Search Results for author:
Found 72 papers, 22 papers with code
Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness
To address this problem, we propose a training framework with certified robustness to eliminate the causes that trigger the generation of profanity.
Knowledge-Guided Paraphrase Identification
We propose to mine outline knowledge of concepts related to given sentences from Wikipedia via BM25 model.
DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery
In-bed human mesh recovery can be crucial and enabling for several healthcare applications, including sleep pattern monitoring, rehabilitation support, and pressure ulcer prevention.
SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
Large Language Models (LLMs) have transformed natural language processing by learning from massive datasets, yet this rapid progress has also drawn legal scrutiny, as the ability to unintentionally generate copyrighted content has already prompted several prominent lawsuits.
Building Machine Learning Challenges for Anomaly Detection in Science
We present the different datasets along with a scheme to make machine learning challenges around the three datasets findable, accessible, interoperable, and reusable (FAIR).
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge editing.
Generating Millions Of Lean Theorems With Proofs By Exploring State Transition Graphs
We developed LeanNavigator, a novel method for generating a large-scale dataset of Lean theorems and proofs by finding new ways to prove existing Lean theorems.
Talk to Right Specialists: Routing and Planning in Multi-agent System for Question Answering
Experimental results demonstrate that RopMura effectively handles both single-hop and multi-hop queries, with the routing mechanism enabling precise answers for single-hop queries and the combined routing and planning mechanisms achieving accurate, multi-step resolutions for complex queries.
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
To fill in this gap, we provide a theoretical study on the inherent trade-off between CF and predictive performance in a model-agnostic manner.
Enhanced Self-Checkout System for Retail Based on Improved YOLOv10
With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation.
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.
Towards Federated RLHF with Aggregated Client Preference for LLMs
Our federated RLHF methods (i. e., FedBis and FedBiscuit) encode each client's preferences into binary selectors and aggregate them to capture common preferences.
FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model
Specifically, our method involves the server generating a compressed LLM and aligning its performance with the full model.
SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits.
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
By adding a sparsity constraint on the product of low-rank matrices and converting it to row and column-wise sparsity, we ensure efficient and precise model updates.
LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
Large language models (LLMs) have achieved impressive performance on various natural language generation tasks.
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications.
Transformer in Touch: A Survey
The Transformer model, initially achieving significant success in the field of natural language processing, has recently shown great potential in the application of tactile perception.
Array SAR 3D Sparse Imaging Based on Regularization by Denoising Under Few Observed Data
However, sparse imaging based on handcrafted regularization functions suffers from target information loss in few observed SAR data.
Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs
In this paper, we propose GraphEval to evaluate an LLM's performance using a substantially large test dataset.
Towards Comprehensive Multimodal Perception: Introducing the Touch-Language-Vision Dataset
Tactility provides crucial support and enhancement for the perception and interaction capabilities of both humans and robots.
Knowledge-Reuse Transfer Learning Methods in Molecular and Material Science
We focus on the application of transfer learning methods for the discovery of advanced molecules/materials, particularly, the construction of transfer learning frameworks for different systems, and how transfer learning can enhance the performance of models.
$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding
Existing model cascade methods seek to enhance inference efficiency by greedily selecting the lightest model capable of processing the current input from a variety of models, based on model confidence scores.
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering
Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios.
Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis
In the evolving field of corporate sustainability, analyzing unstructured Environmental, Social, and Governance (ESG) reports is a complex challenge due to their varied formats and intricate content.
Towards Poisoning Fair Representations
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female.
Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today
In this paper, we explore the potential of LLMs such as GPT-4 to outperform traditional AI tools in dementia diagnosis.
Behavioral Machine Learning? Computer Predictions of Corporate Earnings also Overreact
Machine learning algorithms are known to outperform human analysts in predicting corporate earnings, leading to their rapid adoption.
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.
Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters
In this paper, we propose a novel neural network framework, called Multi-Rater Prism (MrPrism) to learn the medical image segmentation from multiple labels.
Towards Reliable Item Sampling for Recommendation Evaluation
Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are "inconsistent" with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation.
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.
