https://github.com/theophilec/PAC-Bayes-ILE-Structured-Prediction
공식 코드A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Structured Prediction is an area of machine learning focusing on representations of spaces with combinatorial structure, and algorithms for inference and parameter estimation over these structures. Core methods include both tractable exact approaches like dynamic programming and spanning tree algorithms as well as heuristic techniques such as linear programming relaxations and greedy search.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing
Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
Adversarial Structure Matching for Structured Prediction Tasks
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Learning Constraints for Structured Prediction Using Rectifier Networks
A Unified View of Evaluation Metrics for Structured Prediction
Estimating Gradients for Discrete Random Variables by Sampling without Replacement
Code4Struct: Code Generation for Few-Shot Event Structure Prediction
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Structured Output Learning with Conditional Generative Flows
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
Learning the Relation between Code Features and Code Transforms with Structured Prediction
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
Super-Resolution with Deep Convolutional Sufficient Statistics
Deep Metric Learning via Lifted Structured Feature Embedding
Neural Networks for Joint Sentence Classification in Medical Paper Abstracts
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.