Search Results for author:
Found 163 papers, 84 papers with code
OID: Outlier Identifying and Discarding in Blind Image Deblurring
Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.
Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
Enhanced Sparse Model for Blind Deblurring
Specifically, we use a weighted combination of a dense function (i. e. l2) and a newly designed enhanced sparse model termed as le, which is developed from two sparse models (i. e. l1 and l0), to fulfill the task.
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective
Graph autoencoders (GAEs) are self-supervised learning models that can learn meaningful representations of graph-structured data by reconstructing the input graph from a low-dimensional latent space.
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment
As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial.
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e. g., OpenAI o1 achieves 94. 8% on MATH dataset), indicating their inadequacy for truly challenging these models.
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer.
LGFN: Lightweight Light Field Image Super-Resolution using Local Convolution Modulation and Global Attention Feature Extraction
Specifically owing to neighboring regions of the same pixel position in different sub-aperture images exhibit similar structural relationships we design a lightweight CNN-based feature extraction module (namely DGCE) to extract local features better through feature modulation.
Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
The limited training samples for object detectors commonly result in low accuracy out-of-distribution (OOD) object detection.
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.
TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
However, this approach introduces a data imbalance biased to novel data that presents a new challenge of catastrophic forgetting.
L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering
Surprisingly, we find that L2CL, using only one-hop contrastive learning paradigm, is able to capture intrinsic semantic structures and improve the quality of node representation, leading to a simple yet effective architecture.
PID: Physics-Informed Diffusion Model for Infrared Image Generation
Infrared imaging technology has gained significant attention for its reliable sensing ability in low visibility conditions, prompting many studies to convert the abundant RGB images to infrared images.
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing.
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation
Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image, a question, and several options.
Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective
Another promising line of research involves the adoption of modularity maximization, a popular and effective measure for community detection, as the guiding principle for clustering tasks.
One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
Accordingly, we propose a graph fairness framework based on invariant learning, namely FairINV, which enables the training of fair GNNs to accommodate various sensitive attributes within a single training session.
State Space Models on Temporal Graphs: A First-Principles Study
Recently, state space models (SSMs), which are framed as discretized representations of an underlying continuous-time linear dynamical system, have garnered substantial attention and achieved breakthrough advancements in independent sequence modeling.
Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketing
Uplift modeling has been widely employed in online marketing by predicting the response difference between the treatment and control groups, so as to identify the sensitive individuals toward interventions like coupons or discounts.
DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment
Firstly, we propose the Class-wise Prototypes Alignment (CPA) module, which effectively aligns cross-domain features in a class-aware manner by bridging the gap between object detection task and domain adaptation task.
Fair Graph Representation Learning via Sensitive Attribute Disentanglement
In particular, the objective of group fairness is to ensure that the decisions made by GNNs are independent of the sensitive attribute.
Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models.
Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
Therefore, we introduce ALSACE to leverage the learned knowledge from the well-performing languages to guide under-performing ones within the same mPLM, eliminating the need for additional labeled multilingual data.
SGHormer: An Energy-Saving Graph Transformer Driven by Spikes
However, the costs behind outstanding performances of GTs are higher energy consumption and computational overhead.
A Causal Inspired Early-Branching Structure for Domain Generalization
By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework.
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
To this end, we introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency by learning adaptive attention patterns in early layers and pruning visual tokens in subsequent ones.
Consecutive Batch Model Editing with HooK Layers
As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive and batch scenarios to edit the model behavior directly.
PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
Although LoRA fine-tuning is effective, there is still a performance gap compared to full fine-tuning, since its weight update is limited to low-rank matrices.
PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain
To address this, we introduce Embodied-Instruction-Evolution (EIE), an automatic framework for synthesizing instruction tuning examples in multimodal embodied environments.
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.
Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networks
Firstly, TAHyper employs the hyperbolic space to encode the social networks, thereby effectively reducing the distortion of confounder representation caused by Euclidean embeddings.
Expected Transaction Value Optimization for Precise Marketing in FinTech Platforms
In addition to predicting the click-through rate (CTR) or the conversion rate (CVR) as in traditional recommendations, it is essential for FinTech platforms to estimate the customers' purchase amount for each delivered fund and achieve an effective allocation of impressions based on the predicted results to optimize the total expected transaction value (ETV).
