Search Results for author:
Found 23 papers, 11 papers with code
ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Data
Healthcare data frequently contain a substantial proportion of missing values, necessitating effective time series imputation to support downstream disease diagnosis tasks.
Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization
The data-driven worker agent is a large language model being fine-tuned to learn how to generate optimized molecules considering multiple objectives, while the literature-guided research agent is responsible for searching task-related literature to find useful prior knowledge that facilitates identifying the most promising optimized candidates.
LLM4GNAS: A Large Language Model Based Toolkit for Graph Neural Architecture Search
LLM4GNAS includes an algorithm library for graph neural architecture search algorithms based on LLMs, enabling the adaptation of GNAS methods to new search spaces through the modification of LLM prompts.
One Head Eight Arms: Block Matrix based Low Rank Adaptation for CLIP-based Few-Shot Learning
Inspired by recent work on Low-Rank Adaptation (LoRA), Block-LoRA partitions the original low-rank decomposition matrix of LoRA into a series of sub-matrices while sharing all down-projection sub-matrices.
MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance
To improve the efficiency of video representation, we propose Meta Neural Representations for Videos, named MetaNeRV, a novel framework for fast NeRV representation for unseen videos.
Multi-modal Medical Diagnosis via Large-small Model Collaboration
This co-learning mechanism, guided by an adaptive weighting strategy, dynamically balances the complementary strengths between the MoME-fused large model features and the cross-modal reasoning capabilities of the small model.
TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection
Specifically, we adopt INR to parameterize time series data as a continuous function and employ a transformer-based architecture to predict the INR of given data.
Repurposing Foundation Model for Generalizable Medical Time Series Classification
To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets.
SAM-SP: Self-Prompting Makes SAM Great Again
However, these approaches still predominantly necessitate the utilization of domain specific expert-level prompts during the evaluation phase, which severely constrains the model's practicality.
Attention Beats Linear for Fast Implicit Neural Representation Generation
Unlike gradient-based methods, which exhibit lower efficiency in inference, the adoption of hyper-network for generating parameters in Multi-Layer Perceptrons (MLP), responsible for executing INR functions, has surfaced as a promising and efficient alternative.
Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection
Recent advances have utilized Graph Neural Networks (GNNs) to learn effective node representations by aggregating information from neighborhoods.
Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values
However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.
Less is More: A Closer Look at Semantic-based Few-Shot Learning
To address this, we propose a simple but effective framework for few-shot learning tasks, specifically designed to exploit the textual information and language model.
Heterogeneous Graph Neural Architecture Search with GPT-4
The basic idea of GHGNAS is to design a set of prompts that can guide GPT-4 toward the task of generating new heterogeneous graph neural architectures.
Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis
Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs.
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
The results demonstrate that COMET consistently outperforms all baselines, particularly in setup with 10% and 1% labeled data fractions across all datasets.
Graph Neural Architecture Search with GPT-4
In this paper, we integrate GPT-4 into GNAS and propose a new GPT-4 based Graph Neural Architecture Search method (GPT4GNAS for short).
Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPR
To address these challenges, we introduce a novel methodology for the subgrade distress detection task by leveraging the multi-view information from 3D-GPR data.
CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks
Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world.
Hilbert Distillation for Cross-Dimensionality Networks
Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations.
Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy
Besides, CuDFKD adapts the generation target dynamically according to the status of student model.
Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification
Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification.
Temporal Feature Selection on Networked Time Series
For example, social network users are considered to be social sensors that continuously generate social signals (tweets) represented as a time series.
