Awesome-Best-Papers

Collect awesome best papers from top AI conferences.
https://github.com/familyld/Awesome-Best-Papers

Last synced: 6 days ago
JSON representation

KDD
WWW
- Social Networks Under Stress
- HypTrails: A Bayesian Approach for Comparing Hypotheses About Human Trails on the Web - Leibniz Institute for the Social Sciences); Denis Helic (Graz University of Technology); Andreas Hotho, University of Würzburg; Markus Strohmaier (GESIS - Leibniz Institute for the Social Sciences） |
- Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach
- Ermes: Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification - Browser Covert Cryptocurrency Mining in the Wild](https://nikita.ca/papers/outguard-www19.pdf)** Amin Kharraz (University of Illinois at Urbana-Champaign); Zane Ma (University of Illinois at Urbana-Champaign); Paul Murley (University of Illinois at Urbana-Champaign); Charles Lever (Georgia Institute of Technology); Joshua Mason (University of Illinois at Urbana-Champaign); Andrew Miller (University of Illinois at Urbana-Champaign); Nikita Borisov (University of Illinois at Urbana-Champaign); Manos Antonakakis (Georgia Institute of Technology); Michael Bailey (University of Illinois at Urbana-Champaign) |
- Currently missing.
- Social Networks Under Stress
- Efficient Estimation for High Similarities using Odd Sketches
- No Country for Old Members: User Lifecycle and Linguistic Change in Online Communities - Niculescu-Mizil (Stanford University); Robert West (Stanford University); Dan Jurafsky (Stanford University); Jure Leskovec (Stanford University); Christopher Potts (Stanford University) |
- HypTrails: A Bayesian Approach for Comparing Hypotheses About Human Trails on the Web - Leibniz Institute for the Social Sciences); Denis Helic (Graz University of Technology); Andreas Hotho, University of Würzburg; Markus Strohmaier (GESIS - Leibniz Institute for the Social Sciences） |
ICCV
WSDM
CVPR
AAAI
- Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting - Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory](https://arxiv.org/abs/2012.03083)** Stefanos Leonardos (Singapore University of Technology and Design); Georgios Piliouras (Singapore University of Technology and Design) 3. **[Mitigating Political Bias in Language Models Through Reinforced Calibration](https://www.cs.dartmouth.edu/~rbliu/aaai_copy.pdf)** Ruibo Liu (Dartmouth College); Chenyan Jia (University of Texas at Austin); Jason Wei (Google AI); Guangxuan Xu (Dartmouth College); Lili Wang (Dartmouth College); Soroush Vosoughi (Dartmouth College) |
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- How to Combine Tree-Search Methods in Reinforcement Learning
- Memory-Augmented Monte Carlo Tree Search
- Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
- Bidirectional Search That Is Guaranteed to Meet in the Middle - Gurion University); Guni Sharon (Ben-Gurion University); Nathan R. Sturtevant (University of Denver) |
- From Non-Negative to General Operator Cost Partitioning
- Recovering from Selection Bias in Causal and Statistical Inference
- HC-Search: Learning Heuristics and Cost Functions for Structured Prediction - Instance Learning](https://www.aaai.org/ocs/index.php/AAAI/AAAI13/paper/view/6405/7131)** Gary Doran (Case Western Reserve University); Soumya Ray (Case Western Reserve University) |
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting - Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory](https://arxiv.org/abs/2012.03083)** Stefanos Leonardos (Singapore University of Technology and Design); Georgios Piliouras (Singapore University of Technology and Design) 3. **[Mitigating Political Bias in Language Models Through Reinforced Calibration](https://www.cs.dartmouth.edu/~rbliu/aaai_copy.pdf)** Ruibo Liu (Dartmouth College); Chenyan Jia (University of Texas at Austin); Jason Wei (Google AI); Guangxuan Xu (Dartmouth College); Lili Wang (Dartmouth College); Soroush Vosoughi (Dartmouth College) |
- How to Combine Tree-Search Methods in Reinforcement Learning
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- this website
SIGIR
- Controlling Fairness and Bias in Dynamic Learning-to-Rank
- this website
- Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness
- Controlling Fairness and Bias in Dynamic Learning-to-Rank
