Low-dimensional visualizations, or ''projection maps,'' are widely used in scientific and creative domains to interpret large-scale and complex datasets. These visualizations not only aid in understanding existing knowledge spaces but also implicitly guide exploration into unknown areas. Although techniques such as t-SNE and UMAP can generate these maps, there exists no systematic method for leveraging them to generate new content. To address this, we introduce MapExplorer, a novel knowledge discovery task that translates coordinates within any projection map into coherent, contextually aligned textual content. This allows users to interactively explore and uncover insights embedded in the maps. To evaluate the performance of MapExplorer methods, we propose Atometric, a fine-grained metric inspired by ROUGE that quantifies logical coherence and alignment between generated and reference text. Experiments on diverse datasets demonstrate the versatility of MapExplorer in generating scientific hypotheses, crafting synthetic personas, and devising strategies for attacking large language models-even with simple baseline methods. By bridging visualization and generation, our work highlights the potential of MapExplorer to enable intuitive human-AI collaboration in large-scale data exploration.
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
Pre-trained Language Models (PLMs), such as ChatGPT, have significantly advanced the field of natural language processing. This progress has inspired a series of innovative studies that explore the adaptation of PLMs to time series analysis, intending to create a unified foundation model that addresses various time series analytical tasks. However, these efforts predominantly focus on Regularly Sampled Time Series (RSTS), neglecting the unique challenges posed by Irregularly Sampled Time Series (ISTS), which are characterized by uneven sampling intervals and prevalent missing data. To bridge this gap, this work takes the first step in exploring the potential of PLMs for ISTS analysis. We begin by investigating the effect of various methods for representing ISTS, aiming to maximize the efficacy of PLMs in the analysis. Furthermore, we propose a unified PLM-based framework, named ISTS-PLM, to address diverse ISTS analytical tasks. It integrates novel time-aware and variable-aware PLMs tailored to tackle the intractable intra- and inter-time series modeling in ISTS. Finally, extensive experiments on a comprehensive benchmark demonstrate that the ISTS-PLM, utilizing a structured and effective series-based representation for ISTS, consistently achieves state-of-the-art performance across various analytical tasks, such as classification, interpolation, extrapolation, few-shot and zero-shot learning scenarios, spanning scientific domains like healthcare, biomechanics, and climate science.
In the era of large foundation models, data has become a crucial component in building high-performance AI systems. As the demand for high-quality and large-scale data continues to rise, data copyright protection is attracting increasing attention. In this work, we explore the problem of data watermarking for sequential recommender systems, where a watermark is embedded into the target dataset and can be detected in models trained on that dataset. We focus on two settings: dataset watermarking, which protects the ownership of the entire dataset, and user watermarking, which safeguards the data of individual users. We present a method named Dataset Watermarking for Recommender Systems (DWRS) to address them. We define the watermark as a sequence of consecutive items inserted into normal users' interaction sequences. We define a Receptive Field (RF) to guide the inserting process to facilitate the memorization of the watermark. Extensive experiments on five representative sequential recommendation models and three benchmark datasets demonstrate the effectiveness of DWRS in protecting data copyright while preserving model utility.
Recommendation systems (RS) aim to provide personalized content, but they face a challenge in unbiased learning due to selection bias, where users only interact with items they prefer. This bias leads to a distorted representation of user preferences, which hinders the accuracy and fairness of recommendations. To address the issue, various methods such as error imputation based, inverse propensity scoring, and doubly robust techniques have been developed. Despite the progress, from the structural causal model perspective, previous debiasing methods in RS assume the independence of the exogenous variables. In this paper, we release this assumption and propose a learning algorithm based on likelihood maximization to learn a prediction model. We first discuss the correlation and difference between unmeasured confounding and our scenario, then we propose a unified method that effectively handles latent exogenous variables. Specifically, our method models the data generation process with latent exogenous variables under mild normality assumptions. We then develop a Monte Carlo algorithm to numerically estimate the likelihood function. Extensive experiments on synthetic datasets and three real-world datasets demonstrate the effectiveness of our proposed method. The code is at https://github.com/WallaceSUI/kdd25-background-variable.
