Search Results for author:
Found 98 papers, 36 papers with code
Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations
We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.
AdvLoRA: Adversarial Low-Rank Adaptation of Vision-Language Models
Different from LoRA, we improve the efficiency and robustness of adversarial adaptation by designing a novel reparameterizing method based on parameter clustering and parameter alignment.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
Causal Discovery by Kernel Deviance Measures with Heterogeneous Transforms
To go about capturing these discrepancies between cause and effect remains to be a challenge and many current state-of-the-art algorithms propose to compare the norms of the kernel mean embeddings of the conditional distributions.
ControlCap: Controllable Region-level Captioning
The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue.
Ranked #1 on
Dense Captioning
on Visual Genome
In-context Learning with Retrieved Demonstrations for Language Models: A Survey
Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context.
VMamba: Visual State Space Model
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have long been the predominant backbone networks for visual representation learning.
End-to-end Learnable Clustering for Intent Learning in Recommendation
Concretely, we encode users' behavior sequences and initialize the cluster centers (latent intents) as learnable neurons.
A Reliable Representation with Bidirectional Transition Model for Visual Reinforcement Learning Generalization
Visual reinforcement learning has proven effective in solving control tasks with high-dimensional observations.
Navigating Privacy and Copyright Challenges Across the Data Lifecycle of Generative AI
The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data patterns.
SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer
As the third-generation neural network, the Spiking Neural Network (SNN) has the advantages of low power consumption and high energy efficiency, making it suitable for implementation on edge devices.
Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems.
At Which Training Stage Does Code Data Help LLMs Reasoning?
Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning.
Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption
Motivated by the synthetic control method, we construct a synthetic treatment group for the target population by a weighted mixture of treatment groups of source populations.
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i. e. text, image, video, audio, IMU motion sensor), and generates textual responses.
Ranked #7 on
Video Question Answering
on STAR Benchmark
TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification
We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video.
Parameter identifiability and model selection for partial differential equation models of cell invasion
When employing mechanistic models to study biological phenomena, practical parameter identifiability is important for making accurate predictions across wide range of unseen scenarios, as well as for understanding the underlying mechanisms.
Large Language Models for Software Engineering: A Systematic Literature Review
Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.
Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?
Since the recent prosperity of Large Language Models (LLMs), there have been interleaved discussions regarding how to reduce hallucinations from LLM responses, how to increase the factuality of LLMs, and whether Knowledge Graphs (KGs), which store the world knowledge in a symbolic form, will be replaced with LLMs.
DealMVC: Dual Contrastive Calibration for Multi-view Clustering
Then, a global contrastive calibration loss is proposed by aligning the view feature similarity graph and the high-confidence pseudo-label graph.
CONVERT:Contrastive Graph Clustering with Reliable Augmentation
To address these problems, we propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (CONVERT).
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection.
Ranked #2 on
Object Detection
on VEDAI
Reinforcement Graph Clustering with Unknown Cluster Number
To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC).
Decentralised Governance-Driven Architecture for Designing Foundation Model based Systems: Exploring the Role of Blockchain in Responsible AI
Foundation models including large language models (LLMs) are increasingly attracting interest worldwide for their distinguished capabilities and potential to perform a wide variety of tasks.
Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning
To this end, we propose the graph Structure Guided Multimodal Pretrained Transformer for knowledge graph reasoning, termed SGMPT.
arXiv4TGC: Large-Scale Datasets for Temporal Graph Clustering
It makes evaluating models for large-scale temporal graph clustering challenging.
Analytical reconstructions of full-scan multiple source-translation computed tomography under large field of views
This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV).
Dink-Net: Neural Clustering on Large Graphs
Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner.
Distributed Trust Through the Lens of Software Architecture
Distributed trust is a nebulous concept that has evolved from different perspectives in recent years.
Message Intercommunication for Inductive Relation Reasoning
However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs.
Deep Temporal Graph Clustering
To solve the problem, we propose a general framework for deep Temporal Graph Clustering called TGC, which introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs.
A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture
The recent release of large language model (LLM) based chatbots, such as ChatGPT, has attracted huge interest in foundation models.
Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
In this paper, we propose a \textit{simple yet effective} model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning
Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i. e., data-rich relations with similar contextual semantics to the target data-poor relation.
Poisson Conjugate Prior for PHD Filtering based Track-Before-Detect Strategies in Radar Systems
A variety of filters with track-before-detect (TBD) strategies have been developed and applied to low signal-to-noise ratio (SNR) scenarios, including the probability hypothesis density (PHD) filter.
Industrial computed tomography based intelligent non-destructive testing method for power capacitor
Power capacitor device is a widely used reactive power compensation equipment in power transmission and distribution system which can easily have internal fault and therefore affects the safe operation of the power system.
