{"total":38,"rows":[{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94,"area":null},{"id":"2406.09009","title":"Fredformer: Frequency Debiased Transformer for Time Series Forecasting","created":"2024-06-13","cited_by_count":45,"area":null},{"id":"2406.02997","title":"Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs","created":"2024-06-05","cited_by_count":34,"area":null},{"id":"2404.17169","title":"FairGT: A Fairness-aware Graph Transformer","created":"2024-04-26","cited_by_count":29,"area":null},{"id":"2411.04551","title":"Measure-to-measure interpolation using Transformers","created":"2024-11-07","cited_by_count":29,"area":null},{"id":"2312.10325","title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","created":"2023-12-16","cited_by_count":28,"area":null},{"id":"2306.02376","title":"Towards Deep Attention in Graph Neural Networks: Problems and Remedies","created":"2023-06-04","cited_by_count":24,"area":null},{"id":"2402.07225","title":"Rethinking Graph Masked Autoencoders through Alignment and Uniformity","created":"2024-02-11","cited_by_count":22,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2403.12459","title":"Non-negative Contrastive Learning","created":"2024-03-19","cited_by_count":19,"area":null},{"id":"2308.16800","title":"Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2310.18904","title":"Identifiable Contrastive Learning with Automatic Feature Importance Discovery","created":"2023-10-29","cited_by_count":14,"area":null},{"id":"2312.04234","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","created":"2023-12-07","cited_by_count":11,"area":null},{"id":"2503.00507","title":"Projection Head is Secretly an Information Bottleneck","created":"2025-03-01","cited_by_count":11,"area":null},{"id":"2403.15520","title":"GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2311.02687","title":"Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2410.20349","title":"Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition","created":"2024-10-27","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2510.16014","title":"STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter","created":"2025-10-15","cited_by_count":7,"area":null},{"id":"2510.17457","title":"Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2502.04591","title":"Are We Measuring Oversmoothing in Graph Neural Networks Correctly?","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2504.16786","title":"MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2504.12474","title":"Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2502.11394","title":"A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2504.21296","title":"Fairness in Augmented Graph Learning: A Survey","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2312.07753","title":"Polynomial-based Self-Attention for Table Representation learning","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2312.10458","title":"Degree-based stratification of nodes in Graph Neural Networks","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2511.20698","title":"On the Role of Hidden States of Modern Hopfield Network in Transformer","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2306.02117","title":"Oversmoothing: A Nightmare for Graph Contrastive Learning?","created":"2023-06-03","cited_by_count":0,"area":null},{"id":"2503.00578","title":"Channel-Attentive Graph Neural Networks","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2504.13426","title":"Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.05032","title":"Identifying and Understanding Cross-Class Features in Adversarial Training","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.17576","title":"Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2603.22333","title":"Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation","created":"2026-03-20","cited_by_count":0,"area":null}],"next_cursor":null}