Federated Learning (FL) enables multiple clients to collaboratively develop a global model while maintaining data privacy. However, online FL deployment faces challenges due to distribution shifts and evolving test samples. Personalized Federated Learning (PFL) tailors the global model to individual client distributions, but struggles with Out-Of-Distribution (OOD) samples during testing, leading to performance degradation. In real-world scenarios, balancing personalization and generalization during online testing is crucial and existing methods primarily focus on training-phase generalization. To address the test-time trade-off, we introduce a new scenario: Test-time Generalization for Internal and External Distributions in Federated Learning (TGFL), which evaluates adaptability under Internal Distribution (IND) and External Distribution (EXD). We propose BTFL, a Bayesian-based test-time generalization method for TGFL, which balances generalization and personalization at the sample level during testing. BTFL employs a two-head architecture to store local and global knowledge, interpolating predictions via a dual-Bayesian framework that considers both historical test data and current sample characteristics with theoretical guarantee and faster speed. Our experiments demonstrate that BTFL achieves improved performance across various datasets and models with less time cost. The source codes are made publicly available at https://github.com/ZhouYuCS/BTFL.
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
Trajectory representation learning (TRL) maps trajectories to vectors that can be used for many downstream tasks. Existing TRL methods use either grid trajectories, capturing movement in free space, or road trajectories, capturing movement in a road network, as input. We observe that the two types of trajectories are complementary, providing either region and location information or providing road structure and movement regularity. Therefore, we propose a novel multimodal TRL method, dubbed GREEN, to jointly utilize Grid and Road trajectory Expressions for Effective representatioN learning. In particular, we transform raw GPS trajectories into both grid and road trajectories and tailor two encoders to capture their respective information. To align the two encoders such that they complement each other, we adopt a contrastive loss to encourage them to produce similar embeddings for the same raw trajectory and design a mask language model (MLM) loss to use grid trajectories to help reconstruct masked road trajectories. To learn the final trajectory representation, a dual-modal interactor is used to fuse the outputs of the two encoders via cross-attention. We compare GREEN with 7 state-of-the-art TRL methods for 3 downstream tasks, finding that GREEN consistently outperforms all baselines and improves the accuracy of the best-performing baseline by an average of 15.99%. Code and data are available at https://github.com/slzhou-xy/GREEN.
Story discovery on news streams can help people quickly find story from vast amounts of news, improving the efficiency of information acquisition. Recent online story discovery methods encode text topics and then cluster articles into stories based on similarity. However, the results obtained by these methods are one-time, and clustered news cannot adaptively update in a continuous news stream. Additionally, the inadequate quality of article encoding and the presence of noise data deteriorate the performance of story discovery. To this end, we propose HRSTORY for online story discovery on news streams, which employs a historical news review method to enable news to continuously adapt to the latest environment in the stream data and make corrections and updates. Furthermore, HRSTORY captures better article embeddings through modeling multi-layer relational dependencies within the text. By using sentence-level noise masking, HRSTORY improves the relevance of news article representation to core topics and reduces the interference of noise data. Experiments on real news datasets show that HRSTORY outperforms the state-of-the-art algorithms in unsupervised online story discovery performance.
Estimating the conditional average treatment effect (CATE) from observational data plays a crucial role in areas such as e-commerce, healthcare, and economics. Existing studies mainly rely on the strong ignorability assumption that there are no unmeasured confounders, whose presence cannot be tested from observational data and can invalidate any causal conclusion. In contrast, data collected from randomized controlled trials (RCT) do not suffer from confounding, but are usually limited by a small sample size. In this paper, we propose a two-stage pretraining-finetuning (TSPF) framework using both large-scale observational data and small-scale RCT data to estimate the CATE in the presence of unmeasured confounding. In the first stage, a foundational representation of covariates is trained to estimate counterfactual outcomes through large-scale observational data. In the second stage, we propose to train an augmented representation of the covariates, which is concatenated to the foundational representation obtained in the first stage to adjust for the unmeasured confounding. To avoid overfitting caused by the small-scale RCT data in the second stage, we further propose a partial parameter initialization approach, rather than training a separate network. The superiority of our approach is validated on two public datasets with extensive experiments. The code is available at https://github.com/zhouchuanCN/KDD25-TSPF.
