Search Results for author:
Found 116 papers, 51 papers with code
A Mandarin-English Code-Switching Corpus
Generally the existing monolingual corpora are not suitable for large vocabulary continuous speech recognition (LVCSR) of code-switching speech.
Fast Stochastic Variance Reduced ADMM for Stochastic Composition Optimization
We consider the stochastic composition optimization problem proposed in \cite{wang2017stochastic}, which has applications ranging from estimation to statistical and machine learning.
Optimal Cooperative Inference
Cooperative transmission of data fosters rapid accumulation of knowledge by efficiently combining experiences across learners.
Aurora: Providing Trusted System Services for Enclaves On an Untrusted System
Intel SGX provisions shielded executions for security-sensitive computation, but lacks support for trusted system services (TSS), such as clock, network and filesystem.
Cryptography and Security
Double Quantization for Communication-Efficient Distributed Optimization
In this paper, to reduce the communication complexity, we propose \emph{double quantization}, a general scheme for quantizing both model parameters and gradients.
Characterizing Malicious Edges targeting on Graph Neural Networks
Extensive experiments are conducted to show that the proposed detection mechanism can achieve AUC above 90% against the two attack strategies on both Cora and Citeseer datasets.
DAG-GNN: DAG Structure Learning with Graph Neural Networks
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.
GumDrop at the DISRPT2019 Shared Task: A Model Stacking Approach to Discourse Unit Segmentation and Connective Detection
In this paper we present GumDrop, Georgetown University's entry at the DISRPT 2019 Shared Task on automatic discourse unit segmentation and connective detection.
Modeling Long-Range Context for Concurrent Dialogue Acts Recognition
Previous work on DA recognition either assumes one DA per utterance or fails to realize the sequential nature of dialogues.
Acutum: When Generalization Meets Adaptability
To the best of our knowledge, Acutum is the first adaptive gradient method without second moments.
SPAN: A Stochastic Projected Approximate Newton Method
SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products.
Urban Anomaly Analytics: Description, Detection, and Prediction
Urban anomalies may result in loss of life or property if not handled properly.
Data-driven learning of robust nonlocal physics from high-fidelity synthetic data
A key challenge to nonlocal models is the analytical complexity of deriving them from first principles, and frequently their use is justified a posteriori.
STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion.
BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision
We study the open-domain named entity recognition (NER) problem under distant supervision.
SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
Furthermore, most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is a more meaningful but harder task.
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup
Our method, SeqMix, simply augments the queried samples by generating extra labeled sequences in each iteration.
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships.
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach
To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision.
Ranked #1 on
Word Sense Disambiguation
on Words in Context
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks.
Data-driven learning of nonlocal models: from high-fidelity simulations to constitutive laws
We show that machine learning can improve the accuracy of simulations of stress waves in one-dimensional composite materials.
An asymptotically compatible treatment of traction loading in linearly elastic peridynamic fracture
In the absence of fracture, when a corresponding classical continuum mechanics model exists, our improvements provide asymptotically compatible convergence to corresponding local solutions, eliminating surface effects and issues with traction loading which have historically plagued peridynamic discretizations.
Numerical Analysis Computational Engineering, Finance, and Science Numerical Analysis Analysis of PDEs
On Controllability and Persistency of Excitation in Data-Driven Control: Extensions of Willems' Fundamental Lemma
Willems' fundamental lemma asserts that all trajectories of a linear time-invariant system can be obtained from a finite number of measured ones, assuming that controllability and a persistency of excitation condition hold.
deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search
With the rapid increase in the amount of public code repositories, developers maintain a great desire to retrieve precise code snippets by using natural language.
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (One-Shot)
on DuReader
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+19
DAGs with No Curl: An Efficient DAG Structure Learning Approach
To further improve efficiency, we propose a novel learning framework to model and learn the weighted adjacency matrices in the DAG space directly.
GGT: Graph-Guided Testing for Adversarial Sample Detection of Deep Neural Network
Deep Neural Networks (DNN) are known to be vulnerable to adversarial samples, the detection of which is crucial for the wide application of these DNN models.
A data-driven peridynamic continuum model for upscaling molecular dynamics
Nonlocal models, including peridynamics, often use integral operators that embed lengthscales in their definition.
Advances in Trajectory Optimization for Space Vehicle Control
Space mission design places a premium on cost and operational efficiency.
A physics-informed variational DeepONet for predicting the crack path in brittle materials
We propose a physics-informed variational formulation of DeepONet (V-DeepONet) for brittle fracture analysis.
Self-Training with Differentiable Teacher
In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels.
WRENCH: A Comprehensive Benchmark for Weak Supervision
To address these problems, we introduce a benchmark platform, WRENCH, for thorough and standardized evaluation of WS approaches.
A revised comparison between FF five-factor model and three-factor model,based on China's A-share market
In allusion to some contradicting results in existing research, this paper selects China's latest stock data from 2005 to 2020 for empirical analysis.
Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding
In this paper, we propose an approach to bridge pre-trained models and code-related tasks.
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models
We propose {\ours}, a new framework that leverages unlabeled data to improve the label efficiency of active PLM fine-tuning.
NIP: Neuron-level Inverse Perturbation Against Adversarial Attacks
From the perspective of image feature space, some of them cannot reach satisfying results due to the shift of features.
CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing
Existing DNN testing methods are mainly designed to find incorrect corner case behaviors in adversarial settings but fail to discover the backdoors crafted by strong trojan attacks.
NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification
To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data.
Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network
In this work, we propose a novel nonlocal neural operator, which we refer to as nonlocal kernel network (NKN), that is resolution independent, characterized by deep neural networks, and capable of handling a variety of tasks such as learning governing equations and classifying images.
Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery
Therefore, we conjecture that the multimodal and local-global combination strategies can be treated as the guideline of multi-task SSL for drug discovery.
A Survey on Programmatic Weak Supervision
Labeling training data has become one of the major roadblocks to using machine learning.
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training.
Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
In this work, we explore the idea of multiscale modeling with machine learning and employ DeepONet, a neural operator, as an efficient surrogate of the expensive solver.
Smart Tracking Tray System for A Smart and Sustainable Wet Lab Community
Positive feedback has been collected from pilot tests in several labs.
Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modeling
In this work, we propose to use data-driven modeling, which directly utilizes high-fidelity simulation and/or experimental measurements to predict a material's response without using conventional constitutive models.
PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning
Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult.
A Physics-Guided Neural Operator Learning Approach to Model Biological Tissues from Digital Image Correlation Measurements
To improve the generalizability of our framework, we propose a physics-guided neural operator learning model via imposing partial physics knowledge.
Modality-Balanced Embedding for Video Retrieval
This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching.
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.
Cross-Lingual Natural Language Inference
Distributed Computing
+2
Nonparametric learning of kernels in nonlocal operators
In this work, we provide a rigorous identifiability analysis and convergence study for the learning of kernels in nonlocal operators.
MetaNOR: A Meta-Learnt Nonlocal Operator Regression Approach for Metamaterial Modeling
We propose MetaNOR, a meta-learnt approach for transfer-learning operators based on the nonlocal operator regression.
PolyU-BPCoMa: A Dataset and Benchmark Towards Mobile Colorized Mapping Using a Backpack Multisensorial System
Color checker boards are pasted in each surveyed area as targets and ground truth data are collected by an advanced terrestrial laser scanner (TLS).
Physics-Informed Deep Neural Operator Networks
Standard neural networks can approximate general nonlinear operators, represented either explicitly by a combination of mathematical operators, e. g., in an advection-diffusion-reaction partial differential equation, or simply as a black box, e. g., a system-of-systems.
OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms
In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms.
Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach
Large Language Models have demonstrated remarkable few-shot performance, but the performance can be sensitive to the selection of few-shot instances.
Online Poisoning Attacks Against Data-Driven Predictive Control
Data-driven predictive control (DPC) is a feedback control method for systems with unknown dynamics.
ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
We study the problem of extracting N-ary relation tuples from scientific articles.
COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning
We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios.
Ranked #1 on
Zero-shot Text Search
on CQADupStack
Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives
In this paper, we investigate the instability in the standard dense retrieval training, which iterates between model training and hard negative selection using the being-trained model.
Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks
To better adapt GNNs for fMRI analysis, we propose TBDS, an end-to-end framework based on \underline{T}ask-aware \underline{B}rain connectivity \underline{D}AG (short for Directed Acyclic Graph) \underline{S}tructure generation for fMRI analysis.
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
Our dataset consists of ~1, 000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie.
Transferability Estimation Based On Principal Gradient Expectation
Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks.
EDoG: Adversarial Edge Detection For Graph Neural Networks
In this paper, we propose a general adversarial edge detection pipeline EDoG without requiring knowledge of the attack strategies based on graph generation.
INO: Invariant Neural Operators for Learning Complex Physical Systems with Momentum Conservation
Neural operators, which emerge as implicit solution operators of hidden governing equations, have recently become popular tools for learning responses of complex real-world physical systems.
Neighborhood-Regularized Self-Training for Learning with Few Labels
Our further analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36. 8% and saves 57. 3% of the time when compared with the best baseline.
Towards a unified nonlocal, peridynamics framework for the coarse-graining of molecular dynamics data with fractures
Then, based on the coarse-grained MD data, a two-phase optimization-based learning approach is proposed to infer the optimal peridynamics model with damage criterion.
MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics
Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification.
Stochastic Clustered Federated Learning
Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices.
Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning
Markov games model interactions among multiple players in a stochastic, dynamic environment.
