Search Results for author:
Found 95 papers, 26 papers with code
Spelling Correction using Phonetics in E-commerce Search
In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries.
Enforcing Paraphrase Generation via Controllable Latent Diffusion
Paraphrase generation aims to produce high-quality and diverse utterances of a given text.
Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD update
This leads to an interesting open question: Can the local TD-update approach entail low sample and communication complexities?
Strength Lies in Differences! Towards Effective Non-collaborative Dialogues via Tailored Strategy Planning
We investigate non-collaborative dialogue agents that must engage in tailored strategic planning for diverse users to secure a favorable agreement.
DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
The combination of electronic health records (EHR) and medical images is crucial for clinicians in making diagnoses and forecasting prognosis.
Integration of cognitive tasks into artificial general intelligence test for large models
During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application.
Data Distribution Dynamics in Real-World WiFi-Based Patient Activity Monitoring for Home Healthcare
This paper examines the application of WiFi signals for real-world monitoring of daily activities in home healthcare scenarios.
Multi-granularity Correspondence Learning from Long-term Noisy Videos
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos.
Ranked #1 on
Zero-Shot Video Retrieval
on YouCook2
Action Segmentation
Long Video Retrieval (Background Removed)
+2
State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving
Current Large Language Model-based agents reason within an exploration-evaluation framework, navigating problem-solving processes in a tree-like manner.
SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field
We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output.
Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective
Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases.
Explicit Change Relation Learning for Change Detection in VHR Remote Sensing Images
In order to fully mine these three kinds of change features, we propose the triple branch network combining the transformer and convolutional neural network (CNN) to extract and fuse these change features from two perspectives of global information and local information, respectively.
Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments
Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years.
Federated Multi-Objective Learning
In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications.
Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites
Unlike public data, another practical challenge on shopping websites is that some paired images are of low quality.
SwinV2DNet: Pyramid and Self-Supervision Compounded Feature Learning for Remote Sensing Images Change Detection
Therefore, based on swin transformer V2 (Swin V2) and VGG16, we propose an end-to-end compounded dense network SwinV2DNet to inherit the advantages of both transformer and CNN and overcome the shortcomings of existing networks in feature learning.
Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier
Automatic labeling of coronary arteries is an essential task in the practical diagnosis process of cardiovascular diseases.
Geometric Pooling: maintaining more useful information
However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of units dropped by sorting pooling are negative-value units that contain useful information and can contribute considerably to the final decision.
AdaSelection: Accelerating Deep Learning Training through Data Subsampling
In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.
Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals
The machine reading comprehension (MRC) of user manuals has huge potential in customer service.
Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos
First, to avoid the requirement of laborious and unreliable annotation, we propose a novel and effective video classification network for weakly-supervised CSG.
Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach
Automatic detection of machine anomaly remains challenging for machine learning.
Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
To fuse dense image features and sparse point features, we propose a learnable operator named bidirectional camera-LiDAR fusion module (Bi-CLFM).
Ranked #1 on
Scene Flow Estimation
on KITTI 2015 Scene Flow Test
PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities
Decentralized min-max optimization problems with domain constraints underpins many important ML applications, including multi-agent ML fairness assurance, and policy evaluations in multi-agent reinforcement learning.
AI of Brain and Cognitive Sciences: From the Perspective of First Principles
Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation.
AFLGuard: Byzantine-robust Asynchronous Federated Learning
Asynchronous FL aims to address this challenge by enabling the server to update the model once any client's model update reaches it without waiting for other clients' model updates.
FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data
In this paper, we propose a new approach called fair recommendation with optimized antidote data (FairRoad), which aims to improve the fairness performances of recommender systems through the construction of a small and carefully crafted antidote dataset.
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization
Decentralized bilevel optimization has received increasing attention recently due to its foundational role in many emerging multi-agent learning paradigms (e. g., multi-agent meta-learning and multi-agent reinforcement learning) over peer-to-peer edge networks.
