generation, rather than fitting any specific statistical distributions as traditional methods do, thus avoiding the Datasaurus issue. We also propose a comprehensive task-based evaluation protocol beyond Datasaurus to systematically benchmark trajectory generative models on four typical downstream tasks, integrating multiple techniques and evaluation metrics for each task, to assess the ultimate utility of the generated trajectories. We conduct a thorough evaluation of MIRAGE on three real-world user trajectory datasets against a sizeable collection of baselines. Results show that compared to the best baselines, MIRAGE-generated trajectory data not only achieves the best statistical and distributional similarities with 59.0-67.7% improvement, but also yields the best performance in the task-based evaluation with 10.9-33.4% improvement. A series of ablation studies also validate the key design choices of MIRAGE.
The potential harms of algorithmic decisions have ignited algorithmic fairness as a central topic in computer science. One of the fundamental problems in computer science is Set Cover, which has numerous applications with societal impacts, such as assembling a small team of individuals that collectively satisfy a range of expertise requirements. However, despite its broad application spectrum and significant potential impact, set cover has yet to be studied through the lens of fairness. Therefore, in this paper, we introduce Fair Set Cover, which aims not only to cover with a minimum-size set but also to satisfy demographic parity in its selection of sets. To this end, we develop multiple versions of fair set cover, study their hardness, and devise efficient approximation algorithms for each variant. Notably, under certain assumptions, our algorithms always guarantee zero-unfairness, with only a small increase in the approximation ratio compared to regular set cover. Furthermore, our experiments on various data sets and across different settings confirm the negligible price of fairness, as (a) the output size increases only slightly (if any) and (b) the time to compute the output does not significantly increase.
We study the problem of efficiently approximating the effective resistance (ER) on undirected graphs, where ER is a widely used node proximity measure with applications in graph spectral sparsification, multi-class graph clustering, network robustness analysis, graph machine learning, and more. Specifically, given any nodes s and t in an undirected graph G, we aim to efficiently estimate the ER value R(s,t) between nodes s and t, ensuring a small absolute error ε. The previous best algorithm for this problem has a worst-case computational complexity of Õ(Lmax3/ε2d2), where the value of Lmax depends on the mixing time of random walks on G, d = mind(s), d(t), and d(s), d(t) denote the degrees of nodes s and t, respectively. We improve this complexity to Õ ( min Lmax7/3/ε2/3, Lmax3/ε2d2,mLmax ), achieving a theoretical improvement of Õ (maxLmax2/3/ε4/3d2,1, Lmax2/ε2d2m2) over previous results. Here, m denotes the number of edges. Given that Lmax is often very large in real-world networks (e.g., Lmax > 104), our improvement on Lmax is significant, especially for real-world networks. We also conduct extensive experiments on real-world and synthetic graph datasets to empirically demonstrate the superiority of our method. The experimental results show that our method achieves a 10× to 1000× speedup in running time while maintaining the same absolute error compared to baseline methods.
When modifying existing policies in high-risk settings, it is often necessary to ensure with high certainty that the newly proposed policy improves upon a baseline, such as the status quo. In this work, we consider the problem of safe policy improvement, where one only adopts a new policy if it is deemed to be better than the specified baseline with at least a pre-specified probability. We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements, so too often they must revert to the baseline to maintain safety. We overcome these issues by leveraging the most powerful safety test in the asymptotic regime and allowing for multiple candidates to be tested for improvement over the baseline. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level, even in moderate sample sizes. We present CSPI and CSPI-MT, two novel algorithms for selecting cutoff(s) to maximize the policy improvement from baseline. We demonstrate through both synthetic and external datasets that our approaches improve both the detection rates of safe policies and the realized improvement, particularly under stringent safety requirements and low signal-to-noise conditions.
