Search Results for author:
Found 55 papers, 18 papers with code
Knowledge-Guided Paraphrase Identification
We propose to mine outline knowledge of concepts related to given sentences from Wikipedia via BM25 model.
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning
In this work, we show that Relation Graph augmented Learning (RGL) can improve the performance of few-shot natural language understanding tasks.
Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology
In this work, we propose a novel framework that quantifies uncertainty in LLM explanations through a reasoning topology perspective.
ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning
Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans.
GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning
However, the effectiveness of ICL heavily relies on the selection of ICEs, and conventional text-based embedding methods are often inadequate for tasks that require multi-step reasoning, such as mathematical and logical problem solving.
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training.
Warming Up Cold-Start CTR Prediction by Learning Item-Specific Feature Interactions
While existing methods focus on enhancing item ID embeddings for new items within general CTR models, they tend to adopt a global feature interaction approach, often overshadowing new items with sparse data by those with abundant interactions.
Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks
The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models.
Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models
To address these limitations, we propose a novel EHR data generation model called EHRPD.
CoRelation: Boosting Automatic ICD Coding Through Contextualized Code Relation Learning
Automatic International Classification of Diseases (ICD) coding plays a crucial role in the extraction of relevant information from clinical notes for proper recording and billing.
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks.
Ranked #1 on
Visual Question Answering (VQA)
on A-OKVQA
(using extra training data)
Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning
Thus, the lack of DDIs is implicitly compensated by the enriched drug representations and propagated drug similarities.
Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling
Intrusive PEFT techniques directly change a model's internal architecture.
Automated Evaluation of Personalized Text Generation using Large Language Models
Personalized text generation presents a specialized mechanism for delivering content that is specific to a user's personal context.
Hierarchical Pretraining on Multimodal Electronic Health Records
Pretraining has proven to be a powerful technique in natural language processing (NLP), exhibiting remarkable success in various NLP downstream tasks.
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size.
MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation
Health risk prediction is one of the fundamental tasks under predictive modeling in the medical domain, which aims to forecast the potential health risks that patients may face in the future using their historical Electronic Health Records (EHR).
PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
We then adopt a hierarchical adaptation mechanism to adapt the encoder at task-level and the predictor at query-level by the unified GNN adapter.
AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
Unlike typical adaptive computation challenges that deal with single-step generation problems, diffusion processes with a multi-step generation need to dynamically adjust their computational resource allocation based on the ongoing assessment of each step's importance to the final image output, presenting a unique set of challenges.
Teach LLMs to Personalize -- An Approach inspired by Writing Education
Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation.
Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering
Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner.
ColdNAS: Search to Modulate for User Cold-Start Recommendation
Instead of using a fixed modulation function and deciding modulation position by expertise, we propose a modulation framework called ColdNAS for user cold-start problem, where we look for proper modulation structure, including function and position, via neural architecture search.
Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT
This is a new yet practical scenario in federated learning, i. e., labels-at-server semi-supervised federated learning (SemiFL).
SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification
This new framework utilizes data that have similar labels when estimating fairness on a particular label group for better stability, and can unify DP and EOp.
Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement
In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE.
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
To handle this challenge, we propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously in term of input layer-wise similarities with multiple times of early exiting, namely \textbf{MuE}.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Natural Language Understanding
parameter-efficient fine-tuning
+1
Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization
While the optimization problem is nonconvex and nonsmooth, we show that its critical points still have good statistical performance on the tensor completion problem.
Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification
Short text classification is a fundamental task in natural language processing.
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings.
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.
FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning
In particular, we propose to use three networks and a dynamic quality control mechanism to generate high-quality pseudo labels for unlabeled data, which are added to the training set.
Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings.
FedCon: A Contrastive Framework for Federated Semi-Supervised Learning
Most existing FedSSL methods focus on the classical scenario, i. e, the labeled and unlabeled data are stored at the client side.
Property-Aware Relation Networks for Few-Shot Molecular Property Prediction
the target property, such that the limited labels can be effectively propagated among similar molecules.
Multimodal Emergent Fake News Detection via Meta Neural Process Networks
The experimental results show our proposed MetaFEND model can detect fake news on never-seen events effectively and outperform the state-of-the-art methods.
Adaptive Self-training for Neural Sequence Labeling with Few Labels
Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing.
Empirical Studies on the Convergence of Feature Spaces in Deep Learning
While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.
FedSiam: Towards Adaptive Federated Semi-Supervised Learning
In this paper, we focus on designing a general framework FedSiam to tackle different scenarios of federated semi-supervised learning, including four settings in the labels-at-client scenario and two setting in the labels-at-server scenario.
Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation
To fairly evaluate the performance, we also propose three specific evaluation metrics.
Adaptive Self-training for Few-shot Neural Sequence Labeling
While self-training serves as an effective mechanism to learn from large amounts of unlabeled data -- meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
Efficient Knowledge Graph Validation via Cross-Graph Representation Learning
To tackle this challenging task, we propose a cross-graph representation learning framework, i. e., CrossVal, which can leverage an external KG to validate the facts in the target KG efficiently.
A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Completion
Extensive low-rank matrix completion experiments on a number of synthetic and real-world data sets show that the proposed method obtains state-of-the-art recovery performance while being the fastest in comparison to existing low-rank matrix learning methods.
AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
Can one build a knowledge graph (KG) for all products in the world?
Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
(1) We formalize the problem of validating the textual attribute values of products from a variety of categories as a natural language inference task in the few-shot learning setting, and propose a meta-learning latent variable model to jointly process the signals obtained from product profiles and textual attribute values.
Decomposed Adversarial Learned Inference
Effective inference for a generative adversarial model remains an important and challenging problem.
Weak Supervision for Fake News Detection via Reinforcement Learning
In order to tackle this challenge, we propose a reinforced weakly-supervised fake news detection framework, i. e., WeFEND, which can leverage users' reports as weak supervision to enlarge the amount of training data for fake news detection.
Generalizing from a Few Examples: A Survey on Few-Shot Learning
Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small.
General Convolutional Sparse Coding with Unknown Noise
However, existing CSC methods can only model noises from Gaussian distribution, which is restrictive and unrealistic.
AIM: Adversarial Inference by Matching Priors and Conditionals
We propose a novel approach, Adversarial Inference by Matching priors and conditionals (AIM), which explicitly matches prior and conditional distributions in both data and code spaces, and puts a direct constraint on the dependency structure of the generative model.
EANN: Event Adversarial Neural Networks for Multi-Modal Fake News Detection
One of the unique challenges for fake news detection on social media is how to identify fake news on newly emerged events.
Online Convolutional Sparse Coding with Sample-Dependent Dictionary
Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing.
Scalable Online Convolutional Sparse Coding
Convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data.