CNNArginineMe: A CNN structure for training models for predicting arginine methylation sites based on the One-Hot encoding of peptide sequence
The deep-learning model CNN combined with the One-Hot coding showed the best performance, dubbed CNNArginineMe.
Taming Fat-Tailed ("Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning
A key assumption in most existing works on FL algorithms' convergence analysis is that the noise in stochastic first-order information has a finite variance.
SAGDA: Achieving $\mathcal{O}(ε^{-2})$ Communication Complexity in Federated Min-Max Learning
To lower the communication complexity of federated min-max learning, a natural approach is to utilize the idea of infrequent communications (through multiple local updates) same as in conventional federated learning.
Robust Domain Adaptation for Machine Reading Comprehension
Such a process will inevitably introduce mismatched pairs (i. e., noisy correspondence) due to i) the unavailable QA pairs in target documents, and ii) the domain shift during applying the QA construction model to the target domain.
SYNTHESIS: A Semi-Asynchronous Path-Integrated Stochastic Gradient Method for Distributed Learning in Computing Clusters
To increase the training speed of distributed learning, recent years have witnessed a significant amount of interest in developing both synchronous and asynchronous distributed stochastic variance-reduced optimization methods.
NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data
Moreover, whether or not the linear speedup for convergence is achievable under fully decentralized FL with data heterogeneity remains an open question.
INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks
Our main contributions in this paper are two-fold: i) We first propose a deterministic algorithm called INTERACT (inner-gradient-descent-outer-tracked-gradient) that requires the sample complexity of $\mathcal{O}(n \epsilon^{-1})$ and communication complexity of $\mathcal{O}(\epsilon^{-1})$ to solve the bilevel optimization problem, where $n$ and $\epsilon > 0$ are the number of samples at each agent and the desired stationarity gap, respectively.
Bi-fidelity Evolutionary Multiobjective Search for Adversarially Robust Deep Neural Architectures
First, we formulate the NAS problem for enhancing adversarial robustness of deep neural networks into a multiobjective optimization problem.
A Dual-fusion Semantic Segmentation Framework With GAN For SAR Images
With the better representation capability of optical images, we propose to enrich SAR images with generated optical images via the generative adversative network (GAN) trained by numerous SAR and optical images.
Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
In order to fully utilize this advantage while providing comparable learning performance to conventional federated learning that presumes model aggregation via noiseless channels, we consider the joint design of transmission scaling and the number of local iterations at each round, given the power constraint at each edge device.
An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection
In this paper, we propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection, namely SDACD, to effectively alleviate the domain shift between bi-temporal images for better change predictions.
Change Detection
Change detection for remote sensing images
+1
Probabilistic Mass Mapping with Neural Score Estimation
We introduce a novel methodology allowing for efficient sampling of the high-dimensional Bayesian posterior of the weak lensing mass-mapping problem, and relying on simulations for defining a fully non-Gaussian prior.
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning
To our knowledge, this paper is the first work that achieves both $\mathcal{O}(\epsilon^{-2})$ sample complexity and $\mathcal{O}(\epsilon^{-2})$ communication complexity in decentralized policy evaluation for cooperative MARL.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
+1
Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons
Here, a multi-wise comparison takes $m$ items as input and returns a (noisy) result about the best item (the winner feedback) or the order of these items (the full-ranking feedback).
CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data.
Ranked #3 on
Scene Flow Estimation
on Spring
A global convergence theory for deep ReLU implicit networks via over-parameterization
Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures.
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
We analyze the optimization and the generalization performance of the proposed framework for the $\ell_2$ loss.
Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences
We show that the delay impacts in both cases can still be upper bounded by an additive penalty on both the regret and total incentive costs.
Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward
In this paper, we establish the first finite-time convergence result of the actor-critic algorithm for fully decentralized multi-agent reinforcement learning (MARL) problems with average reward.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field.
Anarchic Federated Learning
To satisfy the need for flexible worker participation, we consider a new FL paradigm called "Anarchic Federated Learning" (AFL) in this paper.