- Variance Reduction in Gradient Exploration for Online Learning to Rank - Snook (University of Virginia); Qingyun Wu (University of Virginia); Hongning Wang (University of Virginia) |
- Should I Follow the Crowd? A Probabilistic Analysis of the Effectiveness of Popularity in Recommender Systems
- BitFunnel: Revisiting Signatures for Search
- Understanding Information Need: An fMRI Study
- QuickScorer: A Fast Algorithm to Rank Documents with Additive Ensembles of Regression Trees
- Partitioned Elias-Fano Indexes
- Beliefs and Biases in Web Search
IJCAI
- Boosting for Comparison-Based Learning - Planck-Institute for Intelligent Systems); Ulrike von Luxburg (University of Tubingen) |
- Foundations of Declarative Data Analysis Using Limit Datalog Programs
- Hierarchical Finite State Controllers for Generalized Planning
- Bayesian Active Learning for Posterior Estimation
- Bayesian Optimization in High Dimensions via Random Embeddings
- Reasoning about Consensus when Opinions Diffuse through Majority Dynamics - Mediated Querying](https://www.ijcai.org/Proceedings/2018/0250.pdf)** Cristina Feier (University of Bremen); Carsten Lutz (University of Bremen); Frank Wolte (University of Liverpool) 4. **[What game are we playing? End-to-end learning in normal and extensive form games](https://arxiv.org/pdf/1805.02777.pdf)** Chun Kai Ling (Carnegie Mellon University); Fei Fang (Carnegie Mellon University); J. Zico Kolter (Carnegie Mellon University) 5. **[Commonsense Knowledge Aware Conversation Generation with Graph Attention](https://www.ijcai.org/Proceedings/2018/0643.pdf)** Hao Zhou (Tsinghua University); Tom Young (Beijing Institute of Technology); Minlie Huang (Tsinghua University); Haizhou Zhao, Sogou Inc.; Jingfang Xu, Sogou Inc.; Xiaoyan Zhu (Tsinghua University) 6. **[R-SVM+: Robust Learning with Privileged Information](https://www.ijcai.org/Proceedings/2018/0334.pdf)** Xue Li (Wuhan University); Bo Du (Wuhan University); Chang Xu (University of Sydney); Yipeng Zhang (Wuhan University); Lefei Zhang (Wuhan University); Dacheng Tao (University of Sydney) 7. **[A Degeneracy Framework for Graph Similarity](https://www.ijcai.org/Proceedings/2018/0360.pdf)** Giannis Nikolentzos, École Polytechnique; Polykarpos Meladianos (Athens University of Economics and Business); Stratis Limnios, École Polytechnique; Michalis Vazirgiannis (École Polytechnique) |
- Boosting for Comparison-Based Learning - Planck-Institute for Intelligent Systems); Ulrike von Luxburg (University of Tubingen) |
NeurIPS
- Distribution-Independent PAC Learning of Halfspaces with Massart Noise - Madison); Themis Gouleakis (Max Planck Institute for Informatics) |
- Non-delusional Q-learning and Value-iteration - Smooth Distributed Optimization in Networks](https://papers.nips.cc/paper/7539-optimal-algorithms-for-non-smooth-distributed-optimization-in-networks.pdf)** Kevin Scaman ; Francis Bach ; Sebastien Bubeck ; Laurent Massoulié ; Yin Tat Lee 3. **[Nearly Tight Sample Complexity Bounds for Learning Mixtures of Gaussians via Sample Compression Schemes](https://papers.nips.cc/paper/7601-nearly-tight-sample-complexity-bounds-for-learning-mixtures-of-gaussians-via-sample-compression-schemes.pdf)** Hassan Ashtiani ; Shai Ben-David ; Nick Harvey ; Christopher Liaw ; Abbas Mehrabian ; Yaniv Plan 4. **[Neural Ordinary Differential Equations](https://papers.nips.cc/paper/7892-neural-ordinary-differential-equations.pdf)** Tian Qi Chen ; Yulia Rubanova ; Jesse Bettencourt ; David Duvenaud |
- Value Iteration Networks
- Competitive Distribution Estimation: Why is Good-Turing Good - fast-convergence-of-regularized-learning-in-games.pdf)** Vasilis Syrgkanis (Microsoft Research); Alekh Agarwal (Microsoft Research); Haipeng Luo (Princeton University); Robert Schapire (Microsoft Research) |
- Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) - a-sampling.pdf)** Christopher Maddison (University of Toronto); Daniel Tarlow (Microsoft Research); Tom Minka (Microsoft Research) |
- A memory frontier for complex synapses - submodular-optimization-with-submodular-cover-and-submodular-knapsack-constraints.pdf)** Rishabh Iyer (University of Washington, Seattle); Jeff Bilmes (University of Washington, Seattle) 3. **[Scalable Influence Estimation in Continuous-Time Diffusion Networks](http://papers.nips.cc/paper/4857-scalable-influence-estimation-in-continuous-time-diffusion-networks.pdf)** Nan Du (Georgia Tech); Le Song (Georgia Tech); Manuel Gomez-Rodriguez (MPI for Intelligent Systems); Hongyuan Zha (Georgia Tech) |
