Search Results for author:
Found 39 papers, 21 papers with code
Distance Metric Learning with Joint Representation Diversification
Distance metric learning (DML) is to learn a representation space equipped with a metric, such that examples from the same class are closer than examples from different classes with respect to the metric.
Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning
Data mining and knowledge discovery are essential aspects of extracting valuable insights from vast datasets.
RAGraph: A General Retrieval-Augmented Graph Learning Framework
Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances.
Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models
Furthermore, we demonstrate that popular MLLMs pay special attention to certain multimodal context positions, particularly the beginning and end.
Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning
Retrieval-Augmented Generation (RAG) offers an effective solution to the issues faced by Large Language Models (LLMs) in hallucination generation and knowledge obsolescence by incorporating externally retrieved knowledge.
3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation
To address this, we propose a two-stage model-centric data selection framework, Decomposed Difficulty Data Selection (3DS), which aligns data with the model's knowledge distribution for optimized adaptation.
TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain reasoning capabilities of large language models (LLMs).
IntelliCare: Improving Healthcare Analysis with Variance-Controlled Patient-Level Knowledge from Large Language Models
While pioneering deep learning methods have made great strides in analyzing electronic health record (EHR) data, they often struggle to fully capture the semantics of diverse medical codes from limited data.
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge.
TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems
In the pursuit of enhancing domain-specific Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries.
KlF: Knowledge Localization and Fusion for Language Model Continual Learning
In this paper, we introduce a novel CL framework for language models, named Knowledge Localization and Fusion (KlF), which boosts knowledge transfer without depending on memory replay.
KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models
Simultaneously, we proposed a rewriting strategy and data ratio optimization strategy to address preference imbalances.
SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface.
SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
To tackle this problem, we propose SMART, a Self-Supervised Missing-Aware RepresenTation Learning approach for patient health status prediction, which encodes missing information via elaborated attentions and learns to impute missing values through a novel self-supervised pre-training approach that reconstructs missing data representations in the latent space.
LoRA Dropout as a Sparsity Regularizer for Overfitting Control
We then demonstrate the theoretical mechanism of our LoRA Dropout mechanism from the perspective of sparsity regularization by providing a generalization error bound under this framework.
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks.
Exploring the Potential of Large Language Models in Graph Generation
In this paper, we propose LLM4GraphGen to explore the ability of LLMs for graph generation with systematical task designs and extensive experiments.
Learnable Prompt as Pseudo-Imputation: Reassessing the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction
PAI no longer introduces any imputed data but constructs a learnable prompt to model the implicit preferences of the downstream model for missing values, resulting in a significant performance improvement for all EHR analysis models.
Infinite-Horizon Graph Filters: Leveraging Power Series to Enhance Sparse Information Aggregation
Graph Neural Networks (GNNs) have shown considerable effectiveness in a variety of graph learning tasks, particularly those based on the message-passing approach in recent years.
Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Series
To bridge this gap, we propose PRIME, a Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series.
HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs).
DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data
Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models.
Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a midpoint of source graphs in the Fused Gromov-Wasserstein (FGW) metric space.
Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level
Despite the broad interest in meta-learning, the generalization problem remains one of the significant challenges in this field.
Ground Truth Inference for Weakly Supervised Entity Matching
We also show that a deep learning EM end model (DeepMatcher) trained on labels generated from our weak supervision approach is comparable to an end model trained using tens of thousands of ground-truth labels, demonstrating that our approach can significantly reduce the labeling efforts required in EM.
Domain Generalization through the Lens of Angular Invariance
Based on the proposed term of invariance, we propose a novel deep DG method called Angular Invariance Domain Generalization Network (AIDGN).
M$^3$Care: Learning with Missing Modalities in Multimodal Healthcare Data
M3Care is an end-to-end model compensating the missing information of the patients with missing modalities to perform clinical analysis.
iFlipper: Label Flipping for Individual Fairness
We then propose an approximate linear programming algorithm and provide theoretical guarantees on how close its result is to the optimal solution in terms of the number of label flips.
Learning Hyper Label Model for Programmatic Weak Supervision
We train the model on synthetic data generated in the way that ensures the model approximates the analytical optimal solution, and build the model upon Graph Neural Network (GNN) to ensure the model prediction being invariant (or equivariant) to the permutation of LFs (or data points).
MedFACT: Modeling Medical Feature Correlations in Patient Health Representation Learning via Feature Clustering
Thus, to address the issues, we expect to group up strongly correlated features and learn feature correlations in a group-wise manner to reduce the learning complexity without losing generality.
Learning to be a Statistician: Learned Estimator for Number of Distinct Values
We derive conditions of the learning framework under which the learned model is workload agnostic, in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as, e. g., user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations for unseen tables and workloads.
Demonstration of Panda: A Weakly Supervised Entity Matching System
Panda's IDE includes many novel features purpose-built for EM, such as smart data sampling, a builtin library of EM utility functions, automatically generated LFs, visual debugging of LFs, and finally, an EM-specific labeling model.
OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning
Existing techniques for producing fair ML models either are limited to the type of fairness constraints they can handle (e. g., preprocessing) or require nontrivial modifications to downstream ML training algorithms (e. g., in-processing).
Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions
Machine learning (ML) applications have been thriving recently, largely attributed to the increasing availability of data.
ZeroER: Entity Resolution using Zero Labeled Examples
We investigate an important problem that vexes practitioners: is it possible to design an effective algorithm for ER that requires Zero labeled examples, yet can achieve performance comparable to supervised approaches?
CleanML: A Study for Evaluating the Impact of Data Cleaning on ML Classification Tasks
Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training.
GOGGLES: Automatic Image Labeling with Affinity Coding
We build the GOGGLES system that implements affinity coding for labeling image datasets by designing a novel set of reusable affinity functions for images, and propose a novel hierarchical generative model for class inference using a small development set.
Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions
However, the shallow models leveraging bilinear forms suffer from limitations on capturing complicated nonlinear interactions between drug pairs.
Motif-based Rule Discovery for Predicting Real-valued Time Series
Time series prediction is of great significance in many applications and has attracted extensive attention from the data mining community.