Silkie: Preference Distillation for Large Visual Language Models
This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual context.
Ranked #38 on
Visual Question Answering
on MM-Vet
VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook
In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks.
Rethinking and Simplifying Bootstrapped Graph Latents
Graph contrastive learning (GCL) has emerged as a representative paradigm in graph self-supervised learning, where negative samples are commonly regarded as the key to preventing model collapse and producing distinguishable representations.
The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
Experiments on several benchmark datasets demonstrate that FairGKD, which does not require access to demographic information, significantly improves the fairness of GNNs by a large margin while maintaining their utility.
A Survey of the Evolution of Language Model-Based Dialogue Systems
This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in language models by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e. g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly.
LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data.
WatME: Towards Lossless Watermarking Through Lexical Redundancy
Text watermarking has emerged as a pivotal technique for identifying machine-generated text.
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
Despite Large Language Models (LLMs) like GPT-4 achieving impressive results in function-level code generation, they struggle with repository-scale code understanding (e. g., coming up with the right arguments for calling routines), requiring a deeper comprehension of complex file interactions.
Self-Guard: Empower the LLM to Safeguard Itself
Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards.
Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks.
Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Through in-depth investigations on several real-world heterogeneous graphs exhibiting varying levels of heterophily, we have observed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, fail to generalize to heterogeneous graphs with heterophily or low level of homophily.
Language Agents for Detecting Implicit Stereotypes in Text-to-image Models at Scale
The recent surge in the research of diffusion models has accelerated the adoption of text-to-image models in various Artificial Intelligence Generated Content (AIGC) commercial products.
Guiding AMR Parsing with Reverse Graph Linearization
Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence.
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge.
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages.
Synaptic delay induced macroscopic dynamics of the large-scale network of Izhikevich neurons
We investigate the impact of the heterogeneity of the quenched input current, the SFA mechanism and the synaptic delay on macroscopic dynamics.
Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond
In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents.
Meta Semantic Template for Evaluation of Large Language Models
We hope this initial work can shed light on future research of LLMs evaluation.
Existence of a Competitive Equilibrium with Substitutes, with Applications to Matching and Discrete Choice Models
We propose new results for the existence and uniqueness of a general nonparametric and nonseparable competitive equilibrium with substitutes.
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts.
Ranked #16 on
Visual Reasoning
on Winoground
Making Large Language Models Better Reasoners with Alignment
To address this problem, we introduce an \textit{Alignment Fine-Tuning (AFT)} paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss.
Domain Generalization via Rationale Invariance
Specifically, we propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix.
SAILOR: Structural Augmentation Based Tail Node Representation Learning
In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.
A Self-supervised SAR Image Despeckling Strategy Based on Parameter-sharing Convolutional Neural Networks
The training image pairs are generated by the sub-sampler from real-word SAR image to estimate the noise distribution.
Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring
In this paper, we develop a data-driven approach to model the saturated pixels by a learned latent map.
M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning
To tackle this challenge and promote research in the vision-language field, we introduce the Multi-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed to optimize VLM alignment with human instructions.
Oversmoothing: A Nightmare for Graph Contrastive Learning?
Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance.
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footprint, and energy consumption burden (largely overlooked) for real-world applications.
Large Language Models are not Fair Evaluators
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e. g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models.
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.
TransWorldNG: Traffic Simulation via Foundation Model
To the best of our knowledge, this is the first traffic simulator that can automatically learn traffic patterns from real-world data and efficiently generate accurate and realistic traffic environments.
Building Transportation Foundation Model via Generative Graph Transformer
This data-driven and model-free simulation method addresses the challenges faced by traditional systems in terms of structural complexity and model accuracy and provides a foundation for solving complex transportation problems with real data.
Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation.
On the robust learning mixtures of linear regressions
In this note, we consider the problem of robust learning mixtures of linear regressions.
SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs
Anomaly detection aims to distinguish abnormal instances that deviate significantly from the majority of benign ones.
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Generating persona consistent dialogue response is important for developing an intelligent conversational agent.
Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs
We approach the problem by our proposed STEP, a self-supervised temporal pruning framework that learns to remove potentially redundant edges from input dynamic graphs.
On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
We conduct experiments on a multilingual machine translation benchmark in 11 languages.
Estimation of Characteristics-based Quantile Factor Models
This paper studies the estimation of characteristic-based quantile factor models where the factor loadings are unknown functions of observed individual characteristics while the idiosyncratic error terms are subject to conditional quantile restrictions.
Common Correlated Effects Estimation of Nonlinear Panel Data Models
This paper focuses on estimating the coefficients and average partial effects of observed regressors in nonlinear panel data models with interactive fixed effects, using the common correlated effects (CCE) framework.
Curriculum Modeling the Dependence among Targets with Multi-task Learning for Financial Marketing
For example, in online marketing, the cascade behavior pattern of $impression \rightarrow click \rightarrow conversion$ is usually modeled as multiple tasks in a multi-task manner, where the sequential dependence between tasks is simply connected with an explicitly defined function or implicitly transferred information in current works.
Efficient Halftoning via Deep Reinforcement Learning
In this paper, we propose a fast and structure-aware halftoning method via a data-driven approach.
Cross-View Hierarchy Network for Stereo Image Super-Resolution
Stereo image super-resolution aims to improve the quality of high-resolution stereo image pairs by exploiting complementary information across views.
Improved Test-Time Adaptation for Domain Generalization
Generally, a TTT strategy hinges its performance on two main factors: selecting an appropriate auxiliary TTT task for updating and identifying reliable parameters to update during the test phase.
Ranked #4 on
Image to sketch recognition
on PACS
Image to sketch recognition
Single-Source Domain Generalization
+1
Manipulating Federated Recommender Systems: Poisoning with Synthetic Users and Its Countermeasures
To reveal the real vulnerability of FedRecs, in this paper, we present a new poisoning attack method to manipulate target items' ranks and exposure rates effectively in the top-$K$ recommendation without relying on any prior knowledge.
Self-Sampling Training and Evaluation for the Accuracy-Bias Tradeoff in Recommendation
Specifically, SSTE uses a self-sampling module to generate some subsets with different degrees of bias from the original training and validation data.
Optimizing Feature Set for Click-Through Rate Prediction
Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates.
Ranked #4 on
Click-Through Rate Prediction
on KDD12
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder
Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2. 23% mIOU with superior generalization ability.
MR Elastography with Optimization-Based Phase Unwrapping and Traveling Wave Expansion-based Neural Network (TWENN)
Here we propose a pipeline for processing MRE images using optimization-based displacement extraction and Traveling Wave Expansion-based Neural Network (TWENN) modulus estimation.
Spectral Adversarial Training for Robust Graph Neural Network
In this work, we seek to address these challenges and propose Spectral Adversarial Training (SAT), a simple yet effective adversarial training approach for GNNs.
Are All Edges Necessary? A Unified Framework for Graph Purification
Graph Neural Networks (GNNs) as deep learning models working on graph-structure data have achieved advanced performance in many works.
Large-batch Optimization for Dense Visual Predictions
To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.
A Two-Stage Method for Chinese AMR Parsing
In this paper, we provide a detailed description of our system at CAMRP-2022 evaluation.
Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation
Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics.
Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks
We explore a new direction in that we can capture the evolving dynamics of temporal graphs with spiking neural networks (SNNs) instead of RNNs.
Re-thinking and Re-labeling LIDC-IDRI for Robust Pulmonary Cancer Prediction
The LIDC-IDRI database is the most popular benchmark for lung cancer prediction.
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery.
What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders
The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding.
Spiking Graph Convolutional Networks
Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information.
A Survey of Deep Learning Models for Structural Code Understanding
In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights.
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation
Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect.
GUARD: Graph Universal Adversarial Defense
To mitigate such a threat, considerable research efforts have been devoted to increasing the robustness of GCNs against adversarial attacks.
ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs
As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing.
Ranked #7 on
AMR Parsing
on LDC2020T02
(using extra training data)
Self-Calibrated Efficient Transformer for Lightweight Super-Resolution
Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance.
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations.
Exact mean-field models for spiking neural networks with adaptation
Networks of spiking neurons with adaption have been shown to be able to reproduce a wide range of neural activities, including the emergent population bursting and spike synchrony that underpin brain disorders and normal function.