Given an extensive, semi-infinite collection of multivariate coevolving data sequences (e.g., sensor/web activity streams) whose observations influence each other, how can we discover the time-changing cause-and-effect relationships in co-evolving data streams? How efficiently can we reveal dynamical patterns that allow us to forecast future values? In this paper, we present a novel streaming method, ModePlait, which is designed for modeling such causal relationships (i.e., time-evolving causality) in multivariate co-evolving data streams and forecasting their future values. The solution relies on characteristics of the causal relationships that evolve over time in accordance with the dynamic changes of exogenous variables. ModePlait has the following properties: (a) Effective: it discovers the time-evolving causality in multivariate co-evolving data streams by detecting the transitions of distinct dynamical patterns adaptively. (b) Accurate: it enables both the discovery of time-evolving causality and the forecasting of future values in a streaming fashion. (c) Scalable: our algorithm does not depend on data stream length and thus is applicable to very large sequences. Extensive experiments on both synthetic and real-world datasets demonstrate that our proposed model outperforms state-of-the-art methods in terms of discovering the time-evolving causality as well as forecasting.
Micro-video popularity prediction (MVPP) plays a crucial role in numerous real-world applications, including product marketing and recommendation systems. While existing methodologies predominantly assume complete modalities during multimodal learning, this assumption often fails to hold in practical scenarios due to various constraints, such as privacy concerns or data integrity issues. To address this limitation, we propose SCRAG, a novel Self-Correlation Retrieval-Augmented Generative framework designed to enhance missing-modality robustness in MVPP. SCRAG operates in a retrieval-guided generation manner that explores relevant knowledge to enhance the reconstruction of missing content, which consists of two primary components: (1) a self-correlation retriever and (2) a multimodal mixture-of-experts generator. It first acquires instances pertinent to the missing content through multimodal prompt alignment. Subsequently, the generator extracts contextual modal information from the retrieved context-rich instances. By learning the joint distribution of modalities, SCRAG effectively recovers missing content and addresses the modal heterogeneity challenge inherent in cross-modal generation approaches. Extensive experiments conducted on three real-world datasets demonstrate that SCRAG consistently outperforms state-of-the-art baselines, underscoring its effectiveness in handling incomplete modalities and improving the accuracy of micro-video popularity prediction.
The rise of link recommendation systems in online social networks has sparked significant research interest in strategically adding links to enhance social influence. This paper delves into the influence maximization with augmentation (IMA) problem that aims to add k edges connecting seed nodes and ordinary nodes to boost the influence propagation of the given seed set. IMA is a monotone submodular maximization problem so that the greedy algorithm provides a (1-1/e-ε)-approximate solution, where ε is an error term caused by the intractable nature of influence spread computation. Previous work often utilizes an unbiased estimator that relies on the chosen edges for influence estimation, resulting in non-submodular estimate with respect to edge selection. To ensure the overall error being bounded by ε, such an estimator requires Θ(ε/k) multiplicative error for each estimation, incurring prohibitive overhead. Meanwhile, some other work approximates IMA via conventional influence maximization (IM) on an augmented graph by adding a new node for every edge candidate, leading to heavy extra sampling due to a significant increase in graph size. To address these challenges, we design a novel unbiased estimator on the original graph that is independent of the chosen edges by leveraging the tractability of one-hop influence computation. We show that the estimate via our estimator is submodular so that it enables the estimate of all k edges in a whole with a bounded estimation error of Θ(ε), saving O(k2) time compared to the chosen-edge-dependent estimator while retaining the same graph size. Moreover, we propose several techniques based on the properties of our estimator to further speed up the greedy selection. Putting it together, we develop a scalable algorithm for the IMA problem, namely ScaLIM. Finally, extensive experiments are conducted to validate the effectiveness and efficiency of our proposed approach, e.g., ScaLIM is faster than baselines by nearly two orders of magnitude.
