Search Results for author:
Found 109 papers, 36 papers with code
Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations
We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.
Transparency Promotion with Model-Agnostic Linear Competitors
We propose a novel type of hybrid model for multi-class classification, which utilizes competing linear models to collaborate with an existing black-box model, promoting transparency in the decision-making process.
Large Batch Optimization for Object Detection: Training COCO in 12 Minutes
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.
Instance Migration Diffusion for Nuclear Instance Segmentation in Pathology
To tackle this challenge, we propose a novel data augmentation framework Instance Migration Diffusion Model (IM-Diffusion), IM-Diffusion designed to generate more varied pathological images by constructing diverse nuclear layouts and internuclear spatial relationships.
Make Optimization Once and for All with Fine-grained Guidance
Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks.
Convergence of Iterative Water-Filling in Multi-User Non-Cooperative Power Control: A Comprehensive Analysis for Sequential, Simultaneous, and Asynchronous Schemes
Although classical fixed-point theorems guarantee the existence of a Nash Equilibrium (NE) under mild concavity and compactness conditions, the convergence of practical iterative algorithms to that equilibrium remains a challenging endeavor.
The Value of AI Advice: Personalized and Value-Maximizing AI Advisors Are Necessary to Reliably Benefit Experts and Organizations
Despite advances in AI's performance and interpretability, AI advisors can undermine experts' decisions and increase the time and effort experts must invest to make decisions.
THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation.
Artificial Intelligence for Microbiology and Microbiome Research
Advancements in artificial intelligence (AI) have transformed many scientific fields, with microbiology and microbiome research now experiencing significant breakthroughs through machine learning and deep learning applications.
Improving Decision Sparsity
We present cluster-based SEV and its variant tree-based SEV, introduce a method that improves credibility of explanations, and propose algorithms that optimize decision sparsity in machine learning models.
BFA-YOLO: A balanced multiscale object detection network for building façade attachments detection
To address these issues, we develop the BFA-YOLO model and the BFA-3D dataset in this study.
From Model Explanation to Data Misinterpretation: Uncovering the Pitfalls of Post Hoc Explainers in Business Research
Machine learning models have been increasingly used in business research.
TextMastero: Mastering High-Quality Scene Text Editing in Diverse Languages and Styles
Scene text editing aims to modify texts on images while maintaining the style of newly generated text similar to the original.
Using Advanced LLMs to Enhance Smaller LLMs: An Interpretable Knowledge Distillation Approach
Unlike traditional knowledge distillation, where the "student" model learns directly from the "teacher" model's responses via fine-tuning, our interpretable "strategy" teaching approach involves the teacher providing strategies to improve the student's performance in various scenarios.
Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection
This module adjusts the feature distributions from both the camera and LiDAR, bringing them closer to the ground truth domain and minimizing differences.
SEED: A Simple and Effective 3D DETR in Point Clouds
We argue that the main challenges are twofold: 1) How to obtain the appropriate object queries is challenging due to the high sparsity and uneven distribution of point clouds; 2) How to implement an effective query interaction by exploiting the rich geometric structure of point clouds is not fully explored.
OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection.
Dance of the ADS: Orchestrating Failures through Historically-Informed Scenario Fuzzing
As autonomous driving systems (ADS) advance towards higher levels of autonomy, orchestrating their safety verification becomes increasingly intricate.
Enhancing Terrestrial Net Primary Productivity Estimation with EXP-CASA: A Novel Light Use Efficiency Model Approach
The EXP-CASA model effectively improves the CASA model by using novel functions for estimating the fraction of absorbed photosynthetically active radiation (FPAR) and environmental stress, by utilizing long-term observational data from FLUXNET and MODIS surface reflectance data.
LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing
Addressing this gap, we propose a novel \textbf{L}ightweight \textbf{M}ultimodal data \textbf{F}usion \textbf{Net}work (LMFNet) to accomplish the tasks of fusion and semantic segmentation of multimodal remote sensing images.
