https://github.com/gensyn-ai/noloco
공식 코드NoLoCo: No-all-reduce Low Communication Training Method for Large Models
Papers with Code 아카이브
Blocking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 18
Entity resolution (also known as entity matching, record linkage, or duplicate detection) is the task of finding records that refer to the same real-world entity across different data sources (e.g., data files, books, websites, and databases). (Source: Wikipedia)
Blocking is a crucial step in any entity resolution pipeline because a pair-wise comparison of all records across two data sources is infeasible. Blocking applies a computationally cheap method to generate a smaller set of candidate record pairs reducing the workload of the matcher. During matching a more expensive pair-wise matcher generates a final set of matching record pairs.
Survey on blocking:
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/glouppe/paper-author-disambiguation
공식 코드Ethnicity sensitive author disambiguation using semi-supervised learning
https://github.com/guaishou74851/casnet
공식 코드https://github.com/hadijahanshahi/sdabt
공식 코드S-DABT: Schedule and Dependency-Aware Bug Triage in Open-Source Bug Tracking Systems
https://github.com/hao-ai-lab/vllm-ltr
공식 코드https://github.com/huangqiang/sah
공식 코드SAH: Shifting-aware Asymmetric Hashing for Reverse $k$-Maximum Inner Product Search
https://github.com/hzhang-math/Blocking_SHAP_TL
공식 코드https://github.com/icandle/MAN
공식 코드Multi-scale Attention Network for Single Image Super-Resolution
https://github.com/ironjr/semantic-draw
공식 코드SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models
https://github.com/ironjr/streammultidiffusion
공식 코드SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models
https://github.com/james-qiuhaoran/llm-serving-with-proxy-models
공식 코드Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction
https://github.com/jiamian-wang/s2-transformer-hsi
공식 코드S^2-Transformer for Mask-Aware Hyperspectral Image Reconstruction
https://github.com/jianzhangcs/COAST
공식 코드COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
https://github.com/jianzhangcs/ISTA-Netpp
공식 코드ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing
https://github.com/jlrussin/icl-iwl-interplay
공식 코드The dynamic interplay between in-context and in-weight learning in humans and neural networks
https://github.com/joey1993/bert-defender
공식 코드Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
https://github.com/jrash/chemmodlab
공식 코드chemmodlab: A Cheminformatics Modeling Laboratory for Fitting and Assessing Machine Learning Models
https://github.com/junghunl/diffim
공식 코드DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation
https://github.com/kargaranamir/Wide-AdGraph
공식 코드Wide-AdGraph: Detecting Ad Trackers with a Wide Dependency Chain Graph
https://github.com/lakeraai/dsec-gandalf
공식 코드https://github.com/limorigu/pragmaticfairness
공식 코드Pragmatic Fairness: Developing Policies with Outcome Disparity Control
https://github.com/liuzrcc/PIRE
공식 코드https://github.com/ltkong218/mdflow
공식 코드MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation
https://github.com/martanit/LEAD
공식 코드Effective Model of Loop Extrusion Predicts Chromosomal Domains
https://github.com/metaagentx/opencaptchaworld
공식 코드https://github.com/mhmoslemi2338/pre-EM-bias
공식 코드https://github.com/micdoh/XLRON
공식 코드Reinforcement Learning for Dynamic Resource Allocation in Optical Networks: Hype or Hope?
https://github.com/microsoft/StyleSwin
공식 코드StyleSwin: Transformer-based GAN for High-resolution Image Generation
https://github.com/microsoft/dcvc
공식 코드https://github.com/mitao-cat/feature-level_bias
공식 코드Understanding and Counteracting Feature-Level Bias in Click-Through Rate Prediction
https://github.com/mullervasconcelos/ieee-tac2023
공식 코드Robust one-shot estimation over shared networks in the presence of denial-of-service attacks
https://github.com/newiz430/bandana
공식 코드https://github.com/ngmarchant/dblink
공식 코드https://github.com/noise-lab/automated-dns-censorship
공식 코드Augmenting Rule-based DNS Censorship Detection at Scale with Machine Learning
https://github.com/openai/multiagent-competition
공식 코드https://github.com/openmicg/mcg
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.