1,892 Result(s)
-
Chapter and Conference Paper
Distributional Kernel: An Effective and Efficient Means for Trajectory Retrieval
In this paper, we propose a new and powerful way to represent trajectories and measure the distance between them using a distributional kernel. Our method has two unique properties: (i) the identity property w...
-
Chapter and Conference Paper
APFL: Active-Passive Forgery Localization for Medical Images
Medical image forgery has become an urgent issue in academia and medicine. Unlike natural images, images in the medical field are so sensitive that even minor manipulation can produce severe consequences. Exis...
-
Chapter and Conference Paper
A Weighted Cross-Modal Feature Aggregation Network for Rumor Detection
In this paper, we propose a Weighted Cross-modal Aggregation network (WCAN) for rumor detection in order to combine highly correlated features in different modalities and obtain a unified representation in the...
-
Chapter and Conference Paper
SAWTab: Smoothed Adaptive Weighting for Tabular Data in Semi-supervised Learning
Self-supervised and Semi-supervised learning (SSL) on tabular data is an understudied topic. Despite some attempts, there are two major challenges: 1. Imbalanced nature in the tabular dataset; 2. The one-hot e...
-
Chapter and Conference Paper
Improving Knowledge Tracing via Considering Students’ Interaction Patterns
Knowledge Tracing (KT), which aims to accurately identify students’ evolving mastery of different concepts during their learning process, is a popular task for providing intelligent tutoring in online learning...
-
Chapter and Conference Paper
Improving Anti-money Laundering via Fourier-Based Contrastive Learning
Anti-money laundering (AML) aims to detect money laundering from daily transactions, which is the key frontier of combating financial crimes. Previous deep-learning AML methods are not robust enough. To addres...
-
Chapter and Conference Paper
A Data-Driven Approach for Building a Cardiovascular Disease Risk Prediction System
Cardiovascular disease is a leading cause of mortality worldwide. The disease can develop without showing apparent symptoms at an early stage, making it difficult for domain experts to provide intervention. Us...
-
Chapter and Conference Paper
Rethinking Personalized Federated Learning with Clustering-Based Dynamic Graph Propagation
Most existing personalized federated learning approaches are based on intricate designs, which often require complex implementation and tuning. In order to address this limitation, we propose a simple yet effe...
-
Chapter and Conference Paper
Interpreting Pretrained Language Models via Concept Bottlenecks
Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their “black-box” nature poses challenges for responsi...
-
Chapter and Conference Paper
Kernel Representation Learning with Dynamic Regime Discovery for Time Series Forecasting
Correlations between variables in complex ecosystems such as weather and financial markets lead to a great amount of dynamic and co-evolving time series data, posing a significant challenge to the current fore...
-
Chapter and Conference Paper
Projection-Free Bandit Convex Optimization over Strongly Convex Sets
Projection-free algorithms for bandit convex optimization have received increasing attention, due to the ability to deal with the bandit feedback and complicated constraints simultaneously. The state-of-the-ar...
-
Chapter and Conference Paper
LEMT: A Label Enhanced Multi-task Learning Framework for Malevolent Dialogue Response Detection
Malevolent Dialogue Response Detection has gained much attention from the NLP community recently. Existing methods have difficulties in effectively utilizing the conversational context and the malevolent infor...
-
Chapter and Conference Paper
Look Around! A Neighbor Relation Graph Learning Framework for Real Estate Appraisal
Real estate appraisal is a crucial issue for urban applications, aiming to value the properties on the market. Recently, several methods have been developed to automatize the valuation process by taking the pr...
-
Chapter and Conference Paper
Enhancing Continuous Domain Adaptation with Multi-path Transfer Curriculum
Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuou...
-
Chapter and Conference Paper
Conditional Denoising Diffusion for Sequential Recommendation
Contemporary attention-based sequential recommendations often encounter the oversmoothing problem, which generates indistinguishable representations. Although contrastive learning addresses this problem to a d...
-
Chapter and Conference Paper
FR \(^3\) LS: A Forecasting Model with Robust and Reduced Redundancy Latent Series
While some methods are confined to linear embeddings and others exhibit limited robustness, high-dimensional time series factorization techniques employ scalable matrix factorization for forecasting in latent ...
-
Chapter and Conference Paper
Leveraging Transfer Learning for Enhancing Graph Optimization Problem Solving
Reinforcement learning to solve graph optimization problems has attracted increasing attention recently. Typically, these models require extensive training over numerous graph instances to develop generalizabl...
-
Chapter and Conference Paper
Improving Structural and Semantic Global Knowledge in Graph Contrastive Learning with Distillation
Graph contrastive learning has emerged as a pivotal task in the realm of graph representation learning, with the primary objective of maximizing mutual information between graph-augmented pairs exhibiting simi...
-
Chapter and Conference Paper
Multi-sourced Integrated Ranking with Exposure Fairness
Integrated ranking system is one of the critical components of industrial recommendation platforms. An integrated ranking system is expected to generate a mix of heterogeneous items from multiple upstream sour...
-
Chapter and Conference Paper
Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learning
The foundation models (FMs) have been used to generate synthetic public datasets for the heterogeneous federated learning (HFL) problem where each client uses a unique model architecture. However, the vulnerab...