Loss or Gain: Hierarchical Conditional Information Bottleneck Approach for Incomplete Time Series Classification
PDF ↗Incomplete time series classification is both practically valuable and challenging as missing values in time series data are prevalent in real-world scenarios. Current approaches suffer from two major limitations. First, they overemphasize the consistency of data reconstruction during missing value imputation while neglecting the task-effectiveness of the imputed results for the classification. Second, they fail to systematically establish a synergistic optimization mechanism between data imputation and feature representation. To address these challenges, we propose a Hierarchical Conditional Information Bottleneck (HCIB) framework, which achieves incomplete time series classification through end-to-end joint optimization. Specifically, at the data imputation level, we re-examine the dual effects of missing data: the loss of critical information (Loss) versus the gain in interference suppression (Gain), elucidating this duality through bias-variance trade-off theory. Building on this analysis, we propose a task-information sufficiency criterion and extend the information bottleneck theory into a task-driven imputation framework by incorporating label information as a conditional constraint. At the feature representation level, we construct a hierarchical information bottleneck architecture to learn compressed yet informative temporal representations from the task-oriented imputed data. Furthermore, we derive the optimizable objective function for HCIB and design specialized neural network architectures for time series. Comprehensive experiments on multivariate and univariate time series datasets across multiple domains consistently demonstrate that the proposed method achieves significant improvements in classification performance compared to SOTA approaches.
The emergence of text-to-image models has recently sparked significant interest, but the attendant is a looming shadow of potential infringement by violating user terms. Specifically, an adversary may exploit data created by a commercial model to train their own without proper authorization. To address such risk, it is crucial to investigate the attribution of a suspicious model's training data by determining whether its training data originates, wholly or partially, from a specific source model. To trace the generated data, existing methods need to apply additional watermarks during either the training or inference phases of the source model. However, these methods are impractical for pre-trained models that have been released, especially when model owners lack security expertise. To tackle this challenge, we propose an injection-free training data attribution method for text-to-image models. It can identify whether a model's training data stems from a certain source model without adding additional watermarks on the source model. The rationale of our method lies in the inherent memorization characteristic of text-to-image models. The memorization of training data is inherited through the data generated by the source model to the model trained on that data, making the source model and the infringing model exhibit consistent behaviors on specific samples. Therefore, from instance-level, we develop detection-based and generation-based strategies to uncover these distinct samples and using them as inherent watermarks to verify if a suspicious model originates from the source model. Besides, we also propose a statistical-level attribution method, utilizing the shadow model technique to train an attribution discriminator. Experiments demonstrate that the attribution accuracy and AUC scores of our methods are over 80% even when the infringing model only uses a small proportion of generated data.
Network interdiction problems, arising in critical applications from military strategy to disease control, involve a complex attacker-defender dynamic: one player optimizes a network-based objective, while the other strategically modifies the network to impede that objective. The inherent bi-level optimization and combinatorial nature of these problems pose a significant computational challenge, often rendering traditional exact solvers impractical and hindering the development of effective heuristics. While Graph Neural Networks (GNNs) have demonstrated promise in solving single-level combinatorial optimization problems on graphs, their direct application to bi-level interdiction problems remains limited. In this paper, we bridge this gap by introducing a novel approach that leverages the power of GNNs to learn Mixed-Integer Linear Programming (MILP) formulations of network interdiction problems. By representing the problem in this structured mathematical form, we empower a multipartite GNN with the representational capacity to effectively capture the complex interplay between the two players. This approach aligns the neural network with the underlying mathematical structure of interdiction problems, leading to improved performance. Through extensive experiments on two network interdiction tasks, we demonstrate the superiority of our proposed method over both baseline GNN models and traditional exact solvers, showcasing its potential for real-world applications.