Graph neural network (GNN) has been a powerful approach in collaborative filtering (CF) due to its ability to model high-order user-item relationships. Recently, to alleviate the data sparsity and enhance representation learning, many efforts have been conducted to integrate contrastive learning (CL) with GNNs. Despite the promising improvements, the contrastive view generation based on structure and representation perturbations in existing methods potentially disrupts the collaborative information in contrastive views, resulting in limited effectiveness of positive alignment. To overcome this issue, we propose CoGCL, a novel framework that aims to enhance graph contrastive learning by constructing contrastive views with stronger collaborative information via discrete codes. The core idea is to map users and items into discrete codes rich in collaborative information for reliable and informative contrastive view generation. To this end, we initially introduce a multi-level vector quantizer in an end-to-end manner to quantize user and item representations into discrete codes. Based on these discrete codes, we enhance the collaborative information of contrastive views by considering neighborhood structure and semantic relevance respectively. For neighborhood structure, we propose virtual neighbor augmentation by treating discrete codes as virtual neighbors, which expands an observed user-item interaction into multiple edges involving discrete codes. Regarding semantic relevance, we identify similar users/items based on shared discrete codes and interaction targets to generate the semantically relevant view. Through these strategies, we construct contrastive views with stronger collaborative information and develop a triple-view graph contrastive learning approach. Extensive experiments on four public datasets demonstrate the effectiveness of our proposed approach. Moreover, detailed analyses highlight our contribution in enhancing graph CL for recommendation. Our code is available at https://github.com/RUCAIBox/CoGCL.
Encrypted traffic classification occupies a significant role in cybersecurity and network management. The existing encrypted traffic classification technology mostly relies on intra-flow semantics for extracting features. However, considering that some attack behaviors inherently have similar patterns to legitimate behaviors, and powerful adversaries could simulate benign users to conceal their attack intentions, intra-flow features may be similar between different categories. In this paper, we propose TrafficScope, a time-wavelet fusion network based on Transformer to enhance the performance of encrypted traffic classification. Specifically, in addition to using intra-flow semantics, TrafficScope also extracts contextual information to construct more comprehensive representations. Moreover, to cope with the non-stationary and dynamic contextual traffic, we employ wavelet transform to extract invariant features. For feature fusion, the cross-attention mechanism is adopted to inline combine temporal and wavelet-domain features. We extensively evaluate TrafficScope compared with 7 state-of-the-art baselines based on four groups of real-world traffic datasets, the results show that TrafficScope outperforms existing methods. We conduct a series of experiments in terms of similar intra-flow feature evaluation, data pollution, flow manipulations, and dynamic context to demonstrate the robustness and stability of the proposed method. Furthermore, we produce additional experiments to present the potential of TrafficScope in cross-dataset scenarios.
To be still yet still moving. - Do Hyun Choe Graph contrastive learning (GCL) has recently gained prominence in unsupervised graph representation learning. Traditional GCL approaches generally focus on creating a single contrastive view alongside the main graph view, targeting invariant representation learning in a static framework. Our study introduces a novel manner: despite using static graphs, we aim to learn invariant representations by generating a series of evolving contrastive views with temporal coherence and multi-viewpoint insights at various granularities. In this context, we propose the Progressive Augmentation framework for Graph Contrastive Learning (PaGCL). This framework advances beyond traditional methods by producing a sequence of augmented views, each evolving from the previous one, and assigning timestamps based on piecewise smoothness. This approach enables our model to more effectively extract invariant features from these dynamic views, capturing multi-grained structural and temporal information. Our experiments on diverse benchmark datasets demonstrate that PaGCL significantly outperforms current state-of-the-art methods.
Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently witnessed excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) fail to simultaneously handle the problems of missing attributes, inaccurate attributes and scarce node labels, which limits their expressiveness. In this paper, we propose a generative self-supervised model GraMI to address these issues simultaneously. Specifically, GraMI first initializes all the nodes in the graph with a low-dimensional representation matrix. After that, based on the variational graph autoencoder framework, GraMI learns both node-level and attribute-level embeddings in the encoder, which can provide fine-grained semantic information to construct node attributes. In the decoder, GraMI reconstructs both links and attributes. Instead of directly reconstructing raw features for attributed nodes, GraMI generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed. In this way, GraMI can not only complete informative features for non-attributed nodes, but rectify inaccurate ones for attributed nodes. Finally, we conduct extensive experiments to show the superiority of GraMI in tackling HINs with missing and inaccurate attributes. Our code and data can be found here: https://github.com/See-r/GraMI.