CAR: Class-aware Regularizations for Semantic Segmentation
Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules.
Ranked #8 on
Semantic Segmentation
on PASCAL Context
Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
Faithful learning with sure data for lung nodule diagnosis
In this study, we construct a sure dataset with pathologically-confirmed labels and propose a collaborative learning framework to facilitate sure nodule classification by integrating unsure data knowledge through nodule segmentation and malignancy score regression.
Enhanced DeepONet for Modeling Partial Differential Operators Considering Multiple Input Functions
We propose new Enhanced DeepONet or EDeepONet high-level neural network structure, in which two input functions are represented by two branch DNN sub-networks, which are then connected with output truck network via inner product to generate the output of the whole neural network.
Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack
Despite the progress, applying DGL to real-world applications faces a series of reliability threats including inherent noise, distribution shift, and adversarial attacks.
Robust Dynamic State Estimator of Integrated Energy Systems based on Natural Gas Partial Differential Equations
A novel robust dynamic state estimation methodology for integrated natural gas and electric power systems is proposed based on Kalman filter.
Neighboring Backdoor Attacks on Graph Convolutional Network
To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node.
Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation
Therefore, in this paper, we propose a Geometric anchor-guided Adversarial and conTrastive learning framework with uncErtainty modeling called GATE to alleviate these issues.
Ranked #5 on
Universal Domain Adaptation
on Office-Home
Carrier Phase Ranging for Indoor Positioning with 5G NR Signals
Indoor positioning is one of the core technologies of Internet of Things (IoT) and artificial intelligence (AI), and is expected to play a significant role in the upcoming era of AI.
Perceiving and Modeling Density is All You Need for Image Dehazing
However, due to the paradox caused by the variation of real captured haze and the fixed degradation parameters of the current networks, the generalization ability of recent dehazing methods on real-world hazy images is not ideal. To address the problem of modeling real-world haze degradation, we propose to solve this problem by perceiving and modeling density for uneven haze distribution.
Ranked #7 on
Image Dehazing
on Haze4k
Hierarchical Curriculum Learning for AMR Parsing
Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.
SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring
On this basis, we reduce the number of up-sampling and down-sampling and design a simple network structure.
Ranked #1 on
Image Deblurring
on RealBlur-R(trained on GoPro)
Incorporating Surprisingly Popular Algorithm and Euclidean Distance-based Adaptive Topology into PSO
While many Particle Swarm Optimization (PSO) algorithms only use fitness to assess the performance of particles, in this work, we adopt Surprisingly Popular Algorithm (SPA) as a complementary metric in addition to fitness.
DGCN: Diversified Recommendation with Graph Convolutional Networks
These years much effort has been devoted to improving the accuracy or relevance of the recommendation system.
Understanding Structural Vulnerability in Graph Convolutional Networks
In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i. e., the weighted mean) of GCNs.
Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation
The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training.
Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation
Therefore, backward-compatible representation is proposed to enable "new" features to be compared with "old" features directly, which means that the database is active when there are both "new" and "old" features in it.
Physics-Enforced Modeling for Insertion Loss of Transmission Lines by Deep Neural Networks
In the second method, a third-order polynomial expression is defined first, which ensures positiveness, to approximate the insertion loss, then DeepONet neural network structure, which was proposed recently for function and system modeling, was employed to model the coefficients of polynomials.
Dynamic State Estimation for Integrated Natural Gas and Electric Power Systems
Boundary conditions of pipeline networks are used as supplementary constraints in the system model.
Blind Deblurring for Saturated Images
To address this problem, we introduce a new blur model to fit both saturated and unsaturated pixels, and all informative pixels can be considered during deblurring process.
Learning a Non-Blind Deblurring Network for Night Blurry Images
Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels.
DNA-GCN: Graph convolutional networks for predicting DNA-protein binding
Predicting DNA-protein binding is an important and classic problem in bioinformatics.
Signal Acquisition of Luojia-1A Low Earth Orbit Navigation Augmentation System with Software Defined Receiver
The performance of those integration algorithms on expanding the successful acquisition time range is verified by the real data collected from the Luojia-1A satellite.