Single-domain generalization (SDG) in time series classification (TSC) poses significant challenges for current time-series domain generalization methods due to the extremely limited data available from only one source domain. In this study, we propose Segment-dErived Expansion of Domains (SEED), a diffusion-based method that effectively expands domain diversity for SDG. We reveal that individual instances exhibit intrinsic temporal shifts over time, which provides a principled foundation for creating multiple pseudo domains by segmenting each instance into distinct parts. To do so, SEED extracts two complementary representations from each time-series segment: 1) a segment-specific representation that captures diverse distributional variations, and 2) a segment-invariant representation that preserves class semantics. SEED formulates these representations as pseudo-domain prompts to guide a diffusion model in generating diverse yet semantically consistent time-series data. Additionally, SEED introduces a novel prompt-fused sampling for diffusion, enabling flexible recombination of segment-specific features to continuously expand the pseudo-domain space. We provide both theoretical analysis and extensive empirical evaluations on four widely used TSC benchmarks to validate its ability in reducing generalization error and improving model's performances in SDG. In our experiments, SEED significantly improves classification accuracy by 7.68% on average compared to the strong baselines.
Research on Graph Structure Learning (GSL) provides key insights for graph-based clustering, yet current methods like Graph Neural Networks (GNNs), Graph Attention Networks (GATs), and contrastive learning often rely heavily on the original graph structure. Their performance deteriorates when the original graph's adjacency matrix is too sparse or contains noisy edges unrelated to clustering. Moreover, these methods depend on learning node embeddings and using traditional techniques like k-means to form clusters, which may not fully capture the underlying graph structure between nodes. To address these limitations, this paper introduces DeSE, a novel unsupervised graph clustering framework incorporating Deep Structural Entropy. It enhances the original graph with quantified structural information and deep neural networks to form clusters. Specifically, we first propose a method for calculating structural entropy with soft assignment, which quantifies structure in a differentiable form. Next, we design a Structural Learning layer (SLL) to generate an attributed graph from the original feature data, serving as a target to enhance and optimize the original structural graph, thereby mitigating the issue of sparse connections between graph nodes. Finally, our clustering assignment method (ASS), based on GNNs, learns node embeddings and a soft assignment matrix to cluster on the enhanced graph. The ASS layer can be stacked to meet downstream task requirements, minimizing structural entropy for stable clustering and maximizing node consistency with edge-based cross-entropy loss. Extensive comparative experiments are conducted on four benchmark datasets against eight representative unsupervised graph clustering baselines, demonstrating the superiority of the DeSE in both effectiveness and interpretability.
Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their predictions. While numerous post-hoc instance-level explanation methods have been proposed to interpret GNN predictions, the reliability of these explanations remains uncertain, particularly in the out-of-distribution or unknown test datasets. In this paper, we address this challenge by introducing an explainer framework with the confidence scoring module ( ConfExplainer), grounded in theoretical principle, which is generalized graph information bottleneck with confidence constraint (GIB-CC), that quantifies the reliability of generated explanations. Experimental results demonstrate the superiority of our approach, highlighting the effectiveness of the confidence score in enhancing the trustworthiness and robustness of GNN explanations.
With the advent of large language models (LLMs), managing scientific literature via LLMs has become a promising direction of research. However, existing approaches often overlook the rich structural and semantic relevance among scientific literature, limiting their ability to discern the relationships between pieces of scientific knowledge, and suffer from various types of hallucinations. These methods also focus narrowly on individual downstream tasks, limiting their applicability across use cases. We propose LitFM, the first literature foundation model designed for a wide variety of practical downstream tasks on domain-specific literature, with a focus on citation information. At its core, LitFM contains a novel graph retriever that can provide accurate and diverse recommendations for LLM to integrate graph structure information and relevant literature. LitFM also leverages a knowledge-infused LLM, fine-tuned through a well-developed instruction paradigm. It enables LitFM to extract domain-specific knowledge from literature and reason relationships among them. By integrating citation graphs during both training and inference, LitFM can generalize to unseen papers and accurately assess their relevance within existing literature. Additionally, we introduce new large-scale literature citation benchmark datasets on three academic fields, featuring sentence-level citation information and local context. Extensive experiments validate the superiority of LitFM, achieving 28.1% improvement on retrieval task in precision, and an average improvement of 7.52% over state-of-the-art across six downstream literature-related tasks.
