Search Results for author:
Found 82 papers, 30 papers with code
Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.
HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation
Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers.
Ranked #1 on
Hyperparameter Optimization
on Bayesmark
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
Tinker-HP : Accelerating Molecular Dynamics Simulations of Large Complex Systems with Advanced Point Dipole Polarizable Force Fields using GPUs and Multi-GPUs systems
Perspectives toward the strong-scaling performance of our multi-node massive parallelization strategy, unsupervised adaptive sampling and large scale applicability of the Tinker-HP code in biophysics are discussed.
Computational Physics Distributed, Parallel, and Cluster Computing Mathematical Software Chemical Physics
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices
However, prior supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e. g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance.
EvilModel: Hiding Malware Inside of Neural Network Models
In this paper, we present a new method to covertly and evasively deliver malware through a neural network model.
EvilModel 2.0: Bringing Neural Network Models into Malware Attacks
Therefore, we propose an improved stegomalware EvilModel.
Mixed Pseudo Labels for Semi-Supervised Object Detection
While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach.
Ranked #1 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
For example, MPQ search on ResNet18 with our indicators takes only 0. 06 s, which improves time efficiency exponentially compared to iterative search methods.
Decentralized Federated Learning: A Segmented Gossip Approach
The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data.
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct.
Ranked #3 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 10-way (20-shot)
(using extra training data)
Lifelong Incremental Reinforcement Learning with Online Bayesian Inference
In this paper, we propose LifeLong Incremental Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments.
Online Influence Maximization in Non-Stationary Social Networks
Nevertheless, the existing studies mostly investigate the problem on a one-off basis, assuming fixed known influence probabilities among users, or the knowledge of the exact social network topology.
One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition.
ProcData: An R Package for Process Data Analysis
In addition, several response process generators and a real dataset of response processes of the climate control item in the 2012 Programme for International Student Assessment are included in the package.
Deepfake Forensics via An Adversarial Game
In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities.
Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach
With the advancement of deep learning techniques, major cloud providers and niche machine learning service providers start to offer their cloud-based machine learning tools, also known as machine learning as a service (MLaaS), to the public.
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing
To tackle this challenge, we propose a framework termed collaborative data-free knowledge distillation via multi-level feature sharing (CDFKD-MFS), which consists of a multi-header student module, an asymmetric adversarial data-free KD module, and an attention-based aggregation module.
AdaCompress: Adaptive Compression for Online Computer Vision Services
Then we train the agent in a reinforcement learning way to adapt it for different deep learning cloud services that act as the {\em interactive training environment} and feeding a reward with comprehensive consideration of accuracy and data size.
Multimedia Image and Video Processing
BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization
Evolutionary reinforcement learning (ERL) algorithms recently raise attention in tackling complex reinforcement learning (RL) problems due to high parallelism, while they are prone to insufficient exploration or model collapse without carefully tuning hyperparameters (aka meta-parameters).
Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments
Instance novelty measures an instance's difference from the previous optimum in the original environment, while instance quality corresponds to how well an instance performs in the new environment.
CryptMPI: A Fast Encrypted MPI Library
The cloud infrastructure must provide security for High-Performance Computing (HPC) applications of sensitive data to execute in such an environment.
Distributed, Parallel, and Cluster Computing Cryptography and Security
Performance Evaluation and Modeling of Cryptographic Libraries for MPI Communications
In order for High-Performance Computing (HPC) applications with data security requirements to execute in the public cloud, the cloud infrastructure must ensure the privacy and integrity of data.
Distributed, Parallel, and Cluster Computing Cryptography and Security
Multitask Bandit Learning Through Heterogeneous Feedback Aggregation
In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol.
Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.
A Novel Truncated Norm Regularization Method for Multi-channel Color Image Denoising
However, those methods mostly ignore either the cross-channel difference or the spatial variation of noise, which limits their capacity in real world color image denoising.
Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay
Finally, by interleaving pseudo samples with real ones of the new task, we continually update the state and behavior generators to model progressively diverse behaviors, and regularize the multi-head critic via behavior cloning to mitigate forgetting.
