Search Results for author:
Found 32 papers, 12 papers with code
PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications
Moreover, despite the wealth of benchmarks and studies in the natural language community, there remains a lack of a comprehensive benchmark for systematically evaluating protein language model quality.
DynaMo: Dynamic Community Detection by Incrementally Maximizing Modularity
Community detection is of great importance for online social network analysis.
Social and Information Networks Cryptography and Security
MedChatZH: a Better Medical Adviser Learns from Better Instructions
Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems.
AutoBalance: Optimized Loss Functions for Imbalanced Data
Our experimental findings are complemented with theoretical insights on loss function design and the benefits of train-validation split.
FedNest: Federated Bilevel, Minimax, and Compositional Optimization
Standard federated optimization methods successfully apply to stochastic problems with single-level structure.
Locally Differentially Private Distributed Deep Learning via Knowledge Distillation
As such, it motivates the researchers to conduct distributed deep learning, where the data user would like to build DL models using the data segregated across multiple different data owners.
Provable and Efficient Continual Representation Learning
In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting.
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction
Thus, in this paper, we propose a Hierarchical N-Gram framework for Zero-Shot Link Prediction (HNZSLP), which considers the dependencies among character n-grams of the relation surface name for ZSLP.
Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph
Therefore, this paper focuses on query graph generation from natural language questions.
Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation
Stochastic approximation with multiple coupled sequences (MSA) has found broad applications in machine learning as it encompasses a rich class of problems including bilevel optimization (BLO), multi-level compositional optimization (MCO), and reinforcement learning (specifically, actor-critic methods).
Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
In particular, we prove that: (i) In the first few iterations where the updates are still in the vicinity of the initialization gradient descent only fits to the correct labels essentially ignoring the noisy labels.
Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well.
Multi-Fusion Chinese WordNet (MCW) : Compound of Machine Learning and Manual Correction
By using them, we found that these word networks have low accuracy and coverage, and cannot completely portray the semantic network of PWN.
Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN
Short text is becoming more and more popular on the web, such as Chat Message, SMS and Product Reviews.
Exploring Weight Importance and Hessian Bias in Model Pruning
Model pruning is an essential procedure for building compact and computationally-efficient machine learning models.
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
In parallel, recent developments in self-supervised and semi-supervised learning (S4L) provide powerful techniques, based on data-augmentation, contrastive learning, and self-training, that enable superior utilization of unlabeled data which led to a significant reduction in required labeling in the standard machine learning benchmarks.
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
In this approach, it is common to use bilevel optimization where one optimizes the model weights over the training data (inner problem) and various hyperparameters such as the configuration of the architecture over the validation data (outer problem).
GENERALIZATION GUARANTEES FOR NEURAL NETS VIA HARNESSING THE LOW-RANKNESS OF JACOBIAN
We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well.
MC-GEN:Multi-level Clustering for Private Synthetic Data Generation
MC-GEN applies multi-level clustering and differential private generative model to improve the utility of synthetic data.
SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering
Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism.
TemPL: A Novel Deep Learning Model for Zero-Shot Prediction of Protein Stability and Activity Based on Temperature-Guided Language Modeling
We introduce TemPL, a novel deep learning approach for zero-shot prediction of protein stability and activity, harnessing temperature-guided language modeling.
Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking
Open domain entity state tracking aims to predict reasonable state changes of entities (i. e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions.
W-procer: Weighted Prototypical Contrastive Learning for Medical Few-Shot Named Entity Recognition
Contrastive learning has become a popular solution for few-shot Name Entity Recognization (NER).
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain
Recent advancements in language models (LMs) have led to the emergence of powerful models such as Small LMs (e. g., T5) and Large LMs (e. g., GPT-4).
FedYolo: Augmenting Federated Learning with Pretrained Transformers
These insights on scale and modularity motivate a new federated learning approach we call "You Only Load Once" (FedYolo): The clients load a full PTF model once and all future updates are accomplished through communication-efficient modules with limited catastrophic-forgetting, where each task is assigned to its own module.
A general Temperature-Guided Language model to engineer enhanced Stability and Activity in Proteins
Designing protein mutants with high stability and activity is a critical yet challenging task in protein engineering.
Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation
Experiments on English-German and English-Romanian translation show that: (i) Epi-Curriculum improves both model's robustness and adaptability in seen and unseen domains; (ii) Our episodic training framework enhances the encoder and decoder's robustness to domain shift.
Benchingmaking Large Langage Models in Biomedical Triple Extraction
Biomedical triple extraction systems aim to automatically extract biomedical entities and relations between entities.
A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare
It has gained significant attention in the field of Natural Language Processing (NLP) due to its ability to learn optimal strategies for tasks such as dialogue systems, machine translation, and question-answering.
Class-attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
Confirming this, under a gaussian mixture setting, we show that the optimal SVM classifier for balanced accuracy needs to be adaptive to the class attributes.
Enhancing the efficiency of protein language models with minimal wet-lab data through few-shot learning
Accurately modeling the protein fitness landscapes holds great importance for protein engineering.
A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models
To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation.