- No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium - Descent Curve for Column Subset Selection and the Nyström Method](https://arxiv.org/pdf/2002.09073.pdf)** Michal Derezinski (UC Berkeley); Rajiv Khanna (UC Berkeley); Michael W. Mahoney (UC Berkeley) 3. **[Language Models are Few-Shot Learners](https://arxiv.org/pdf/2005.14165.pdf)** Tom B. Brown (OpenAI); Benjamin Mann (OpenAI); Nick Ryder (OpenAI); Melanie Subbiah (OpenAI); Jared D. Kaplan (Johns Hopkins University); Prafulla Dhariwal (OpenAI); Arvind Neelakantan (OpenAI); Pranav Shyam (OpenAI); Girish Sastry (OpenAI); Amanda Askell (OpenAI); Sandhini Agarwal (OpenAI); Ariel Herbert-Voss (OpenAI); Gretchen M. Krueger (OpenAI); Tom Henighan (OpenAI); Rewon Child (OpenAI); Aditya Ramesh (OpenAI); Daniel Ziegler (OpenAI); Jeffrey Wu (OpenAI); Clemens Winter (OpenAI); Chris Hesse (OpenAI); Mark Chen (OpenAI); Eric Sigler (OpenAI); Mateusz Litwin (OpenAI); Scott Gray (OpenAI); Benjamin Chess (OpenAI); Jack Clark (OpenAI); Christopher Berner (OpenAI); Sam McCandlish (OpenAI); Alec Radford (OpenAI); Ilya Sutskever (OpenAI); Dario Amodei (OpenAI) |
ICML
- Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies - Dickstein (Google Brain) |
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Delayed Impact of Fair Machine Learning
- Understanding Black-box Predictions via Influence Functions
- Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling
- A Nearly-Linear Time Framework for Graph-Structured Sparsity
- Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis
- Vanishing Component Analysis - Packard Labs); Sagi Schein (Hewlett-Packard Labs); Hila Nachlieli (Hewlett-Packard Labs); Shai Shalev Shwartz (The Hebrew University of Jerusalum); Amir Globerson (The Hebrew University of Jerusalum) 2. **[Fast Semidifferential-based Submodular Function Optimization](https://arxiv.org/pdf/1308.1006.pdf)** Rishabh Iyer (University of Washington); Stefanie Jegelka (University of California Berkeley); Jeff Bilmes (University of Washington) |
- On Learning Sets of Symmetric Elements - free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems](https://proceedings.icml.cc/static/paper_files/icml/2020/4134-Paper.pdf)** Kaixuan Wei (Beijing Institute of Technology); Angelica I Aviles-Rivero (University of Cambridge); Jingwei Liang (University of Cambridge); Ying Fu (Beijing Institute of Technology); Carola-Bibiane Schönlieb (University of Cambridge); Hua Huang (Beijing Institute of Technology) |
ICLR
- Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters - Based Simulation with Graph Networks](https://openreview.net/pdf?id=roNqYL0_XP)** Tobias Pfaff (DeepMind); Meire Fortunato (DeepMind); Alvaro Sanchez-Gonzalez (DeepMind); Peter Battaglia (DeepMind) 5. **[Neural Synthesis of Binaural Speech from Mono Audio](https://openreview.net/pdf?id=uAX8q61EVRu)** Alexander Richard (Facebook); Dejan Markovic (Facebook); Israel D. Gebru (Facebook); Steven Krenn (Facebook); Gladstone Alexander Butler (Facebook); Fernando Torre (Facebook); Yaser Sheikh (Facebook) 6. **[Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime](https://openreview.net/pdf?id=PULSD5qI2N1)** Atsushi Nitanda (The University of Tokyo); Taiji Suzuki (The University of Tokyo) 7. **[Rethinking Architecture Selection in Differentiable NAS](https://openreview.net/pdf?id=PKubaeJkw3)** Ruochen Wang (UCLA); Minhao Cheng (UCLA); Xiangning Chen (UCLA); Xiaocheng Tang (DiDi); Cho-Jui Hsieh (UCLA) 8. **[Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/pdf?id=PxTIG12RRHS)** Yang Song (Stanford University); Jascha Sohl-Dickstein (Google Brain); Diederik P Kingma (Google Brain); Abhishek Kumar (Google Brain); Stefano Ermon (Stanford University); Ben Poole (Google Brain)|
CIKM
- Do People and Neural Networks Pay Attention to the Same Words? Studying Eye-tracking Data for Non-factoid QA Evaluation - Baranova (RMIT University); Vladislav Blinov (Ural Federal University); Yukun Zheng (Tsinghua University); Mark Sanderson (University of Massachusetts Amherst); Falk Scholer (RMIT University); Bruce Croft (RMIT University) 2. **[FANG: Leveraging Social Context for Fake News Detection Using Graph Representation](https://arxiv.org/pdf/2008.07939.pdf)** Van-Hoang Nguyen (National University of Singapore); Kazunari Sugiyama (Kyoto University); Preslav Nakov (Qatar Computing Research Institute; HBKU); Min-Yen Kan (National University of Singapore) |