Federated Learning with Fair Worker Selection: A Multi-Round Submodular Maximization Approach
Considering the achieved training accuracy of the global model as the utility of the selected workers, which is typically a monotone submodular function, we formulate the worker selection problem as a new multi-round monotone submodular maximization problem with cardinality and fairness constraints.
The Role of "Live" in Livestreaming Markets: Evidence Using Orthogonal Random Forest
Over the post-livestream period, the demand for the recorded version is still sensitive to price, but much less than in the pre-livestream period.
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution.
CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning
This matches the convergence rate of distributed/federated learning without compression, thus achieving high communication efficiency while not sacrificing learning accuracy in FL.
Incentivized Bandit Learning with Self-Reinforcing User Preferences
In this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pull the arms by itself and thus has to offer rewards to users to incentivize arm-pulling indirectly; and (ii) if users with specific arm preferences are well rewarded, they induce a "self-reinforcing" effect in the sense that they will attract more users of similar arm preferences.
GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning
Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity.
Data Poisoning Attacks and Defenses to Crowdsourcing Systems
Our empirical results show that the proposed defenses can substantially reduce the estimation errors of the data poisoning attacks.
Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning
Our results also reveal that the local steps in FL could help the convergence and show that the maximum number of local steps can be improved to $T/m$ in full worker participation.
Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans.
Distributionally robust second-order stochastic dominance constrained optimization with Wasserstein ball
We consider a distributionally robust second-order stochastic dominance constrained optimization problem.
Optimization and Control 90C15, 91B70, 90C31, 90-08
FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
Finally, the service provider computes the average of the normalized local model updates weighted by their trust scores as a global model update, which is used to update the global model.
$κ$TNG: Effect of Baryonic Processes on Weak Lensing with IllustrisTNG Simulations
The $\kappa$TNG suite includes 10, 000 realisations of $5 \times 5 \, \mathrm{deg}^2$ maps for 40 source redshifts up to $z_s = 2. 6$, well covering the range of interest for existing and upcoming weak lensing surveys.
Cosmology and Nongalactic Astrophysics
The Scale of Superpartner Masses and Electroweakino Searches at the High-Luminosity LHC
Searches for weakly interacting particles is one of the main goals of the high luminosity LHC run.
High Energy Physics - Phenomenology High Energy Physics - Experiment
The Sample Complexity of Best-$k$ Items Selection from Pairwise Comparisons
From a given set of items, the learner can make pairwise comparisons on every pair of items, and each comparison returns an independent noisy result about the preferred item.
Multi-Armed Bandits with Local Differential Privacy
To handle this dilemma, we adopt differential privacy and study the regret upper and lower bounds for MAB algorithms with a given LDP guarantee.
Re-examining the Solar Axion Explanation for the XENON1T Excess
Meanwhile, they can also scatter with the atoms through the inverse Primakoff process via the axion-photon coupling, which emits a photon and mimics the electronic recoil signals.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Transformation Importance with Applications to Cosmology
Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence.
Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
Given the number of fake users the attacker can inject, we formulate the crafting of rating scores for the fake users as an optimization problem.
Toward Low-Cost and Stable Blockchain Networks
To address the high mining cost problem of blockchain networks, in this paper, we propose a blockchain mining resources allocation algorithm to reduce the mining cost in PoW-based (proof-of-work-based) blockchain networks.
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
Under a sparse true linear regression model with $p$ i. i. d.
Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Further, we show that the iteration complexity of the proposed method is $O(n\varepsilon^{-2})$ to achieve $\epsilon$-stationary point, where $n$ is the number of blocks of coordinates.
Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
In this paper, we consider the problem of jointly improving data privacy and communication efficiency of distributed edge learning, both of which are critical performance metrics in wireless edge network computing.
Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
In the applications of signal processing and data analytics, there is a wide class of non-convex problems whose objective function is freed from the common global Lipschitz continuous gradient assumption (e. g., the nonnegative matrix factorization (NMF) problem).
