Search Results for author:
Found 19 papers, 7 papers with code
Multi-Pair Text Style Transfer for Unbalanced Data via Task-Adaptive Meta-Learning
Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content.
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but moreover continual, post-deployment monitoring to quickly detect and address any unsafe behavior.
Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning
Through extensive experiments on six dynamic graph datasets, we demonstrate that the linear time encoder improves the performance of TGAT and DyGFormer in most cases.
Quadratic Gating Functions in Mixture of Experts: A Statistical Insight
Mixture of Experts (MoE) models are highly effective in scaling model capacity while preserving computational efficiency, with the gating network, or router, playing a central role by directing inputs to the appropriate experts.
On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions
With the growing prominence of the Mixture of Experts (MoE) architecture in developing large-scale foundation models, we investigate the Hierarchical Mixture of Experts (HMoE), a specialized variant of MoE that excels in handling complex inputs and improving performance on targeted tasks.
Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models
To evaluate our approach, we constructed a proprietary dataset comprising typical automotive industry documents, including technical reports and corporate regulations.
Achieving Fairness Across Local and Global Models in Federated Learning
Achieving fairness across diverse clients in Federated Learning (FL) remains a significant challenge due to the heterogeneity of the data and the inaccessibility of sensitive attributes from clients' private datasets.
Novel Node Category Detection Under Subpopulation Shift
We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel categories in attributed graphs under subpopulation shifts.
LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotemporal graph neural networks (STGNNs) is a basic assumption of current traffic flow prediction models.
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples.
Split Localized Conformal Prediction
The modified score inherits the spirit of split conformal methods, which is simple and efficient and can scale to high dimensional settings.
Efficient Forecasting of Large Scale Hierarchical Time Series via Multilevel Clustering
To attain this goal, each time series is first assigned the forecast for its cluster representative, which can be considered as a "shrinkage prior" for the set of time series it represents.
Architecture Agnostic Federated Learning for Neural Networks
With growing concerns regarding data privacy and rapid increase in data volume, Federated Learning(FL) has become an important learning paradigm.
Dynamic Combination of Heterogeneous Models for Hierarchical Time Series
We conduct a comprehensive evaluation of both point and quantile forecasts for hierarchical time series (HTS), including public data and user records from a large financial software company.
MECATS: Mixture-of-Experts for Probabilistic Forecasts of Aggregated Time Series
We introduce a mixture of heterogeneous experts framework called MECATS, which simultaneously forecasts the values of a set of time series that are related through an aggregation hierarchy.
Multi-Pair Text Style Transfer on Unbalanced Data
Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content.
Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
In such applications, it is important that the forecasts, in addition to being reasonably accurate, are also consistent w. r. t one another.
Certified Monotonic Neural Networks
In this work, we propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem. This provides a new general approach for learning monotonic neural networks with arbitrary model structures.
Model-Agnostic Explanations using Minimal Forcing Subsets
How can we find a subset of training samples that are most responsible for a specific prediction made by a complex black-box machine learning model?
