Search Results for author:
Found 76 papers, 25 papers with code
Graph Positional Autoencoders as Self-supervised Learners
The position path, on the other hand, leverages node representations to refine positions and approximate eigenvectors, thereby enabling the encoder to learn diverse frequency information.
Optimized Contact Plan Design for Reflector and Phased Array Terminals in Cislunar Space Networks
Cislunar space is emerging as a critical domain for human exploration, requiring robust infrastructure to support spatial users - spacecraft with navigation and communication demands.
Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed.
Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling
Cross-domain recommendation (CDR) is a task that aims to improve the recommendation performance in a target domain by leveraging the information from source domains.
Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations
With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation.
GCoT: Chain-of-Thought Prompt Learning for Graphs
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.
SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain?
An Aspect Performance-aware Hypergraph Neural Network for Review-based Recommendation
In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews.
A Contrastive Framework with User, Item and Review Alignment for Recommendation
Traditional approaches rely on user-item interaction data to map users and items into a shared latent space, but the sparsity of interactions often poses challenges.
MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral Imagery
Specifically, to align IR and RGB channels, we first apply super-resolution to IR channels to match the resolution of RGB channels for data fusion.
An Overview on IRS-Enabled Sensing and Communications for 6G: Architectures, Fundamental Limits, and Joint Beamforming Designs
Next, we consider a single IRS to facilitate integrated sensing and communication (ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming.
A Survey of Ontology Expansion for Conversational Understanding
This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding.
DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment
Traditional imitation learning methods often require a large amount of data and encounter distributional shifts and accumulative errors in these tasks.
AMPO: Automatic Multi-Branched Prompt Optimization
Prompt engineering is very important to enhance the performance of large language models (LLMs).
Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs
To address the limitation, we propose RelAdapter, a context-aware adapter for few-shot relation learning in KGs designed to enhance the adaptation process in meta-learning.
Diversified and Adaptive Negative Sampling on Knowledge Graphs
In reality, since knowledge graphs are sparse and incomplete, negative triplets often lack explicit labels, and thus they are often obtained from various sampling strategies (eg: randomly replacing an entity in a positive triplet).
FineMolTex: Towards Fine-grained Molecular Graph-Text Pre-training
Specifically, FineMolTex consists of two pre-training tasks: a contrastive alignment task for coarse-grained matching and a masked multi-modal modeling task for fine-grained matching.
Retrieval Augmented Generation for Dynamic Graph Modeling
This approach presents two critical challenges: (1) How to identify and retrieve high-quality demonstrations that are contextually and temporally analogous to dynamic graph samples?
Exploring the Potential of Large Language Models for Heterophilic Graphs
In the second stage, we adaptively manage message propagation in GNNs for different edge types based on node features, structures, and heterophilic or homophilic characteristics.
Non-Homophilic Graph Pre-Training and Prompt Learning
In particular, many real-world graphs are non-homophilic, not strictly or uniformly homophilic with mixing homophilic and heterophilic patterns, exhibiting varying non-homophilic characteristics across graphs and nodes.
Collaborative Cross-modal Fusion with Large Language Model for Recommendation
To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, for recommendation.
Performance Analysis and Low-Complexity Beamforming Design for Near-Field Physical Layer Security
In particular, it is shown that 1) Artificial noise (AN) is crucial to near-field security provisioning, transforming an insecure system to a secure one; 2) AN can yield numerous security gains, which considerably enhances PLS in the near field as compared to the case without AN taken into account.
A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs
Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision.
Contrastive General Graph Matching with Adaptive Augmentation Sampling
Graph matching has important applications in pattern recognition and beyond.
Accelerating evolutionary exploration through language model-based transfer learning
In this work, we propose an approach for integrating transfer learning with gene expression programming applied to symbolic regression.
A Practice-Friendly LLM-Enhanced Paradigm with Preference Parsing for Sequential Recommendation
Specifically, in the information reconstruction stage, we design a new user-level SFT task for collaborative information injection with the assistance of a pre-trained SRS model, which is more efficient and compatible with limited text information.
Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models
To address these issues, we propose MDGPT, a text free Multi-Domain Graph Pre-Training and adaptation framework designed to exploit multi-domain knowledge for graph learning.
Node-Time Conditional Prompt Learning In Dynamic Graphs
To bridge the gap, prompt-based learning has gained traction on graphs, but most existing efforts focus on static graphs, neglecting the evolution of dynamic graphs.
Alterations of electrocortical activity during hand movements induced by motor cortex glioma
Glioma cells can reshape functional neuronal networks by hijacking neuronal synapses, leading to partial or complete neurological dysfunction.
Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study
In this research, we conduct a comprehensive experimental investigation on the impact of mainstream scanning directions and their combinations on semantic segmentation of remotely sensed images.
Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction
To capture the nuances of the temporal and spatial relationships and heterogeneous characteristics in an interconnected graph of sensors, we introduce a novel model named Temporal and Heterogeneous Graph Neural Networks (THGNN).
Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty
In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.
Diffusion-based Negative Sampling on Graphs for Link Prediction
Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space.
Deep unfolding Network for Hyperspectral Image Super-Resolution with Automatic Exposure Correction
In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR).
SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning
Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time.
A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning
The techniques can be broadly categorized into meta-learning, pre-training, and hybrid approaches, with a finer-grained classification in each category to aid readers in their method selection process.
HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning
In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design.
MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
Hence, in this paper, we propose MultiGPrompt, a novel multi-task pre-training and prompting framework to exploit multiple pretext tasks for more comprehensive pre-trained knowledge.
Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs
In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs.
Towards Graph Foundation Models: A Survey and Beyond
Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains.
Robust Long-Tailed Learning via Label-Aware Bounded CVaR
Data in the real-world classification problems are always imbalanced or long-tailed, wherein the majority classes have the most of the samples that dominate the model training.
Voucher Abuse Detection with Prompt-based Fine-tuning on Graph Neural Networks
We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task in pre-training, thereby narrowing the objective gap.
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation
This paper presents OmniDataComposer, an innovative approach for multimodal data fusion and unlimited data generation with an intent to refine and uncomplicate interplay among diverse data modalities.
Ranked #21 on
Zero-Shot Video Question Answer
on MSRVTT-QA
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Prompt Tuning on Graph-augmented Low-resource Text Classification
During pre-training, we propose three graph interaction-based contrastive strategies to jointly pre-train a graph-text model; during downstream classification, we explore handcrafted discrete prompts and continuous prompt tuning for the jointly pre-trained model to achieve zero- and few-shot classification, respectively.
SDRCNN: A single-scale dense residual connected convolutional neural network for pansharpening
Pansharpening is a process of fusing a high spatial resolution panchromatic image and a low spatial resolution multispectral image to create a high-resolution multispectral image.
Contrastive Multi-view Framework for Customer Lifetime Value Prediction
Accurate customer lifetime value (LTV) prediction can help service providers optimize their marketing policies in customer-centric applications.
Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications.
OSTA: One-shot Task-adaptive Channel Selection for Semantic Segmentation of Multichannel Images
In this study, the concept of pruning from a supernet is used for the first time to integrate the selection of channel combination and the training of a semantic segmentation network.
Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting
Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions.
Link Prediction on Latent Heterogeneous Graphs
Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed.
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks
In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner.
A Survey on Spectral Graph Neural Networks
Graph neural networks (GNNs) have attracted considerable attention from the research community.
On Generalized Degree Fairness in Graph Neural Networks
In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes.
Learning to Count Isomorphisms with Graph Neural Networks
However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting.
VQNet 2.0: A New Generation Machine Learning Framework that Unifies Classical and Quantum
Therefore, based on VQNet 1. 0, we further propose VQNet 2. 0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization.
SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image
However, it was found in this study that different classes of objects had their preferred resizing scale for more accurate semantic segmentation.
On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach
To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose a framework of Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound.
Motif Graph Neural Network
However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing \emph{high-order} graph structures as opposed to \emph{low-order} structures.
Node-wise Localization of Graph Neural Networks
Ideally, how a node receives its neighborhood information should be a function of its local context, to diverge from the global GNN model shared by all nodes.
Count-GNN: Graph Neural Networks for Subgraph Isomorphism Counting
At the graph level, we modulate the graph representation conditioned on the query subgraph, so that the model can be adapted to each unique query for better matching with the input graph.
Meta-Inductive Node Classification across Graphs
That is, MI-GNN does not directly learn an inductive model; it learns the general knowledge of how to train a model for semi-supervised node classification on new graphs.
Growth, Electronic Structure and Superconductivity of Ultrathin Epitaxial CoSi2 Films
We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).
Mesoscale and Nanoscale Physics
Localized Meta-Learning: A PAC-Bayes Analysis for Meta-Learning Beyond Global Prior
Meta-learning methods learn the meta-knowledge among various training tasks and aim to promote the learning of new tasks under the task similarity assumption.
Graph Deformer Network
In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.
Reflectivity and Spectrum of Relativistic Flying Plasma Mirrors
Flying plasma mirrors induced by intense lasers has been proposed as a promising way to generate few-cycle EUV or X-ray lasers.
Plasma Physics
Charge density wave and weak Kondo effect in a Dirac semimetal CeSbTe
Using angle-resolved photoemission spectroscopy (ARPES) and low-energy electron diffraction (LEED), together with density-functional theory (DFT) calculation, we report the formation of charge density wave (CDW) and its interplay with the Kondo effect and topological states in CeSbTe.
Strongly Correlated Electrons Materials Science
Spatial Transformer Point Convolution
In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds.
Recent Advances in Network-based Methods for Disease Gene Prediction
Thirdly, an empirical analysis is conducted to evaluate the performance of the selected methods across seven diseases.
Adaptive Task Sampling for Meta-Learning
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks.
Emotion Recognition in Audio and Video Using Deep Neural Networks
Humans are able to comprehend information from multiple domains for e. g. speech, text and visual.
Multi-View Collaborative Network Embedding
Real-world networks often exist with multiple views, where each view describes one type of interaction among a common set of nodes.
Localized Meta-Learning: A PAC-Bayes Analysis for Meta-Leanring Beyond Global Prior
Meta-learning methods learn the meta-knowledge among various training tasks and aim to promote the learning of new tasks under the task similarity assumption.
Correlation-Sensitive Next-Basket Recommendation
Items adopted by a user over time are indicative of the underlying preferences.
Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text
Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text.
Entity Linking on Microblogs with Spatial and Temporal Signals
Microblogs present an excellent opportunity for monitoring and analyzing world happenings.