Detecting Cyberattacks in Industrial Control Systems Using Online Learning Algorithms
Similar to other information systems, a significant threat to industrial control systems is the attack from cyberspace---the offensive maneuvers launched by "anonymous" in the digital world that target computer-based assets with the goal of compromising a system's functions or probing for information.
FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation
The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.
Hierarchical Feature-Aware Tracking
Moreover, with the novel expert selection strategy, overfitting caused by fixed experts for each frame can be mitigated.
Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approach
In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to disrupt the training process.
On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons
This paper studies the problem of finding the exact ranking from noisy comparisons.
Urban flows prediction from spatial-temporal data using machine learning: A survey
Urban spatial-temporal flows prediction is of great importance to traffic management, land use, public safety, etc.
Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach
In this work, we consider to improve the model estimation efficiency by aggregating the neighbors' information as well as identify the subgroup membership for each node in the network.
LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #29 on
Real-Time Semantic Segmentation
on Cityscapes test
Nucleus Neural Network: A Data-driven Self-organized Architecture
In this paper, we propose a nucleus neural network (NNN) and corresponding connecting architecture learning method.
Habitat: A Platform for Embodied AI Research
We present Habitat, a platform for research in embodied artificial intelligence (AI).
Ranked #2 on
PointGoal Navigation
on Gibson PointGoal Navigation
Combinatorial Sleeping Bandits with Fairness Constraints
To tackle this new problem, we extend an online learning algorithm, UCB, to deal with a critical tradeoff between exploitation and exploration and employ the virtual queue technique to properly handle the fairness constraints.
Exploring $k$ out of Top $ρ$ Fraction of Arms in Stochastic Bandits
Results in this paper provide up to $\rho n/k$ reductions compared with the "$k$-exploration" algorithms that focus on finding the (PAC) best $k$ arms out of $n$ arms.
Poisoning Attacks to Graph-Based Recommender Systems
To address the challenge, we formulate the poisoning attacks as an optimization problem, solving which determines the rating scores for the fake users.
Multiobjective Optimization Training of PLDA for Speaker Verification
Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers.
Multiobjective Optimization
Text-Independent Speaker Verification
PAC Ranking from Pairwise and Listwise Queries: Lower Bounds and Upper Bounds
For the PAC top-$k$ ranking problem, we derive a lower bound on the sample complexity (aka number of queries), and propose an algorithm that is sample-complexity-optimal up to an $O(\log(k+l)/\log{k})$ factor.
Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning
Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning.
Adaptive Stochastic Gradient Langevin Dynamics: Taming Convergence and Saddle Point Escape Time
In this paper, we propose a new adaptive stochastic gradient Langevin dynamics (ASGLD) algorithmic framework and its two specialized versions, namely adaptive stochastic gradient (ASG) and adaptive gradient Langevin dynamics(AGLD), for non-convex optimization problems.
Generative Steganography by Sampling
In this paper, a new data-driven information hiding scheme called generative steganography by sampling (GSS) is proposed.
Coverless Information Hiding Based on Generative adversarial networks
The main idea of the method is that the class label of generative adversarial networks is replaced with the secret information as a driver to generate hidden image directly, and then extract the secret information from the hidden image through the discriminator.
Cryptography and Security Multimedia
Generative Steganography with Kerckhoffs' Principle
The secret messages can be outputted by the generator if and only if the extraction key and the cover image are both inputted.
Multimedia
Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification
Additionally, we also find that even though bottleneck features perform well for text-independent speaker verification, they do not outperform MFCCs on the most challenging Imposter-Correct trials on RedDots.
Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network
Adaptive traffic signal control, which adjusts traffic signal timing according to real-time traffic, has been shown to be an effective method to reduce traffic congestion.
Networking and Internet Architecture
Lepton Jets from Radiating Dark Matter
In this paper, we discuss lepton jets as a promising signature of an extended dark sector.
High Energy Physics - Phenomenology