Stable Memory Allocation in the Hippocampus: Fundamental Limits and Neural Realization
In Valiant's neuroidal model, the hippocampus was described as a randomly connected graph, the computation on which maps input to a set of activated neuroids with stable size.
Still Hammerable and Exploitable: on the Effectiveness of Software-only Physical Kernel Isolation
The exploit is motivated by our key observation that the modern OSes have double-owned kernel buffers (e. g., video buffers) owned concurrently by the kernel and user domains.
Cryptography and Security
Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach
Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way.
Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
An Exploratory Analysis of the Latent Structure of Process Data via Action Sequence Autoencoder
In this article, we propose a method to extract latent variables from process data.
A Pvalue-guided Anomaly Detection Approach Combining Multiple Heterogeneous Log Parser Algorithms on IIoT Systems
In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.
Cryptography and Security
Subtask Analysis of Process Data Through a Predictive Model
Response process data collected from human-computer interactive items contain rich information about respondents' behavioral patterns and cognitive processes.
DeepC2: AI-powered Covert Command and Control on OSNs
The defender can limit the attacker once it is exposed.
MQES: Max-Q Entropy Search for Efficient Exploration in Continuous Reinforcement Learning
Recently, the principle of optimism in the face of (aleatoric and epistemic) uncertainty has been utilized to design efficient exploration strategies for Reinforcement Learning (RL).
Maximum correntropy criterion for robust TOA-based localization in NLOS environments
We investigate the problem of time-of-arrival (TOA) based localization under possible non-line-of-sight (NLOS) propagation conditions.
Neurodynamic TDOA localization with NLOS mitigation via maximum correntropy criterion
In this paper, we exploit the maximum correntropy criterion (MCC) to robustify the traditional time-difference-of-arrival (TDOA) location estimator in the presence of non-line-of-sight (NLOS) propagation conditions.
Polymorphous density-functional description of paramagnetic phases of quantum magnets
The kernel of the study of magnetic quantum materials focuses on the magnetic phase transitions, among which the most common phenomenon is the transition between low-temperature magnetic-ordered phase to high-temperature paramagnetic phase.
Materials Science
A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric
All the results demonstrate that the re-organized dataset splits and new metric can better monitor the progress in TSGV.
Spin-orbit driven ferromagnetism at half moiré filling in magic-angle twisted bilayer graphene
Strong electron correlation and spin-orbit coupling (SOC) provide two non-trivial threads to condensed matter physics.
Mesoscale and Nanoscale Physics Materials Science Strongly Correlated Electrons
Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction
In this paper, we focus on efficient navigation with the RL technique and combine the advantages of these two kinds of methods into a rule-based RL (RuRL) algorithm for reducing the sample complexity and cost of time.
Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
Task-agnostic knowledge distillation, a teacher-student framework, has been proved effective for BERT compression.
Online Continual Adaptation with Active Self-Training
Our theoretical results show that OSAMD can fast adapt to changing environments with active queries.
Provably Efficient Multi-Task Reinforcement Learning with Model Transfer
We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs).
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ).
A Survey on Temporal Sentence Grounding in Videos
In this survey, we give a comprehensive overview for TSGV, which i) summarizes the taxonomy of existing methods, ii) provides a detailed description of the evaluation protocols(i. e., datasets and metrics) to be used in TSGV, and iii) in-depth discusses potential problems of current benchmarking designs and research directions for further investigations.
OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning
Many exploration strategies are built upon the optimism in the face of the uncertainty (OFU) principle for reinforcement learning.
bert2BERT: Towards Reusable Pretrained Language Models
However, large language model pre-training costs intensive computational resources and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful.
Fully Self-Supervised Learning for Semantic Segmentation
To solve this problem, we proposed a bootstrapped training scheme for semantic segmentation, which fully leveraged the global semantic knowledge for self-supervision with our proposed PGG strategy and CAE module.