Although Graph Neural Networks (GNNs) have shown promising potential in fake news detection, they remain highly vulnerable to adversarial manipulations within social networks. Existing methods primarily establish connections between malicious accounts and individual target news to investigate the vulnerability of graph-based detectors, while they neglect the structural relationships surrounding targets, limiting their effectiveness in robustness evaluation. In this work, we propose a novel Structural Information principles-guided Adversarial Attack Framework, namely SI2AF, which effectively challenges graph-based detectors and further probes their detection robustness. Specifically, structural entropy is introduced to quantify the dynamic uncertainty in social engagements and identify hierarchical communities that encompass all user accounts and news posts. An influence metric is presented to measure each account's probability of engaging in random interactions, facilitating the design of multiple agents that manage distinct malicious accounts. For each target news, three attack strategies are developed through multi-agent collaboration within the associated subgraph to optimize evasion against black-box detectors. By incorporating the adversarial manipulations generated by SI2AF, we enrich the original network structure and refine graph-based detectors to improve their robustness against adversarial attacks. Extensive evaluations demonstrate that SI2AF significantly outperforms state-of-the-art baselines in attack effectiveness with an average improvement of 16.71%, and enhances GNN-based detection robustness by 41.54% on average.
Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features
PDF ↗In real-world graphs, we often encounter missing feature situations where a few or the majority of node features, e.g., sensitive information, are missed. In such scenarios, directly utilizing Graph Neural Networks (GNNs) would yield sub-optimal results in downstream tasks such as node classification. Despite the emergence of a few GNN-based methods attempting to mitigate its missing situation, when only a few features are available, they rather perform worse than traditional structure-based models. To this end, we propose a novel framework that further illuminates the potential of classical Label Propagation (Oldie), taking advantage of Feature Propagation, especially when only a partial feature is available. Now called by GOODIE, it takes a hybrid approach to obtain embeddings from the Label Propagation branch and Feature Propagation branch. To do so, we first design a GNN-based decoder that enables the Label Propagation branch to output hidden embeddings that align with those of the FP branch. Then, GOODIE automatically captures the significance of structure and feature information thanks to the newly designed Structure-Feature Attention. Followed by a novel Pseudo-Label contrastive learning that differentiates the contribution of each positive pair within pseudo-labels originating from the LP branch, GOODIE outputs the final prediction for the unlabeled nodes. Through extensive experiments, we demonstrate that our proposed model, GOODIE, outperforms the existing state-of-the-art methods not only when only a few features are available but also in abundantly available situations. Source code of GOODIE is available at: https://github.com/SukwonYun/GOODIE.
Large multimodal models (LMMs) exhibit enhanced capabilities in understanding and generating both textual and visual content. By leveraging item metadata, LMMs are also applied for recommendation and demonstrate improvements across diverse scenarios. However, the majority of existing methods explore static item attributes without considering additional contextual information (e.g., price, brand). Moreover, overlooking the interaction between the retrieval and ranking stages may lead to suboptimal solutions for fine-grained recommendations. In this work, we introduce PRIME: preference-optimized retrieval and ranking for efficient multimodal recommendation. PRIME operates in two stages: (i) a lightweight retriever identifies potential candidate items; (ii) an LMM learns to rank the retrieved candidates with detailed user history and multimodal features (e.g., text and image attributes). These features are incorporated into a carefully designed prompt, facilitating fine-grained transition patterns for user preference understanding. To optimize the inference efficiency of PRIME, we introduce verbalizer-based inference, which computes ranking scores for all candidate items in a single forward pass. Furthermore, we employ the LMM ranker to provide feedback on sampled candidate sets, enabling online preference optimization that refines the retriever model and improves the alignment between retrieval and ranking. As a result, PRIME can capture subtle user intentions and efficiently rank candidate items with minimal inference costs. Extensive experiments show the effectiveness and efficiency of PRIME, which consistently achieves superior performance over baseline methods.