Signed graphs capture both positive and negative relationships between entities, with balance being a fundamental concept. In these graphs, a vertex is considered balanced if all cycles it belongs to contain an even number of negative edges. On the other hand, unbalanced vertices often experience cognitive dissonance and emotional disturbance, motivating efforts to modify the graph to achieve balance for these vertices. Yet, most existing research emphasizes global balance, focusing on lengthy cycles that represent distant interactions. In contrast, this paper shifts the focus to local balance, where a vertex is deemed balanced when the triangles (length-three cycles) it participates in are positive, reflecting more immediate relationships. Building on this, we introduce the Locally Balancing Signed Graph (LBS) problem, which aims to maximize the number of locally balanced vertices through graph modification. Despite the NP-hard nature of the LBS problem and the absence of properties such as monotonicity and submodularity, our novel greedy method effectively addresses these challenges. We further enhance our method with dynamic computation and pruning techniques. Extensive experiments show the efficacy of our greedy method in solving the LBS problem and underscore the substantial runtime reductions achieved through our optimization techniques.
Medication recommendation (MR) has undergone rapid advancement in recent years, driven by its significant practical implications in healthcare. However, such high-risk scenarios still experience two critical yet overlooked challenges: the prevalent overconfidence in raw confidence for individual medications and the lack of a robust solution for confidence quantification in medication combinations. This paper represents the first in-depth study addressing this gap. We introduce two innovative methodologies tailored to the unique challenges of MR scenarios: 1) A discernible binning-based calibration method with theoretical guarantees for the confidence of individual medication. It guarantees distinct accuracy levels between adjacent bins and maintains consistent statistical reliability across calibration and test data, enabling calibrated confidence to reflect the correctness of medication recommendations distinctively. 2) A sample-based quantification method for the set confidence of medication combination, which is applicable for various existing performance metrics in MR. Utilizing representative deep MR models as backbones and conducting extensive experiments on the widely recognized MIMIC datasets, we empirically prove the effectiveness and robustness of our proposed methods. Our approaches not only improve the reliability of MR but also pave the way for more informed decision-making in clinical settings.
In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional Graph Neural Networks (GNNs) often struggle in such scenarios, as they tend to overfit to majority classes while underrepresenting minority classes. Existing solutions, which either prioritize nodes based on class size or synthesize new nodes for minority classes, often fall short of effectively addressing this imbalance issue. This paper introduces a novel approach to class-imbalanced node classification by utilizing a balanced meta-set for importance measurement, where a training node is considered significant if it enhances model performance under an unbiased setting. Our method identifies important nodes that can counteract class imbalance and utilizes them for model training, allowing for fine-grained and dynamic node selection throughout the training process. We theoretically derive a formula to directly assess node importance, reducing computational overhead and providing an intuitive threshold for node selection. Guided by this metric, we develop a novel framework that filters valuable labeled, unlabeled, and synthetic nodes that enhance model performance in an unbiased context. A key advantage of this framework is its separation of the synthetic node generation process from the filtering process, ensuring compatibility with various node generation techniques. Furthermore, we introduce a strategy to construct a high-quality meta-set that closely approximates the overall feature distribution, ensuring robust representation of each class. We evaluate our framework, NodeImport, across multiple benchmark datasets using popular GNN architectures, demonstrating its superiority over state-of-the-art baselines. Our results highlight the flexibility and effectiveness of the framework in mitigating class imbalance, leading to improved node classification outcomes. The source code is available at https://github.com/NanChanNN/NodeImport.
Leveraging graph structures for time-series forecasting has garnered significant attention due to their effective relationship modeling between nodes and their associated time-series. However, in scenarios entities communicate in a broadcasting manner, graph models fall short of pairwise modeling. Hypergraph models address this by capturing beyond-pairwise interactions among node time-series. Nevertheless, most hypergraph models overlook the dynamics between nodes and their incident hyperedges, assuming constant node-hyperedge connections. In this paper, we introduce a novel model, Probabilistic Hypergraph Recurrent Neural Networks (PHRNN), which leverages node-hyperedge dynamics for accurate time-series forecasting. PHRNN associates each time-series with a node and models node interactions on a hypergraph, capturing beyond-pairwise interactions. Moreover, PHRNN learns a probabilistic hypergraph in which node-hyperedge relations are modeled as probabilistic distributions instead of fixed values, capturing dynamic node-hyperedge relations. PHRNN further integrates a prior knowledge KNN hypergraph as regularization when learning the probabilistic hypergraph structure. To the best of our knowledge, PHRNN is the first time-series forecasting model that incorporates hypergraph modeling and probabilistic relationship modeling. Forecasting results from extensive experiments show that PHRNN outperforms state-of-the-art graph and hypergraph baselines on real-world datasets.