Temporal Spatial Decomposition and Fusion Network for Time Series Forecasting
One decomposition approach often cannot be used for numerous forecasting tasks since the standard time series decomposition lacks flexibility and robustness.
An Efficient Person Clustering Algorithm for Open Checkout-free Groceries
Then, to ensure that the method adapts to the dynamic and unseen person flow, we propose Graph Convolutional Network (GCN) with a simple Nearest Neighbor (NN) strategy to accurately cluster the instances of CSG.
Anchor Sampling for Federated Learning with Partial Client Participation
The lack of inactive clients' updates in partial client participation makes it more likely for the model aggregation to deviate from the aggregation based on full client participation.
SeATrans: Learning Segmentation-Assisted diagnosis model via Transformer
To model the segmentation-diagnosis interaction, SeA-block first embeds the diagnosis feature based on the segmentation information via the encoder, and then transfers the embedding back to the diagnosis feature space by a decoder.
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
Label a Herd in Minutes: Individual Holstein-Friesian Cattle Identification
In particular, for the task of automatic identification of individual Holstein-Friesians in real-world farm CCTV, we show that self-supervision, metric learning, cluster analysis, and active learning can complement each other to significantly reduce the annotation requirements usually needed to train cattle identification frameworks.
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive.
Deep Learning for Spatiotemporal Modeling of Urbanization
Here we explore the capacity of deep spatial learning for the predictive modeling of urbanization.
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.
Path-specific Causal Fair Prediction via Auxiliary Graph Structure Learning
To tackle these challenges, we propose a novel casual graph based fair prediction framework, which integrates graph structure learning into fair prediction to ensure that unfair pathways are excluded in the causal graph.
On the regularization landscape for the linear recommendation models
Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders several standard recommendation benchmarks.
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.
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.
On Sampling Top-K Recommendation Evaluation
Recently, Rendle has warned that the use of sampling-based top-$k$ metrics might not suffice.
Towards a Better Understanding of Linear Models for Recommendation
Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.
Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset
Motivated by the labelling burden involved in constructing visual cattle identification systems, we propose exploiting the temporal coat pattern appearance across videos as a self-supervision signal for animal identity learning.
Fairness-aware Outlier Ensemble
Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance.
On Estimating Recommendation Evaluation Metrics under Sampling
The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision (Krichene and Rendle 2020; Li et al. 2020).
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.
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.
Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
Holstein-Friesian cattle exhibit individually-characteristic black and white coat patterns visually akin to those arising from Turing's reaction-diffusion systems.
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.
Large-scale Real-time Personalized Similar Product Recommendations
Similar product recommendation is one of the most common scenes in e-commerce.
Practical Data Poisoning Attack against Next-Item Recommendation
In real-world recommendation systems, the cost of retraining recommendation models is high, and the interaction frequency between users and a recommendation system is restricted. Given these real-world restrictions, we propose to let the agent interact with a recommender simulator instead of the target recommendation system and leverage the transferability of the generated adversarial samples to poison the target system.
A Survey on Causal Inference
Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.
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.
Atmospheric turbulence removal using convolutional neural network
This paper describes a novel deep learning-based method for mitigating the effects of atmospheric distortion.
Data Poisoning Attack against Knowledge Graph Embedding
Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph. Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently.
Representation Learning for Treatment Effect Estimation from Observational Data
Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.
Finding Similar Medical Questions from Question Answering Websites
Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users.
Towards Differentially Private Truth Discovery for Crowd Sensing Systems
To better utilize sensory data, the problem of truth discovery, whose goal is to estimate user quality and infer reliable aggregated results through quality-aware data aggregation, has emerged as a hot topic.
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.
Long-Term Memory Networks for Question Answering
Question answering is an important and difficult task in the natural language processing domain, because many basic natural language processing tasks can be cast into a question answering task.
Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks
Existing work solves this problem by employing recurrent neural networks (RNNs) to model EHR data and utilizing simple attention mechanism to interpret the results.
Multi-source Hierarchical Prediction Consolidation
We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources.
Multilabel Consensus Classification
Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time.
Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models
First, we can boost the diversity of classification ensemble by incorporating multiple clustering outputs, each of which provides grouping constraints for the joint label predictions of a set of related objects.