Ranked #1 on
Semantic Segmentation
on Potsdam
Less is More for Improving Automatic Evaluation of Factual Consistency
Assessing the factual consistency of automatically generated texts in relation to source context is crucial for developing reliable natural language generation applications.
TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis
Motivated by these insights, we introduce a Text-oriented Cross-Attention Network (TCAN), emphasizing the predominant role of the text modality in MSA.
Penalized Generative Variable Selection
Deep networks are increasingly applied to a wide variety of data, including data with high-dimensional predictors.
Sparse and Faithful Explanations Without Sparse Models
In the loan denial example above, the SEV is 1 because only one factor is needed to explain why the loan was denied.
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
This implies that our FedCEO can effectively recover the disrupted semantic information by smoothing the global semantic space for different privacy settings and continuous training processes.
Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation
Language models demonstrate fundamental abilities in syntax, semantics, and reasoning, though their performance often depends significantly on the inputs they process.
S3Net: Innovating Stereo Matching and Semantic Segmentation with a Single-Branch Semantic Stereo Network in Satellite Epipolar Imagery
Stereo matching and semantic segmentation are significant tasks in binocular satellite 3D reconstruction.
Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings
The field of Remote Sensing (RS) widely employs Change Detection (CD) on very-high-resolution (VHR) images.
Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning
In this study, inspired by human beings' way of grasping an image, i. e., focusing on the main object first, we present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge.
Personalized Path Recourse for Reinforcement Learning Agents
This paper introduces Personalized Path Recourse, a novel method that generates recourse paths for a reinforcement learning agent.
Finite-Time Adaptive Fuzzy Tracking Control for Nonlinear State Constrained Pure-Feedback Systems
This paper investigates the finite-time adaptive fuzzy tracking control problem for a class of pure-feedback system with full-state constraints.
Adaptive Fuzzy Tracking Control for Nonlinear State Constrained Pure-Feedback Systems With Input Delay via Dynamic Surface Technique
Furthermore, a low-pass filter driven by a newly-defined control input, is employed to generate the actual control input, which facilitates the design of backstepping control.
An Empirical Study of Instruction-tuning Large Language Models in Chinese
This paper will release a powerful Chinese LLMs that is comparable to ChatGLM.
Adaptive Multi-NeRF: Exploit Efficient Parallelism in Adaptive Multiple Scale Neural Radiance Field Rendering
Recent advances in Neural Radiance Fields (NeRF) have demonstrated significant potential for representing 3D scene appearances as implicit neural networks, enabling the synthesis of high-fidelity novel views.
Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
Orbital-free density functional theory (OFDFT) is a quantum chemistry formulation that has a lower cost scaling than the prevailing Kohn-Sham DFT, which is increasingly desired for contemporary molecular research.
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident.
Wasserstein Generative Regression
Our approach simultaneously estimates a regression function and a conditional generator using a generative learning framework, where a conditional generator is a function that can generate samples from a conditional distribution.
t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation
Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models.
Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be effective.
GPT-3-driven pedagogical agents for training children's curious question-asking skills
In this context, we propose to leverage advances in the natural language processing field (NLP) and investigate the efficiency of using a large language model (LLM) for automating the production of the pedagogical content of a curious question-asking (QA) training.
An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge @ NeurIPS 2022
In the technical report, we provide our solution for OGB-LSC 2022 Graph Regression Task.
ProtoX: Explaining a Reinforcement Learning Agent via Prototyping
To teach ProtoX about visual similarity, we pre-train an encoder using contrastive learning via self-supervised learning to recognize states as similar if they occur close together in time and receive the same action from the black-box agent.
Learning to Advise Humans in High-Stakes Settings
The human's reconciliation costs and imperfect discretion behavior introduce the need to develop AI systems which (1) provide recommendations selectively, (2) leverage the human partner's ADB to maximize the team's decision accuracy while regularizing for reconciliation costs, and (3) are inherently interpretable.
Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation
Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation.
Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning
Meta-Adapters perform competitively with state-of-the-art few-shot learning methods that require full fine-tuning, while only fine-tuning 0. 6% of the parameters.
Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design
Structure-based drug design is drawing growing attentions in computer-aided drug discovery.
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Finally, we fine-tune the model with limited data with true labels to fully adapt it to the target domain.
Research on Creative Thinking Mode Based on Category Theory
Human's rational thinking mode has a high degree of freedom and transcendence, and such problems cannot be expected to be studied by elaborating the realization of the nervous system.
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons.
NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering
However, most existing methods 1) do not directly address the clustering task, since the representation learning and clustering process are separated; 2) depend too much on data augmentation, which greatly limits the capability of contrastive learning; 3) ignore the contrastive message for clustering tasks, which adversely degenerate the clustering results.
Multi-View Substructure Learning for Drug-Drug Interaction Prediction
Drug-drug interaction (DDI) prediction provides a drug combination strategy for systemically effective treatment.
Better Language Model with Hypernym Class Prediction
Class-based language models (LMs) have been long devised to address context sparsity in $n$-gram LMs.
Functional universality in slow-growing microbial communities arises from thermodynamic constraints
To understand the community structure in these energy-limited environments, we developed a microbial community consumer-resource model incorporating energetic and thermodynamic constraints on an interconnected metabolic network.
Direct Molecular Conformation Generation
Molecular conformation generation aims to generate three-dimensional coordinates of all the atoms in a molecule and is an important task in bioinformatics and pharmacology.
C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection
The decision boundary between any two categories is the angular bisector of their weight vectors.
DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points
To make the local features aware of the global context and improve their matching accuracy, we introduce DenseGAP, a new solution for efficient Dense correspondence learning with a Graph-structured neural network conditioned on Anchor Points.
Backdoor Attack through Frequency Domain
We also evaluate FTROJAN against state-of-the-art defenses as well as several adaptive defenses that are designed on the frequency domain.
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks.
Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery.
Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis
This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually.
A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations
We propose a framework for such decisions, including a globally interpretable machine learning model, an interactive visualization of it, and several types of summaries and explanations for any given decision.
Entity Resolution in Open-domain Conversations
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest.
Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved.
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Faceted summarization provides briefings of a document from different perspectives.
Ranked #1 on
Unsupervised Extractive Summarization
on FacetSum
Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE prediction is attributed to the interaction of features via a black-box model, with the goal to boost the predictive performance while maintaining interpretability.
Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
Adaptive Class Suppression Loss for Long-Tail Object Detection
To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies.
Quantum Transport in Two-Dimensional WS$_2$ with High-Efficiency Carrier Injection Through Indium Alloy Contacts
Here, temperature-dependent transfer length measurements are performed on chemical vapour deposition grown single-layer and bilayer WS$_2$ devices with indium alloy contacts.
Materials Science Mesoscale and Nanoscale Physics
Stochastic social behavior coupled to COVID-19 dynamics leads to waves, plateaus and an endemic state
It is well recognized that population heterogeneity plays an important role in the spread of epidemics.
A SOM-based Gradient-Free Deep Learning Method with Convergence Analysis
As gradient descent method in deep learning causes a series of questions, this paper proposes a novel gradient-free deep learning structure.
Exploring the Regulatory Function of the N-terminal Domain of SARS-CoV-2 Spike Protein Through Molecular Dynamics Simulation
We performed molecular dynamics simulation on the S protein with a focus on the function of its N-terminal domains (NTDs).
Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness
We formulate a multi-objective optimization for building a surrogate model, where we simultaneously optimize for both predictive performance and bias.
An Empirical Study on Neural Keyphrase Generation
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them.
Same-Day Delivery with Fairness
The demand for same-day delivery (SDD) has increased rapidly in the last few years and has particularly boomed during the COVID-19 pandemic.
ProtoryNet - Interpretable Text Classification Via Prototype Trajectories
We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories.
Exploring and Predicting Transferability across NLP Tasks
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
Task-adaptive Asymmetric Deep Cross-modal Hashing
Unlike previous cross-modal hashing approaches, our learning framework jointly optimizes semantic preserving that transforms deep features of multimedia data into binary hash codes, and the semantic regression which directly regresses query modality representation to explicit label.