Cluster-guided Contrastive Graph Clustering Network
Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views.
Decentralized Gradient Tracking with Local Steps
Gradient tracking (GT) is an algorithm designed for solving decentralized optimization problems over a network (such as training a machine learning model).
Swin MAE: Masked Autoencoders for Small Datasets
The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets.
Hard Sample Aware Network for Contrastive Deep Graph Clustering
Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal
According to the graph types, existing KGR models can be roughly divided into three categories, i. e., static models, temporal models, and multi-modal models.
Attribute Graph Clustering via Learnable Augmentation
To this end, we propose an Attribute Graph Clustering method via Learnable Augmentation (\textbf{AGCLA}), which introduces learnable augmentors for high-quality and suitable augmented samples for CDGC.
Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View
However, they neglect the subgraph-subgraph comparison information which the normal and abnormal subgraph pairs behave differently in terms of embeddings and structures in GAD, resulting in sub-optimal task performance.
A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource
However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field.
Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models.
High Dynamic Range Image Quality Assessment Based on Frequency Disparity
In this paper, a novel and effective image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range (HDR) images is proposed, termed as local-global frequency feature-based model (LGFM).
PatchDropout: Economizing Vision Transformers Using Patch Dropout
This simple approach, PatchDropout, reduces FLOPs and memory by at least 50% in standard natural image datasets such as ImageNet, and those savings only increase with image size.
Sparse-based Domain Adaptation Network for OCTA Image Super-Resolution Reconstruction
To be more specific, we first perform a simple degradation of the 3x3 mm2/high-resolution (HR) image to obtain the synthetic LR image.
Multiple Kernel Clustering with Dual Noise Minimization
As a representative, late fusion MKC first decomposes the kernels into orthogonal partition matrices, then learns a consensus one from them, achieving promising performance recently.
On the Representation of Causal Background Knowledge and its Applications in Causal Inference
Causal background knowledge about the existence or the absence of causal edges and paths is frequently encountered in observational studies.
Spatial Transformation for Image Composition via Correspondence Learning
Instead, we propose a novel correspondence learning network (CorrelNet) to model the correspondence between foreground and background using cross-attention maps, based on which we can predict the target coordinate that each source coordinate of foreground should be mapped to on the background.
Mixed Graph Contrastive Network for Semi-Supervised Node Classification
Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years.
Simple Contrastive Graph Clustering
To solve this problem, we propose a Simple Contrastive Graph Clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function.
FedSynth: Gradient Compression via Synthetic Data in Federated Learning
Model compression is important in federated learning (FL) with large models to reduce communication cost.
Improved Dual Correlation Reduction Network
Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task.
Deep Graph Clustering via Dual Correlation Reduction
To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner.
Temporal epistasis inference from more than 3,500,000 SARS-CoV-2 Genomic Sequences
We use Direct Coupling Analysis (DCA) to determine epistatic interactions between loci of variability of the SARS-CoV-2 virus, segmenting genomes by month of sampling.
Siamese Attribute-missing Graph Auto-encoder
First, we entangle the attribute embedding and structure embedding by introducing a siamese network structure to share the parameters learned by both processes, which allows the network training to benefit from more abundant and diverse information.
CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
Interval and large invasive breast cancers, which are associated with worse prognosis than other cancers, are usually detected at a late stage due to false negative assessments of screening mammograms.
Control of diffusion-driven pattern formation behind a wave of competency
In certain biological contexts, such as the plumage patterns of birds and stripes on certain species of fishes, pattern formation takes place behind a so-called "wave of competency".
AutoNLU: Detecting, root-causing, and fixing NLU model errors
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task.
Lagrangian Inference for Ranking Problems
Our proposed method aims to infer general ranking properties of the BTL model.
Mutation frequency time series reveal complex mixtures of clones in the world-wide SARS-CoV-2 viral population
We compute the allele frequencies of the alpha (B. 1. 1. 7), beta (B. 1. 351) and delta (B. 167. 2) variants of SARS-CoV-2 from almost two million genome sequences on the GISAID repository.
Blockchain-based Trustworthy Federated Learning Architecture
To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture.
Entity Resolution in Open-domain Conversations
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest.
Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved.
Towards Demystifying Serverless Machine Learning Training
The appeal of serverless (FaaS) has triggered a growing interest on how to use it in data-intensive applications such as ETL, query processing, or machine learning (ML).
Option to survive or surrender: carbon asset management and optimization in thermal power enterprises from China
Considering the impact of price fluctuations of carbon emission right allowance, we investigate the operation of Chinese thermal power plant by modeling the decision-making with optimal stopping problem, which is established on the stochastic environment with carbon emission allowance price process simulated by geometric Brownian motion.
Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.
Deep Learning for Android Malware Defenses: a Systematic Literature Review
In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.
A Local Method for Identifying Causal Relations under Markov Equivalence
We propose a local approach to identify whether a variable is a cause of a given target under the framework of causal graphical models of directed acyclic graphs (DAGs).
Electron heating mode transitions in radio-frequency driven micro atmospheric pressure plasma jets in He/O$_{2}$: A fluid dynamics approach
A two-dimensional fluid model is used to investigate the electron heating dynamics and the production of neutral species in a capacitively coupled radio-frequency micro atmospheric pressure helium plasma jet -- specifically the COST jet -- with a small oxygen admixture.
Plasma Physics
Out-of-Distribution Generalization Analysis via Influence Function
One of the definitions of OOD accuracy is worst-domain accuracy.
Electron pairing in the pseudogap state revealed by shot noise in copper-oxide junctions
In the quest to understand high-temperature superconductivity in copper oxides, a vigorous debate has been focused on the pseudogap - a partial gap that opens over portions of the Fermi surface in the 'normal' state above the bulk critical temperature ($T_{c}$).
Superconductivity Mesoscale and Nanoscale Physics Strongly Correlated Electrons
Reconstruction Condition of Quantized Signals in Unlimited Sampling Framework
The latest theoretical advances in the field of unlimited sampling framework (USF) show the potential to avoid clipping problems of analog-to-digital converters (ADC).
Deep Neural Network Approach for Annual Luminance Simulations
The proposed DNN model can faithfully predict high-quality annual panoramic luminance maps from one of the three options within 30 minutes training time: a) point-in-time luminance imagery spanning 5% of the year, when evenly distributed during daylight hours, b) one-month hourly imagery generated or collected continuously during daylight hours around the equinoxes (8% of the year); or c) 9 days of hourly data collected around the spring equinox, summer and winter solstices (2. 5% of the year) all suffice to predict the luminance maps for the rest of the year.
Blockchain-based Federated Learning for Failure Detection in Industrial IoT
Therefore, in this paper, we present a platform architecture of blockchain-based federated learning systems for failure detection in IIoT.
Video Moment Retrieval via Natural Language Queries
However, the inference time will not be a problem for our model since our model has a simple architecture which enables efficient training and inference.
Adding Seemingly Uninformative Labels Helps in Low Data Regimes
Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features.
Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
With this in mind, we trained networks using three different criteria to select the positive training data (i. e. images from patients that will develop cancer): an inherent risk model trained on images with no visible signs of cancer, a cancer signs model trained on images containing cancer or early signs of cancer, and a conflated model trained on all images from patients with a cancer diagnosis.
Online NEAT for Credit Evaluation -- a Dynamic Problem with Sequential Data
In this paper, we describe application of Neuroevolution to a P2P lending problem in which a credit evaluation model is updated based on streaming data.
Risk Variance Penalization
The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains.
On Low Rank Directed Acyclic Graphs and Causal Structure Learning
Despite several advances in recent years, learning causal structures represented by directed acyclic graphs (DAGs) remains a challenging task in high dimensional settings when the graphs to be learned are not sparse.
Stable Prediction via Leveraging Seed Variable
By assuming the relationships between causal variables and response variable are invariant across data, to address this problem, we propose a conditional independence test based algorithm to separate those causal variables with a seed variable as priori, and adopt them for stable prediction.
Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices
For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations.
RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System
Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes.
Spots, strips, and spiral waves in models for static and motile cells
The polarization and motility of eukaryotic cells depends on assembly and contraction of the actin cytoskeleton and its regulation by proteins called GTPases.
Characterizing and Predicting Repeat Food Consumption Behavior for Just-in-Time Interventions
Human beings are creatures of habit.
Estimating Glycemic Impact of Cooking Recipes via Online Crowdsourcing and Machine Learning
Consumption of diets with low glycemic impact is highly recommended for diabetics and pre-diabetics as it helps maintain their blood glucose levels.
Causal Discovery by Kernel Intrinsic Invariance Measure
We show our algorithm can be reduced to an eigen-decomposition task on a kernel matrix measuring intrinsic deviance/invariance.
Cell size, mechanical tension, and GTPase signaling in the Single Cell
We further consider the feedback between mechanical tension, GTPase activation, and cell deformation in both static, growing, shrinking, and moving cells.
Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality
Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information.
Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text
Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings.
Recurrent knowledge distillation
Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network.
Exploiting Task-Oriented Resources to Learn Word Embeddings for Clinical Abbreviation Expansion
In the medical domain, identifying and expanding abbreviations in clinical texts is a vital task for both better human and machine understanding.
Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models
Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision.
