325 citations · 1.7k across the 55 of their papers we have counts for
30 papers · 1 filter
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Defu Cao, Furong Jia, Sercan O Arik +4
The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary high…
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
Nicasia Beebe-Wang, Sayna Ebrahimi, Jinsung Yoon +2
Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entitie…
LANISTR: Multimodal Learning from Structured and Unstructured Data
Sayna Ebrahimi, Sercan O. Arik, Yihe Dong +1
Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured d…
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. A…
TSMixer: An All-MLP Architecture for Time Series Forecasting
Si-An Chen, Chun-Liang Li, Nate Yoder +2
Real-world time-series datasets are often multivariate with complex dynamics. To capture this complexity, high capacity architectures like recurrent- or attention-based sequential…
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li +2
Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-la…
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zifeng Wang, Zizhao Zhang, Jacob Devlin +6
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities. We presen…
Invariant Structure Learning for Better Generalization and Causal Explainability
Yunhao Ge, Sercan Ö. Arik, Jinsung Yoon +3
Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Lear…
Interpretable Mixture of Experts
Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon +3
The need for reliable model explanations is prominent for many machine learning applications, particularly for tabular and time-series data as their use cases often involve high-st…
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi +8
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store pa…
Data-Efficient and Interpretable Tabular Anomaly Detection
Chun-Hao Chang, Jinsung Yoon, Sercan Arik +2
Anomaly detection (AD) plays an important role in numerous applications. We focus on two understudied aspects of AD that are critical for integration into real-world applications.…
Decoupling Local and Global Representations of Time Series
Sana Tonekaboni, Chun-Liang Li, Sercan Arik +2
Real-world time series data are often generated from several sources of variation. Learning representations that capture the factors contributing to this variability enables a bett…
Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series
Sercan O. Arik, Nathanael C. Yoder, Tomas Pfister
Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional tr…
Towards Group Robustness in the presence of Partial Group Labels
Vishnu Suresh Lokhande, Kihyuk Sohn, Jinsung Yoon +3
Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correl…
Learning to Prompt for Continual Learning
Zifeng Wang, Zizhao Zhang, Chen-Yu Lee +7
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challeng…
Learning Fast Sample Re-weighting Without Reward Data
Zizhao Zhang, Tomas Pfister
Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels. Recent methods develop learning-based algorithms to learn sa…
Controlling Neural Networks with Rule Representations
Sungyong Seo, Sercan O. Arik, Jinsung Yoon +3
We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. Deep Neural Networks with Controllab…
Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection
Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li +3
Anomaly detection (AD), separating anomalies from normal data, has many applications across domains, from security to healthcare. While most previous works were shown to be effecti…
Interpretable Sequence Learning for COVID-19 Forecasting
Sercan O. Arik, Chun-Liang Li, Jinsung Yoon +12
We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19. Our model is explainable by design as it ex…
Differentiable Top-k Operator with Optimal Transport
Yujia Xie, Hanjun Dai, Minshuo Chen +5
The top-k operation, i.e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, m…
Distance-Based Learning from Errors for Confidence Calibration
Chen Xing, Sercan Arik, Zizhao Zhang +1
Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based l…
On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Chih-Kuan Yeh, Been Kim, Sercan O. Arik +3
Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for De…
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
Mingfei Gao, Zizhao Zhang, Guo Yu +3
Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performanc…
Distilling Effective Supervision from Severe Label Noise
Zizhao Zhang, Han Zhang, Sercan O. Arik +2
Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing me…