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
Proposal of large-scale datasets has facilitated research on deep neural models for news summarization.
Abstractive Dialogue Summarization
Common Sense Reasoning
+3
AutoDebias: Learning to Debias for Recommendation
This provides a valuable opportunity to develop a universal solution for debiasing, e. g., by learning the debiasing parameters from data.
Personalized Bundle Recommendation in Online Games
In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.
Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation
As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.
Model-based Reinforcement Learning
Recommendation Systems
+3
Neural Architecture Search based on Cartesian Genetic Programming Coding Method
To evolve the architectures under the framework of CGP, the operations such as convolution are identified as the types of function nodes of CGP, and the evolutionary operations are designed based on Evolutionary Strategy.
Robust Kalman filter-based dynamic state estimation of natural gas pipeline networks
To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.
A High-dimensional Sparse Fourier Transform in the Continuous Setting
In this paper, we theoretically propose a new hashing scheme to establish the sparse Fourier transform in high-dimensional space.
Data Structures and Algorithms Information Theory Numerical Analysis Information Theory Numerical Analysis 41A63 G.1.2; F.2.1
GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.
Calculation of Photocarrier Generation from Optical Absorption for Time-domain Simulation of Optoelectronic Devices
In this work, an optical absorption-based model is proposed to accurately calculate the generation rate in time-domain simulations.
Optics Computational Engineering, Finance, and Science Computational Physics
A possible blazar spectral irregularity case caused by photon--axionlike-particle oscillations
We investigate this possibility by fitting the spectrum with the photon-ALP oscillation model, and find that the parameter space of ALP mass $m_a\leq 10^{-8}$\, eV and the coupling constant (between photons and ALPs) $g_{a\gamma}$=1. 16--1. 48$\times 10^{-10}$\, GeV$^{-1}$ can provide a fit to the line-like feature, while the magnetic field at the emission site of $\gamma$-rays is fixed at 0. 7\, G.
High Energy Astrophysical Phenomena
Lower Bound on the Optimal Access Bandwidth of ($K+2,K,2$)-MDS Array Code with Degraded Read Friendly
Accessing the data in the failed disk (degraded read) with low latency is crucial for an erasure-coded storage system.
Information Theory Information Theory
Matching Function Equilibria with Partial Assignment: Existence, Uniqueness and Estimation
We argue that models coming from a variety of fields, such as matching models and discrete choice models among others, share a common structure that we call matching function equilibria with partial assignment.
Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control
To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity.
Decoding PPP Corrections from BDS B2b Signals Using a Software-defined Receiver: an Initial Performance Evaluation
With the rapid development of China's BeiDou Navigation Satellite System(BDS), the application of real-time precise point positioning (RTPPP) based on BDS has become an active research area in the field of Global Navigation Satellite System (GNSS).
Learning to Sample the Most Useful Training Patches from Images
Some image restoration tasks like demosaicing require difficult training samples to learn effective models.
Ensemble Knowledge Distillation for CTR Prediction
Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications.
GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
Most existing GNN models exploit a single type of aggregator (e. g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node.
Self-supervised Graph Learning for Recommendation
In this work, we explore self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation.
Ranked #6 on
Collaborative Filtering
on Yelp2018
Stochastic Time-Periodic Tonelli Lagrangian on Compact Manifold
In this paper, we study a class of time-periodic stochastic Tonelli Lagrangians on compact manifolds.
Dynamical Systems
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Adversarial Attack on Large Scale Graph
Currently, most works on attacking GNNs are mainly using gradient information to guide the attack and achieve outstanding performance.
Variance-reduced Language Pretraining via a Mask Proposal Network
In particular, we first propose a principled gradient variance decomposition theorem, which shows that the variance of the stochastic gradient of the language pretraining can be naturally decomposed into two terms: the variance that arises from the sample of data in a batch, and the variance that arises from the sampling of the mask.
Interactive Path Reasoning on Graph for Conversational Recommendation
Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user preference.
Realistic Adversarial Data Augmentation for MR Image Segmentation
In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation.
Crossed-Time Delay Neural Network for Speaker Recognition
Time Delay Neural Network (TDNN) is a well-performing structure for DNN-based speaker recognition systems.