Ranked #13 on
Unsupervised Semantic Segmentation
on COCO-Stuff-27
Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
In this paper, we propose a new method based on local communication learning to tackle the multi-agent RL (MARL) challenge within a large number of agents coexisting.
A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach
New benchmarking results indicate that our proposed evaluation protocols can better monitor the research progress.
Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Second, BPR algorithms usually require numerous samples to estimate the probability distribution of the tabular-based observation model, which may be expensive and even infeasible to learn and maintain, especially when using the state transition sample as the signal.
Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach
We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level.
SeqNet: An Efficient Neural Network for Automatic Malware Detection
We demonstrate the effectiveness of our methods and the low training cost requirement of SeqNet in our experiments.
A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
We use a Dirichlet process mixture to model the non-stationary task distribution, which captures task relatedness by estimating the likelihood of task-to-cluster assignments and clusters the task models in a latent space.
Thompson Sampling for Robust Transfer in Multi-Task Bandits
We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments.
MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees
While achieving tremendous success in various fields, existing multi-agent reinforcement learning (MARL) with a black-box neural network architecture makes decisions in an opaque manner that hinders humans from understanding the learned knowledge and how input observations influence decisions.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Multi-channel Nuclear Norm Minus Frobenius Norm Minimization for Color Image Denoising
Specifically, based on the block-matching, the color image is decomposed into overlapping RGB patches.
SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization
This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset.
TextIR: A Simple Framework for Text-based Editable Image Restoration
We use the text-image feature compatibility of the CLIP to alleviate the difficulty of fusing text and image features.
Efficient and Secure Federated Learning for Financial Applications
Experiments show that under different Non-IID experiment settings, our method can reduce the upload communication cost to about 2. 9% to 18. 9% of the conventional federated learning algorithm when the sparse rate is 0. 01.
Advanced Multi-Microscopic Views Cell Semi-supervised Segmentation
In this paper, we introduce a novel semi-supervised cell segmentation method called Multi-Microscopic-view Cell semi-supervised Segmentation (MMCS), which can train cell segmentation models utilizing less labeled multi-posture cell images with different microscopy well.
Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers
In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space.
Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with a compact latent representation from partial observation for boosting value decomposition.
Knowledge Soft Integration for Multimodal Recommendation
To address this issue, we propose using knowledge soft integration to balance the utilization of multimodal features and the curse of knowledge problem it brings about.
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding
In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks.
Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
Existing reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution, which may fail to provide sufficient information about the ever-changing environment with high complexity.
Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsing
In this paper, we present Semantic-Human, a novel method that achieves both photorealistic details and viewpoint-consistent human parsing for the neural rendering of humans.
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.
Deep Learning Predicts Biomarker Status and Discovers Related Histomorphology Characteristics for Low-Grade Glioma
Biomarker detection is an indispensable part in the diagnosis and treatment of low-grade glioma (LGG).
DAGC: Data-Volume-Aware Adaptive Sparsification Gradient Compression for Distributed Machine Learning in Mobile Computing
Assigning varying compression ratios to workers with distinct data distributions and volumes is thus a promising solution.
Unified learning-based lossy and lossless JPEG recompression
Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images.
OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty.
Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers.
Large Language Model Adaptation for Networking
In this paper, we present NetLLM, the first LLM adaptation framework that efficiently adapts LLMs to solve networking problems.
MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models
To tackle this challenge, we propose a MamMIL framework for WSI classification by cooperating the selective structured state space model (i. e., Mamba) with MIL for the first time, enabling the modeling of instance dependencies while maintaining linear complexity.
Metric Learning from Limited Pairwise Preference Comparisons
We study whether the metric can still be recovered, even though it is known that learning individual ideal items is now no longer possible.
Investigating the Impact of Quantization on Adversarial Robustness
Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment.
BAMBOO: a predictive and transferable machine learning force field framework for liquid electrolyte development
Despite the widespread applications of machine learning force field (MLFF) on solids and small molecules, there is a notable gap in applying MLFF to complex liquid electrolytes.
TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
Diffusion models have emerged as preeminent contenders in the realm of generative models.
