Search Results for author:
Found 60 papers, 16 papers with code
HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression
While large language models (LLMs) have proven effective in leveraging textual data for recommendations, their application to multimodal recommendation tasks remains relatively underexplored.
Inductive Spatio-Temporal Kriging with Physics-Guided Increment Training Strategy for Air Quality Inference
Inductive spatio-temporal kriging with increment training strategy has demonstrated its effectiveness using virtual nodes to simulate unobserved nodes.
Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharing
Through theoretical analysis, we identify key factors affecting task performance and introduce a task attention mechanism to dynamically evaluate task importance, thereby achieving efficient resource allocation.
Drift-Aware Federated Learning: A Causal Perspective
This paper examine the relationship between model update drift and global as well as local optimizer from causal perspective.
Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty
It is proved in this paper that the exit of abnormal edge clients can guarantee the effect of the model on most clients.
The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligence
This paper examines the impact of unknown causes of delay on training performance in an Asynchronous Federated Learning (AFL) system with data heterogeneity.
MAB-Based Channel Scheduling for Asynchronous Federated Learning in Non-Stationary Environments
To address these challenges, we propose an asynchronous federated learning scheduling framework for non-stationary channel environments to reduce staleness while promoting fair and efficient communication and aggregation. We focus on two channel scenarios: extremely non-stationary and piecewise stationary.
PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL
Using the multi-granularity schema linking (MSL) module, PSM-SQL learns the schema semantics at the column, table, and database levels.
A Multi-annotated and Multi-modal Dataset for Wide-angle Video Quality Assessment
Wide-angle video is favored for its wide viewing angle and ability to capture a large area of scenery, making it an ideal choice for sports and adventure recording.
A Survey on Diffusion Models for Anomaly Detection
Diffusion models (DMs) have emerged as a powerful class of generative AI models, showing remarkable potential in anomaly detection (AD) tasks across various domains, such as cybersecurity, fraud detection, healthcare, and manufacturing.
UAV-Assisted Multi-Task Federated Learning with Task Knowledge Sharing
The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety of applications, such as emergency communications, regional surveillance, and disaster relief.
Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection
In each layer of GNN, node features aggregate information from their neighboring nodes to update their information.
Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL
Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems.
Subset Random Sampling of Finite Time-vertex Graph Signals
Time-varying data with irregular structures can be described by finite time-vertex graph signals (FTVGS), which represent potential temporal and spatial relationships among multiple sources.
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
Our method extends from traditional scalar-valued measures by learning eigenvalues, eigenfunctions, and projection spaces of density ratios from realizations of the signal, addressing the interpretability, scalability, and local temporal dependence of cortico-muscular connectivity.
Decoupling Contact for Fine-Grained Motion Style Transfer
However, it is unknown how to decouple and control contact to achieve fine-grained control in motion style transfer.
The Transferability of Downsamped Sparse Graph Convolutional Networks
By incorporating both sparsity and topological similarity into the model, this study establishes an upper bound on the transfer error for downsampling in the training of large-scale sparse graphs and provides insight into the influence of topological structure on transfer performance.
Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition
Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Networking Systems for Video Anomaly Detection: A Tutorial and Survey
The increasing utilization of surveillance cameras in smart cities, coupled with the surge of online video applications, has heightened concerns regarding public security and privacy protection, which propelled automated Video Anomaly Detection (VAD) into a fundamental research task within the Artificial Intelligence (AI) community.
CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network
We train the CTRL model with a future event (a subgraph) prediction task to capture the evolution of the high-order network structure.
Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment
Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.
Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes.
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition.
Online Signed Sampling of Bandlimited Graph Signals
In this paper, we are interested in how to sample based on sign information in an online manner, by which the direction of the original graph signal can be estimated.
Graph Relation Distillation for Efficient Biomedical Instance Segmentation
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
CoT (Chain-of-Thought) is a way to solve reasoning problems for LLMs .
RSMT: Real-time Stylized Motion Transition for Characters
Styled online in-between motion generation has important application scenarios in computer animation and games.
Feature Learning in Image Hierarchies using Functional Maximal Correlation
This paper proposes the Hierarchical Functional Maximal Correlation Algorithm (HFMCA), a hierarchical methodology that characterizes dependencies across two hierarchical levels in multiview systems.