Graph Neural Networks (GNNs) learn from graph-structured data by passing messages between neighboring nodes along edges on certain topological layouts. While layouts can be essential to GNNs' performance, extant methods generally consider obtaining layouts from limited perspectives. In this paper, we introduce Distributional Edge Layouts (DELs), a first-of-its-kind method to sample a collection of topological layouts from a Boltzmann distribution under physical energies. By integrating DELs into GNNs, a wide landscape of feasible graph layouts can be captured from a holistic perspective, overcoming the intrinsic drawbacks in existing GNN designs.In practice, DELs can complement various GNN architectures with high versatility. Our theoretical analysis proves that GNNs equipped with DELs maintain at least the same expressive as their original counterparts, with empirical potential offering extra expressivity. Extensive experiments demonstrate that DELs consistently and substantially improve the performance of a wide range of GNN baselines across multiple datasets, achieving state-of-the-art results. This improvement suggests that DELs capture important distributional information previously overlooked by traditional GNN approaches. DEL is open-sourced at https://github.com/LOGO-CUHKSZ/DEL.
This paper presents an analytical study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs). Generalizing beyond extant approaches grounded in random walk analysis or particle systems, we approach this problem through operator semigroup theory. This theoretical framework allows us to rigorously prove that oversmoothing is intrinsically linked to the ergodicity of the diffusion operator. Relying on semigroup method, we can quantitatively analyze the dynamic of graph diffusion and give a specific mathematical form of the smoothing feature by ergodicity and invariant measure of operator, which improves previous works only show existence of oversmoothing. This finding further poses a general and mild ergodicity-breaking condition, encompassing the various specific solutions previously offered, thereby presenting a more universal and theoretically grounded approach to relieve oversmoothing in diffusion-based GNNs. Additionally, we offer a probabilistic interpretation of our theory, forging a link with prior works and broadening the theoretical horizon. Our experimental results reveal that this ergodicity-breaking term effectively mitigates oversmoothing measured by Dirichlet energy, and simultaneously enhances performance in node classification tasks.
In recent years, Graph Neural Networks (GNNs) become very effective methods to utilize graphs and have been applied to many real-world applications, including recommendation, advertisement, and financial fraud detection. In fact, GNNs are mostly trained and test in the environments with the same distribution. However, in the real cases, selection bias are inevitably existed in both the node features and the graph structures, which will lead to serious impact on the GNN performance. Several works of literature have investigated the out-of-distribution (OOD) problem on the feature distribution, but little research specifically studies the effect caused by the bias of graph structure. However, graph structure is very fundamental for GNNs since it greatly affects the message propagation mechanism. In order to solve the above problem, we propose an unsupervised Stable Graph Representation learning (SGR) framework to obtain stable graphs from multiple environments with graph structure bias, and to improve the stability ability of GNN model across environments. Comprehensive experiments have been carried out on 4 public benchmark dataset and a real-world financial dataset. The experimental results show that the proposed stable learning method significantly improves the stability of GNN model in varying test environments.
Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutions are based on online learning, which continually organize recent time series observations as new training samples and update model parameters according to the forecasting feedback on recent data. However, they overlook a critical issue: obtaining ground-truth future values of each sample should be delayed until after the forecast horizon. This delay creates a temporal gap between the training samples and the test sample. Our empirical analysis reveals that the gap can introduce concept drift, causing forecast models to adapt to outdated concepts. In this paper, we present Proceed, a novel proactive model adaptation framework for online time series forecasting. Proceed first estimates the concept drift between the recently used training samples and the current test sample. It then employs an adaptation generator to efficiently translate the estimated drift into parameter adjustments, proactively adapting the model to the test sample. To enhance the generalization capability of the framework, Proceed is trained on synthetic diverse concept drifts. Extensive experiments on five real-world datasets across various forecast models demonstrate that Proceed brings more performance improvements than the state-of-the-art online learning methods, significantly facilitating forecast models' resilience against concept drifts. Code is available at https://github.com/SJTU-DMTai/OnlineTSF.
Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention. Recently, we have witnessed the significant success of large language models (LLMs), leading many to explore the great potential of LLMs on GNNs. However, they mainly focus on improving the performance of GNNs by utilizing LLMs to enhance the node features. Therefore, we ask: Will the robustness of GNNs also be enhanced with the powerful understanding and inference capabilities of LLMs? By presenting the empirical results, we find that despite that LLMs can improve the robustness of GNNs, there is still an average decrease of 23.1% in accuracy, implying that the GNNs remain extremely vulnerable against topology attacks. Therefore, another question is how to extend the capabilities of LLMs on graph adversarial robustness. In this paper, we propose an LLM-based robust graph structure inference framework, LLM4RGNN. The source code in https://github.com/zhongjian-zhang/LLM4RGNN, which distills the inference capabilities of GPT-4 into a local LLM for identifying malicious edges and an LM-based edge predictor for finding missing important edges, so as to recover a robust graph structure. Extensive experiments demonstrate that LLM4RGNN consistently improves the robustness across various GNNs. Even in some cases where the perturbation ratio increases to 40%, the accuracy of GNNs is still better than that on the clean graph.
Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge, e.g., emotional sociology and medicine. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in the absence of specialized training. In distinction to existing paradigms that merely utilize external knowledge from general KGs or static domain KGs to prompt LLM for enhanced domain-specific reasoning, WTS proposes an innovative ''LLM↻KG'' paradigm, which achieves bidirectional enhancement between specialized LLM and domain knowledge graph (DKG). The proposed paradigm encompasses two closely coupled components: the DKG-Augmented LLM and the LLM-Assisted DKG Evolution. The former retrieves question-relevant domain knowledge from DKG and uses it to prompt LLM to enhance the reasoning capability for domain-specific tasks; the latter leverages LLM to generate new domain knowledge from processed tasks and use it to evolve DKG. WTS closes the loop between DKG-Augmented LLM and LLM-Assisted DKG Evolution, enabling continuous improvement in the domain specialization as it progressively answers and learns from domain-specific questions. We validate the performance of WTS on 7 datasets (e.g., TweetQA, ChatDoctor5k) spanning 6 domains, e.g., emotional sociology, medical, ect. The experimental results show that WTS surpasses the previous SOTA in 5 specialized domains, and achieves a maximum performance improvement of 11.3%.
Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity is measured by the cosine distance. However, many real-world graphs, especially of hierarchical nature, cannot be embedded well in the Euclidean space. Although the hyperbolic embedding is suitable for hierarchical representation learning, naively applying CL to the hyperbolic space may result in the so-called dimension collapse, i.e., features will concentrate mostly within few density regions, leading to poor utilization of the whole feature space. Thus, we propose a novel contrastive learning framework to learn high-quality graph embeddings in hyperbolic space. Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information, as well as we propose a substitute of the uniformity metric to prevent the so-called dimensional collapse. We show that in the hyperbolic space one has to address the leaf- and height-level uniformity related to properties of trees. In the ambient space of the hyperbolic manifold these notions translate into imposing an isotropic ring density towards boundaries of Poincaré ball. Our experiments support the efficacy of our method.
Gene sequence search is a fundamental operation in computational genomics with broad applications in medicine, evolutionary biology, metagenomics, and more. Due to the petabyte scale of genome archives, most gene search systems now use hashing-based data structures such as Bloom Filters (BF). The state-of-the-art systems such as Compact bit-slicing signature index (COBS) and Repeated And Merged Bloom filters (RAMBO) use BF with Random Hash (RH) functions for gene representation and identification. The standard recipe is to cast the gene search problem as a sequence of membership problems testing if each subsequent gene substring (called kmer) of Q is present in the set of kmers of the entire gene database D. We observe that RH functions, which are crucial to the memory and the computational advantage of BF, are also detrimental to the system performance of gene-search systems. While subsequent kmers being queried are likely very similar, RH, oblivious to any similarity, uniformly distributes the kmers to different parts of potentially large BF, thus triggering excessive cache misses and causing system slowdown. We propose a novel hash function called the Identity with Locality (IDL) hash family, which co-locates the keys close in input space without causing collisions. This approach ensures both cache locality and key preservation. IDL functions can be a drop-in replacement for RH functions and help improve the performance of information retrieval systems. We give a simple but practical construction of IDL function families and show that replacing the RH with IDL functions reduces cache misses by a factor of 5x, thus improving query and indexing times of SOTA methods such as COBS and RAMBO by factors up to 2x without compromising their quality. We also provide a theoretical analysis of the false positive rate of BF with IDL functions. Our hash function is the first study that bridges Locality Sensitive Hash (LSH) and RH to obtain cache efficiency. Our design and analysis could be of independent theoretical interest.