Dynamic Routing in Stochastic Urban Air Mobility Networks: A Markov Decision Process Approach
Urban air mobility (UAM) is an emerging concept in short-range aviation transportation, where the aircraft will take off, land, and charge their batteries at a set of vertistops, and travel only through a set of flight corridors connecting these vertistops.
ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks.
Ranked #1 on
Zero-Shot Text Classification
on AG News
Higher Order Gauge Equivariant CNNs on Riemannian Manifolds and Applications
With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$.
DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling
Most existing methods for learning from noisy labels use static input features for denoising, but these methods are limited by the information they can provide on true label distributions and can result in biased or incorrect predictions.
R-Mixup: Riemannian Mixup for Biological Networks
Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities.
Local Boosting for Weakly-Supervised Learning
In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels.
A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises
This work aims to serve as a valuable resource for understanding the potential and opportunities of HKG in health research.
Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training
To address this challenge, we propose a weakly-supervised approach for scientific document classification using label names only.
MUBen: Benchmarking the Uncertainty of Molecular Representation Models
While some studies have included UQ to improve molecular pre-trained models, the process of selecting suitable backbone and UQ methods for reliable molecular uncertainty estimation remains underexplored.
ToolQA: A Dataset for LLM Question Answering with External Tools
To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs' ability to use external tools for question answering.
Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing
In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e. g., horizontally/vertically-partitioned data).
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks.
Personalized Federated Learning via Amortized Bayesian Meta-Learning
Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data.
Model Provenance via Model DNA
Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e. g., understanding where the model comes from, how it is trained, and how it is used).
Intelligence-Endogenous Management Platform for Computing and Network Convergence
Therefore, in this article, we present the concept of an intelligence-endogenous management platform for CNCs called \emph{CNC brain} based on artificial intelligence technologies.
Active Inverse Learning in Stackelberg Trajectory Games
We formulate an inverse learning problem in a Stackelberg game between a leader and a follower, where each player's action is the trajectory of a dynamical system.
Provable Training for Graph Contrastive Learning
To this end, we propose the PrOvable Training (POT) for GCL, which regularizes the training of GCL to encode node embeddings that follows the GCL principle better.
At Which Training Stage Does Code Data Help LLMs Reasoning?
Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning.
Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation
Meanwhile, while traditional techniques leveraging such semantic information require complex static or dynamic code analysis to obtain features such as data flow and control flow, SeCoT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (i. e., in-context learning), while being generalizable and applicable to challenging domains.
Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models
Clinical natural language processing requires methods that can address domain-specific challenges, such as complex medical terminology and clinical contexts.
Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning
To fully unleash the power of explanations, we propose EASE, an Explanation-Aware Soft Ensemble framework to empower in-context learning with LLMs.
On What Basis? Predicting Text Preference Via Structured Comparative Reasoning
Comparative reasoning plays a crucial role in text preference prediction; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning.
How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking
This paper presents LEMR (Label-Efficient Model Ranking) and introduces the MoraBench Benchmark.
Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws
In this work, we introduce conservation law-encoded neural operators (clawNOs), a suite of NOs that endow inference with automatic satisfaction of such conservation laws.
EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection
In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important.
Towards Fair Graph Federated Learning via Incentive Mechanisms
Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.
Causal Discovery under Identifiable Heteroscedastic Noise Model
We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and to learn a causal DAG from data with heteroscedastic variable noise under varying variance.
Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs).
SecFormer: Towards Fast and Accurate Privacy-Preserving Inference for Large Language Models
However, the application of SMPC in Privacy-Preserving Inference (PPI) for large language models, particularly those based on the Transformer architecture, often leads to considerable slowdowns or declines in performance.
Noise-Aware and Equitable Urban Air Traffic Management: An Optimization Approach
Urban air mobility (UAM), a transformative concept for the transport of passengers and cargo, faces several integration challenges in complex urban environments.
Training and Serving System of Foundation Models: A Comprehensive Survey
Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems.
Peridynamic Neural Operators: A Data-Driven Nonlocal Constitutive Model for Complex Material Responses
In this work, we introduce a novel integral neural operator architecture called the Peridynamic Neural Operator (PNO) that learns a nonlocal constitutive law from data.
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records
Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving.
HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification
The best-performing models aim to learn a static representation by combining document and hierarchical label information.
ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources.
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences.
Multi-modal Stance Detection: New Datasets and Model
Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets.
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs).
ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation
Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning.
VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation
In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated.
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models
Although Large Language Models (LLMs) exhibit remarkable adaptability across domains, these models often fall short in structured knowledge extraction tasks such as named entity recognition (NER).
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning
To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics.
Heterogeneous Peridynamic Neural Operators: Discover Biotissue Constitutive Law and Microstructure From Digital Image Correlation Measurements
Then, in the second phase we reinitialize the learnt bond force and the kernel function, and training them together with a fiber orientation field for each material point.
Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning
Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult.
AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models
We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training.
