Search Results for author:
Found 36 papers, 6 papers with code
Gradient Projection For Continual Parameter-Efficient Tuning
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and protecting old knowledge, leading to zero-shot generalization collapse, and cross-modal hallucination.
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
With this regard, we design a mixed compression model, which organically combines Low-Rank matrix approximation And structured Pruning (LoRAP).
Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage.
Integrating Homomorphic Encryption and Trusted Execution Technology for Autonomous and Confidential Model Refining in Cloud
By the outsourcing, other than utilizing the extensive and scalable resource offered by the cloud service provider, it will also be attractive to users if the cloud servers can manage the machine learning processes autonomously on behalf of the users.
Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
The increasing size of language models raises great research interests in parameter-efficient fine-tuning such as LoRA that freezes the pre-trained model, and injects small-scale trainable parameters for multiple downstream tasks (e. g., summarization, question answering and translation).
Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition
Besides, to further exploit the potential of positive pairs and increase the robustness of self-supervised representation learning, we propose a Positive Feature Transformation (PFT) strategy which adopts feature-level manipulation to increase the variance of positive pairs.
Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning
In this paper, we propose a novel domain adaptation method, which infers target pseudo-labels through cross-domain label propagation, such that the underlying manifold structure of two domain data can be explored.
Leveraging Summary Guidance on Medical Report Summarization
This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derived from MIMIC-III, respectively.
Constrained Maximum Cross-Domain Likelihood for Domain Generalization
Finally, a Constrained Maximum Cross-domain Likelihood (CMCL) optimization problem is deduced, by solving which the joint distributions are naturally aligned.
Mitigating Both Covariate and Conditional Shift for Domain Generalization
Domain generalization (DG) aims to learn a model on several source domains, hoping that the model can generalize well to unseen target domains.
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
And the other introduces a new metric based on mutual information between adjacent action proposals and evaluates the informativeness of video samples, named Temporal Context Inconsistency (TCI).
Attentive pooling for Group Activity Recognition
However, the existing methods simply employed max/average pooling in this framework, which ignored the distinct contributions of different individuals to the group activity recognition.
Variational Distillation for Multi-View Learning
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions.
Deep Multi-View Semi-Supervised Clustering with Sample Pairwise Constraints
Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration.
Improving Fraud Detection via Hierarchical Attention-based Graph Neural Network
In this paper, we propose a Hierarchical Attention-based Graph Neural Network (HA-GNN) for fraud detection, which incorporates weighted adjacency matrices across different relations against camouflage.
Differentiable N-gram Objective on Abstractive Summarization
ROUGE is a standard automatic evaluation metric based on n-grams for sequence-to-sequence tasks, while cross-entropy loss is an essential objective of neural network language model that optimizes at a unigram level.
Learnable Faster Kernel-PCA for Nonlinear Fault Detection: Deep Autoencoder-Based Realization
In this work, to deal with the two drawbacks, a learnable faster realization of the conventional KPCA is proposed.
Multi-scale 2D Representation Learning for weakly-supervised moment retrieval
Specifically, we first construct a two-dimensional map for each temporal scale to capture the temporal dependencies between candidates.
Towards Book Cover Design via Layout Graphs
Book covers are intentionally designed and provide an introduction to a book.
Optimizing Fund Allocation for Game-based Verifiable Computation Outsourcing
The cloud server makes a deposit for each task it takes, each client allocates a budget (including the wage for the server and the cost for possibly hiring TTP) for each task submitted, and every party has its limited fund for either deposits or task budgets.
Computer Science and Game Theory
Solving the Travelling Thief Problem based on Item Selection Weight and Reverse Order Allocation
The Travelling Thief Problem (TTP) is a challenging combinatorial optimization problem that attracts many scholars.
Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
As a result, it exploits more discriminative features for DR grading.
Deep Reinforcement Learning for Dynamic Spectrum Sensing and Aggregation in Multi-Channel Wireless Networks
Then, the vacant channels in the selected segment will be aggregated for satisfying the user requirement.
A Non-Stationary VVLC MIMO Channel Model for Street Corner Scenarios
The study of the underlying VLC channel is the basis for designing the VLC communication system.
Robust Locality-Aware Regression for Labeled Data Classification
With the dramatic increase of dimensions in the data representation, extracting latent low-dimensional features becomes of the utmost importance for efficient classification.
Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning
Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain.
Instance Scale Normalization for image understanding
Scale variation remains a challenging problem for object detection.
Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control
The key challenges for the sequential decision process is to online generate sequential decision-making policy directly, and transferring knowledge across tasks domain.
Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces
Policy evaluation with linear function approximation is an important problem in reinforcement learning.
Effective Image Retrieval via Multilinear Multi-index Fusion
In this paper, we propose a new multi-index fusion scheme for image retrieval.
Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
In particular, the original tensor-based multi-view self-representation clustering problem is a special case of our approach and can be solved by our algorithm.
Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks
We propose an automatic diabetic retinopathy (DR) analysis algorithm based on two-stages deep convolutional neural networks (DCNN).
On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly.
Weighted Schatten $p$-Norm Minimization for Image Denoising and Background Subtraction
However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications.
A New Low-Rank Tensor Model for Video Completion
On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way.
Distortion-driven Turbulence Effect Removal using Variational Model
To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new variational model and distortion-driven spatial-temporal kernel regression.