Attention Paper: How Generative AI Reshapes Digital Shadow Industry?
The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning.
OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities
At present, most approaches focus on chains of thought (COT) and tool use, without considering the adoption and application of human cognitive frameworks.
A Soma Segmentation Benchmark in Full Adult Fly Brain
Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.
The Normalized Cross Density Functional: A Framework to Quantify Statistical Dependence for Random Processes
We mathematically prove that FMCA learns the dominant eigenvalues and eigenfunctions of NCD directly from realizations.
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations.
One for All, All for One: Learning and Transferring User Embeddings for Cross-Domain Recommendation
CAT-ART boosts the recommendation performance in any target domain through the combined use of the learned global user representation and knowledge transferred from other domains, in addition to the original user embedding in the target domain.
Linear RNNs Provably Learn Linear Dynamic Systems
We study the learning ability of linear recurrent neural networks with Gradient Descent.
Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems
Existing benchmark datasets for recommender systems (RS) either are created at a small scale or involve very limited forms of user feedback.
Sampling of Correlated Bandlimited Continuous Signals by Joint Time-vertex Graph Fourier Transform
When sampling multiple signals, the correlation between the signals can be exploited to reduce the overall number of samples.
Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model
Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain.
Entry-Flipped Transformer for Inference and Prediction of Participant Behavior
Our key idea is to model the spatio-temporal relations among participants in a manner that is robust to error accumulation during frame-wise inference and prediction.
TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback
That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms.
Real-time Controllable Motion Transition for Characters
Then, during generation, we design a transition model which is essentially a sampling strategy to sample from the learned manifold, based on the target frame and the aimed transition duration.
Cross-domain Trajectory Prediction with CTP-Net
Further, considering the consistency between the observed and the predicted trajectories, a target domain offset discriminator is utilized to adversarially regularize the future trajectory predictions to be in line with the observed trajectories.
Information Theoretic Structured Generative Modeling
We test the framework for estimation of mutual information and compare the results with the mutual information neural estimation (MINE), for density estimation, for conditional probability estimation in Markov models as well as for training adversarial networks.
On the Provable Generalization of Recurrent Neural Networks
In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$.
Recovery of Graph Signals from Sign Measurements
Sampling and interpolation have been extensively studied, in order to reconstruct or estimate the entire graph signal from the signal values on a subset of vertexes, of which most achievements are about continuous signals.
Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference
In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training.
Optical Mouse: 3D Mouse Pose From Single-View Video
We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos.
Regularized Recovery by Multi-order Partial Hypergraph Total Variation
In this work, we take this divergence into consideration, and propose a multi-order hypergraph Laplacian and the corresponding total variation.
Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis
Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids.
Energy-constrained Self-training for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain.
DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster
DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex.
Astrophysics of Galaxies
Sampling Policy Design for Tracking Time-Varying Graph Signals with Adaptive Budget Allocation
There have been many works that focus on the sampling set design for a static graph signal, but few for time-varying graph signals (GS).
On Critical Sampling of Time-Vertex Graph Signals
This paper focuses on the fundamental problem of sampling and reconstruction of joint time-vertex graph signals.
Locality-constrained Spatial Transformer Network for Video Crowd Counting
Then to relate the density maps between neighbouring frames, a Locality-constrained Spatial Transformer (LST) module is introduced to estimate the density map of next frame with that of current frame.
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions.
Talent Search and Recommendation Systems at LinkedIn: Practical Challenges and Lessons Learned
LinkedIn Talent Solutions business contributes to around 65% of LinkedIn's annual revenue, and provides tools for job providers to reach out to potential candidates and for job seekers to find suitable career opportunities.
Towards Deep and Representation Learning for Talent Search at LinkedIn
In this paper, we present the results of our application of deep and representation learning models on LinkedIn Recruiter.
Deploying Deep Ranking Models for Search Verticals
In this paper, we present an architecture executing a complex machine learning model such as a neural network capturing semantic similarity between a query and a document; and deploy to a real-world production system serving 500M+users.
Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
The visual attributes of cells, such as the nuclear morphology and chromatin openness, are critical for histopathology image analysis.
Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System
We consider a D2D-enabled cellular network where user equipments (UEs) owned by rational users are incentivized to form D2D pairs using tokens.