Optimizing Traffic Lights with Multi-agent Deep Reinforcement Learning and V2X communication
We consider a system to optimize duration of traffic signals using multi-agent deep reinforcement learning and Vehicle-to-Everything (V2X) communication.
Modeling microbial cross-feeding at intermediate scale portrays community dynamics and species coexistence
We used the three models to study each community's limits of robustness to perturbations such as variations in resource supply, antibiotic treatments and invasion by other "cheaters" species.
Interpretable Companions for Black-Box Models
We present an interpretable companion model for any pre-trained black-box classifiers.
Early Predictions for Medical Crowdfunding: A Deep Learning Approach Using Diverse Inputs
The prediction model and the interpretable insights can be applied to assist fundraisers with better promoting their fundraising campaigns and can potentially help crowdfunding platforms to provide more timely feedback to all fundraisers.
Model-Agnostic Linear Competitors -- When Interpretable Models Compete and Collaborate with Black-Box Models
Driven by an increasing need for model interpretability, interpretable models have become strong competitors for black-box models in many real applications.
Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence
Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation.
Metalearned Neural Memory
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning.
Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model
The interpretable model substitutes the black-box model on a subset of data where the black-box is overkill or nearly overkill, gaining transparency at no or low cost of the predictive accuracy.
Next Hit Predictor - Self-exciting Risk Modeling for Predicting Next Locations of Serial Crimes
Our goal is to predict the location of the next crime in a crime series, based on the identified previous offenses in the series.
Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations
We present the Multi-value Rule Set (MRS) for interpretable classification with feature efficient presentations.
An Interpretable Model with Globally Consistent Explanations for Credit Risk
We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment.
Interpretable Patient Mortality Prediction with Multi-value Rule Sets
We propose a Bayesian framework for formulating a MRS model and propose an efficient inference method for learning a maximum \emph{a posteriori}, incorporating theoretically grounded bounds to iteratively reduce the search space and improve the search efficiency.
Neural Models for Key Phrase Extraction and Question Generation
We propose a two-stage neural model to tackle question generation from documents.
Gaining Free or Low-Cost Transparency with Interpretable Partial Substitute
This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case.
Causal Rule Sets for Identifying Subgroups with Enhanced Treatment Effect
The Bayesian model has tunable parameters that can characterize subgroups with various sizes, providing users with more flexible choices of models from the \emph{treatment efficient frontier}.
Multi-Value Rule Sets
MARS introduces a more generalized form of association rules that allows multiple values in a condition.
Annotating High-Level Structures of Short Stories and Personal Anecdotes
Stories are a vital form of communication in human culture; they are employed daily to persuade, to elicit sympathy, or to convey a message.
Cultural Vocal Bursts Intensity Prediction
Vocal Bursts Intensity Prediction
Predicting the Quality of Short Narratives from Social Media
An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality.
Neural Models for Key Phrase Detection and Question Generation
We propose a two-stage neural model to tackle question generation from documents.
A Joint Model for Question Answering and Question Generation
We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents.
Machine Comprehension by Text-to-Text Neural Question Generation
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers.
A Semantic QA-Based Approach for Text Summarization Evaluation
In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books).
NewsQA: A Machine Comprehension Dataset
We present NewsQA, a challenging machine comprehension dataset of over 100, 000 human-generated question-answer pairs.
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering.
Topic Modeling over Short Texts by Incorporating Word Embeddings
Inferring topics from the overwhelming amount of short texts becomes a critical but challenging task for many content analysis tasks, such as content charactering, user interest profiling, and emerging topic detecting.
Learning Optimized Or's of And's
Or's of And's (OA) models are comprised of a small number of disjunctions of conjunctions, also called disjunctive normal form.
Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems
In both cases, there are prior parameters that the user can set to encourage the model to have a desired size and shape, to conform with a domain-specific definition of interpretability.