In online marketing, the advertisers aim to balance achieving high volumes and high profitability. The companies' business units address this tradeoff by maximizing the volumes while guaranteeing a minimum Return On Investment (ROI) level. Such a task can be naturally modeled as a combinatorial optimization problem subject to ROI and budget constraints that can be solved online. In this picture, the learner's uncertainty over the constraints' parameters plays a crucial role since the algorithms' exploration choices might lead to their violation during the entire learning process. Such violations represent a major obstacle to adopting online techniques in real-world applications. Thus, controlling the algorithms' exploration during learning is paramount to making humans trust online learning tools. This paper studies the nature of both optimization and learning problems. In particular, we show that the learning problem is inapproximable within any factor (unless P = NP) and provide a pseudo-polynomial-time algorithm to solve its discretized version. Subsequently, we prove that no online learning algorithm can violate the (ROI or budget) constraints a sublinear number of times during the learning process while guaranteeing a sublinear regret. We provide the GCB algorithm that guarantees sublinear regret at the cost of a linear number of constraint violations and GCBsafe that guarantees w.h.p.a constant upper bound on the number of constraint violations at the cost of a linear regret. Moreover, we designed GCBsafe(ψ, φ), which guarantees both sublinear regret and safety w.h.p. at the cost of accepting tolerances ψ and φ in the satisfaction of the ROI and budget constraints, respectively. Finally, we provide experimental results to compare the regret and constraint violations of GCB, GCBsafe, and GCBsafe(ψ, φ).
In recent years, graph anomaly detection has gained considerable attention and has found extensive applications in various domains such as social, financial, and communication networks. However, anomalies in graph-structured data present unique challenges, including label scarcity, ill-defined anomalies, and varying anomaly types, making supervised or semi-supervised methods unreliable. Researchers often adopt unsupervised approaches to address these challenges, assuming that anomalies deviate significantly from the normal data distribution. Yet, when the available data is insufficient, capturing the normal distribution accurately and comprehensively becomes difficult. To overcome this limitation, we propose to utilize external graph data (i.e., graph data in the wild) to help anomaly detection tasks. This naturally raises the question: How can we use external data to help graph anomaly detection task? To answer this question, we propose a novel framework Wild-GAD. Our framework is built upon a unified database, UniWildGraph, which comprises a large and diverse collection of graph data with broad domain coverage, ample data volume, and a unified feature space. We further develop selection criteria based on representativity and diversity to identify the most suitable external data for each anomaly detection task. Extensive experiments on six real-world test datasets demonstrate the effectiveness of Wild-GAD. Compared to the baseline methods, our framework has an average 18% AUCROC and 32% AUCPR improvement over the best-competing methods.
We present GERN, a novel scalable framework for training GNNs in node classification tasks, based on effective resistance, a standard tool in spectral graph theory. Our method progressively refines the GNN weights on a sequence of random spanning trees suitably transformed into path graphs which, despite their simplicity, are shown to retain essential topological and node information of the original input graph. The sparse nature of these path graphs substantially lightens the computational burden of GNN training. This not only enhances scalability but also improves accuracy in subsequent test phases, especially under small training set regimes, which are of great practical importance, as in many real-world scenarios labels may be hard to obtain. In these settings, our framework yields very good results as it effectively counters the training deterioration caused by overfitting when the training set is small. Our method also addresses common issues like over-squashing and over-smoothing while avoiding under-reaching phenomena. Although our framework is flexible and can be deployed in several types of GNNs, in this paper we focus on graph convolutional networks and carry out an extensive experimental investigation on a number of real-world graph benchmarks, where we achieve simultaneous improvement of training speed and test accuracy over a wide pool of representative baselines.