Online market platforms serve as a central hub for sharing and deploying AI models among researchers, developers, and companies. In this context, watermarking techniques are essential to protect intellectual property (IP), preventing unauthorized use and duplication of large language models (LLMs). Two key challenges arise: (i) These platforms host diverse LLMs, yet current watermarking techniques are only tailored to specific models, such as fine-tuned or quantized LLMs. (ii) Efficient watermarking is critical. However, traditional methods require substantial data and costly hardware, which limits their feasibility. In this paper, we propose an efficient white-box LLM watermarking technique called ELLMark. This method treats LLMs as multi-layered matrices while embedding watermarks only relies on modifying the model's weights. To preserve LLMs' performance, it filters weights by correlations with the activation magnitudes and downstream tasks, then modifies weights as minimal as possible via histogram modulation. Notably, all phases are training-free with low hardware resources, making it efficient for online platforms. We conduct extensive experiments to evaluate the effectiveness of ELLMark on LLaMA-3, OPT, and Phi-3 LLMs. The results demonstrate that it achieves 100% success in watermark detection while preserving model performance. Moreover, the preprocessing, encoding, and decoding processes remain efficient, taking less than 7 minutes, 12 minutes, and 18 seconds, respectively, for models with 80B parameters. Lastly, it exhibits robustness against parameter overwriting, re-watermarking, forging, fine-tuning, and pruning attacks.
Chain-of-thought (CoT) prompting has achieved remarkable success in natural language processing (NLP). However, its vast potential remains largely unexplored for graphs. This raises an interesting question: How can we design CoT prompting for graphs to guide graph models to learn step by step? On one hand, unlike natural languages, graphs are non-linear and characterized by complex topological structures. On the other hand, many graphs lack textual data, making it difficult to formulate language-based CoT prompting. %Therefore we cannot directly adopt the CoT prompting methods used in the language domain. In this work, we propose the first CoT prompt learning framework for text-free graphs, GCoT. Specifically, we decompose the adaptation process for each downstream task into a series of inference steps, with each step consisting of prompt-based inference, ''thought'' generation, and thought-conditioned prompt learning. While the steps mimic CoT prompting in NLP, the exact mechanism differs significantly. Specifically, at each step, an input graph, along with a prompt, is first fed into a pre-trained graph encoder for prompt-based inference. We then aggregate the hidden layers of the encoder to construct a ''thought'', which captures the working state of each node in the current step. Conditioned on this thought, we learn a prompt specific to each node based on the current state. These prompts are fed into the next inference step, repeating the cycle. To evaluate and analyze the effectiveness of GCoT, we conduct comprehensive experiments on eight public datasets, which demonstrate the advantage of our approach.
With the rise of web-based technologies, online tutoring platforms have emerged to provide personalized learning services by modeling learners' engagement behaviors, improving both convenience and efficiency in academic progress. Cognitive diagnosis has been always recognized a essential learner modeling task in personalized education, which aims to infer learners' mastery in specific knowledge concepts by mining and analyzing their practice behavior. However, most existing studies fail to explicitly disentangling the multiple interdependent factors that influence learner's response feedback during the problem-solving process, both in web-based environments and real-world contexts. To address this issue, we propose DISCD, a feedback-centric DIS entangled Cognitive Diagnosis framework for enhancing effective and interpretable learner modeling. Specifically, we first introduce a feedback-centric disentangled encoder grounded in variational inference to effectively characterize learners' cognitive traits by modeling their practice responses. To achieve this, we fully leverage the interaction matrix and the exercise-concept correlation matrix to extract implicit signals in the disentanglement process, employing three dedicated sub-encoders to efficiently and comprehensively capture these attributes. Next, we develop a multi-level cognitive coordination module to systematically model the disentangled cognitive factors, ensuring their seamless integration into the diagnosis decoding process. Finally, we design a cognitive interaction decoder to reconstruct and refine learners' engagement trajectories in exercises. Extensive experiments on four educational datasets validate the effectiveness of the proposed DISCD model in learner modeling for cognitive diagnosis.