We focus on unlearning unwanted knowledge in autoregressive large language models (LLMs) through pruning. Our goal is to selectively remove undesirable information (e.g., harmful responses, privacy-sensitive data) while ensuring the preservation of desirable knowledge (e.g., positive responses and objective facts). Previous approaches use gradient ascent (GA) over undesired knowledge to inversely optimize LLMs, which compromises the model's performance on desired knowledge. To address this limitation, we introduce a novel two-stage approach, named LLM-Eraser, for selectively identifying and editing parameters specifically associated with undesirable knowledge. LLM-Eraser operates in two stages: localization and unlearning. During the localization stage, we utilize neuron scores and trainable soft masks to identify parameters crucial to the undesired knowledge. In the unlearning stage, we prune these identified parameters and apply a selective post-training process to enhance the model's selectiveness. Our experiments, conducted across five task datasets, demonstrate that LLM-Eraser effectively unlearns undesirable knowledge-evidenced by the model's near-random performance on multiple-choice questions related to the erased knowledge-while maintaining high proficiency in desirable knowledge, with an average performance deficit of only 2.5%.
Transformer-based models have gained significant traction in sequential recommender systems (SRSs) for their ability to capture user-item interactions effectively. However, these models often suffer from high computational costs and slow inference. Meanwhile, existing efficient SRS approaches struggle to embed high-quality semantic and positional information into latent representations. To tackle these challenges, this paper introduces GLINT-RU, a lightweight and efficient SRS leveraging a single-layer dense selective Gated Recurrent Units (GRU) module to accelerate inference. By incorporating a dense selective gate, GLINT-RU adaptively captures temporal dependencies and fine-grained positional information, generating high-quality latent representations. Additionally, a parallel mixing block infuses fine-grained positional features into user-item interactions, enhancing both recommendation quality and efficiency. Extensive experiments on three datasets demonstrate that GLINT-RU achieves superior prediction accuracy and inference speed, outperforming baselines based on RNNs, Transformers, MLPs, and SSMs. These results establish GLINT-RU as a powerful and efficient solution for SRSs. The implementation code is publicly available for reproducibility. https://github.com/szhang-cityu/GLINT-RU.
The objective of privacy-preserving synthetic graph publishing is to safeguard individuals' privacy while retaining the utility of original data. Most existing methods focus on graph neural networks under differential privacy (DP), and yet two fundamental problems in generating synthetic graphs remain open. First, the current research often encounters high sensitivity due to the intricate relationships between nodes in a graph. Second, DP is usually achieved through advanced composition mechanisms that tend to converge prematurely when working with a small privacy budget. In this paper, inspired by the simplicity, effectiveness, and ease of analysis of PageRank, we design PrivDPR, a novel privacy-preserving deep PageRank for graph synthesis. In particular, we achieve DP by adding noise to the gradient for a specific weight during learning. Utilizing weight normalization as a bridge, we theoretically reveal that increasing the number of layers in PrivDPR can effectively mitigate the high sensitivity and privacy budget splitting. Through formal privacy analysis, we prove that the synthetic graph generated by PrivDPR satisfies node-level DP. Experiments on real-world graph datasets show that PrivDPR preserves high data utility across multiple graph structural properties.
Federated learning (FL) enables the training of a global machine learning model among multiple local clients in a collaborative fashion without directly sharing the details of their data. Due to this advantage, it has been utilized in a wide range of applications where privacy is a critical concern and has attracted great attention for graph representation learning (GRL). Despite the offered advances, there still exist two major challenges in the FL for GRL across distributed graph data, including heterogeneity and complementarity. In order to tackle these challenges, a novel personalized federated graph augmentation (PFGA) framework is proposed in this work. Unlike existing techniques, it utilizes generative models as bridges to enable information sharing among clients, thereby facilitating the collaborative training of GRL models. Instead of directly using the generative model trained on each client individually, we aggregate them into the globally generative model to gain a global view of the entire graph, which effectively alleviates the heterogeneity and complementarity issues simultaneously. We formulate the training of the generative and GRL models as a min-max adversarial learning problem and theoretically prove the convergence. Furthermore, the effectiveness of the method is demonstrated using experimental results on six real-world datasets.