Collaborative fairness is a crucial challenge in federated learning. However, existing approaches often overlook a practical yet complex form of heterogeneity: imbalanced covariate shift. We provide a theoretical analysis of this setting, which motivates the design of FedAKD (Federated Asynchronous Knowledge Distillation) - a simple yet effective approach that balances accurate prediction with collaborative fairness. FedAKD consists of client and server updates. In the client update, we introduce a novel asynchronous knowledge distillation strategy based on our preliminary analysis, which reveals that while correctly predicted samples exhibit similar feature distributions across clients, incorrectly predicted samples show significant variability. This suggests that imbalanced covariate shift primarily arises from misclassified samples. Leveraging this insight, our approach first applies traditional knowledge distillation to update client models while keeping the global model fixed. Next, we select the correctly predicted high-confidence samples and update the global model using these samples, while keeping the client models fixed. The server update simply aggregates all client models. We further provide a theoretical proof of FedAKD's convergence. Experimental results on both public datasets (FashionMNIST and CIFAR10) and a real-world Electronic Health Records (EHR) dataset demonstrate that FedAKD significantly improves collaborative fairness, enhances predictive accuracy, and fosters client participation, even under highly heterogeneous data distributions.
Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Rates
PDF ↗Multivariate Time Series Forecasting (MTSF) involves predicting future values of multiple interrelated time series. Recently, deep learning-based MTSF models have gained significant attention for their promising ability to mine semantics (global and local information) within MTS data. However, these models are pervasively susceptible to missing values caused by malfunctioning data collectors. These missing values not only disrupt the semantics of MTS, but their distribution also changes over time. Nevertheless, existing models lack robustness to such issues, leading to suboptimal forecasting performance. To this end, in this paper, we propose Multi-View Representation Learning (Merlin), which can help existing models achieve semantic alignment between incomplete observations with different missing rates and complete observations in MTS. Specifically, Merlin consists of two key modules: offline knowledge distillation and multi-view contrastive learning. The former utilizes a teacher model to guide a student model in mining semantics from incomplete observations, similar to those obtainable from complete observations. The latter improves the student model's robustness by learning from positive/negative data pairs constructed from incomplete observations with different missing rates, ensuring semantic alignment across different missing rates. Therefore, Merlin is capable of effectively enhancing the robustness of existing models against unfixed missing rates while preserving forecasting accuracy. Experiments on four real-world datasets demonstrate the superiority of Merlin.
Self-supervised learning (SSL) has emerged as a promising paradigm that presents supervisory signals to real-world problems, bypassing the extensive cost of manual labeling. Consequently, self-supervised anomaly detection (SSAD) has seen a recent surge of interest, since SSL is especially attractive for unsupervised tasks. However, recent works have reported that the choice of a data augmentation function has significant impact on the accuracy of SSAD, posing augmentation search as an essential but nontrivial problem due to lack of labeled validation data. In this paper, we introduce ST-SSAD, the first unsupervised approach to end-to-end augmentation tuning for SSAD. To this end, our work presents two key contributions. The first is a new unsupervised validation loss that quantifies the alignment between augmented training data and unlabeled validation data. The second is new differentiable augmentation functions, allowing data augmentation hyperparameter(s) to be tuned in an end-to-end manner. Experiments on two testbeds with semantic class anomalies and subtle industrial defects show that ST-SSAD gives significant performance gains over existing works. All our code and testbeds are available at https://github.com/jaeminyoo/ST-SSAD.