- Relevance estimation with multiple information sources on search engine result pages
- Hike: A Hybrid Human-Machine Method for Entity Alignment in Large-Scale Knowledge Bases
- Vandalism Detection in Wikidata - Universität Weimar); Benno Stein (Bauhaus-Universität Weimar); Gregor Engels (Paderborn University) |
- Assessing the Impact of Syntactic and Semantic Structures for Answer Passages Reranking
- Cross-Device Search
- Penguins in Sweaters, or Serendipitous Entity Search on User-generated Content
ICDM
- this website
- Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
- Discovering Reliable Dependencies from Data: Hardness and Improved Algorithms
- TensorCast: Forecasting with Context using Coupled Tensors
- Diamond Sampling for Approximate Maximum All-pairs Dot-product (MAD) Search
- Ternary Matrix Factorization
- Reconstructing Individual Mobility from Smart Card Transactions: A Space Alignment Approach - Zhong Sun (University of Science and Technology of China) |
RecSys
- Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
- Causal Embeddings for Recommendation
- Local Item-Item Models for Top-N Recommendation
- Context-Aware Event Recommendation in Event-based Social Networks
- Beyond Clicks: Dwell Time for Personalization
- A Fast Parallel SGD for Matrix Factorization in Shared Memory Systems - Sheng Chin (National Taiwan University); Yu-Chih Juan (National Taiwan University); Chih-Jen Lin (National Taiwan University) |
- Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations
ECCV
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images - Csaba Marton (German Aerospace Center); Maximilian Durner (German Aerospace Center); Rudolph Triebel (German Aerospace Center) |
- Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera
- Large-Scale Object Classification using Label Relation Graphs
- this website
ACL
- Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
- Bridging the Gap between Training and Inference for Neural Machine Translation
- Finding syntax in human encephalography with beam search
- Probabilistic Typology: Deep Generative Models of Vowel Inventories
- Finding Non-Arbitrary Form-Meaning Systematicity Using String-Metric Learning for Kernel Regression
- Improving Evaluation of Machine Translation Quality Estimation - 1015.pdf)** Emma Strubell (University of Massachusetts Amherst); Luke Vilnis (University of Massachusetts Amherst); Kate Silverstein (University of Massachusetts Amherst); Andrew McCallum (University of Massachusetts Amherst) |
- Fast and Robust Neural Network Joint Models for Statistical Machine Translation
- Grounded Language Learning from Video Described with Sentences
EMNLP
- Digital voicing of Silent Speech
- Specializing Word Embeddings (for Parsing) by Information Bottleneck
- Linguistically-Informed Self-Attention for Semantic Role Labeling
- Depression and Self-Harm Risk Assessment in Online Forums - level Constraints](https://arxiv.org/pdf/1707.09457.pdf)** Jieyu Zhao (University of Virginia); Tianlu Wang (University of Virginia); Mark Yatskar (University of Washington); Vicente Ordonez (University of Virginia); Kai-Wei Chang (University of Virginia) |
- Global Neural CCG Parsing with Optimality Guarantees
- Broad-coverage CCG Semantic Parsing with AMR - based Natural Language Generation for Spoken Dialogue Systems](https://arxiv.org/pdf/1508.01745.pdf)** Tsung-Hsien Wen (Cambridge University); Milica Gasic (Cambridge University); Nikola Mrkši´c (Cambridge University); Pei-Hao Su (Cambridge University); David Vandyke (Cambridge University); Steve Young (Cambridge University) |
- Modeling Biological Processes for Reading Comprehension - Chun Chen (Stanford University); Abby Vander Linden (Stanford University); Brittany Harding (Stanford University); Brad Huang (Stanford University); Peter Clark (Stanford University); Christopher D. Manning (Stanford University) |
- Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction
NAACL
- Deep contextualized word representations
- Feuding Families and Former Friends; Unsupervised Learning for Dynamic Fictional Relationships - Graber (University of Colorado); Hal Daumé III (University of Maryland) 2. **[Learning to Compose Neural Networks for Question Answering](https://www.aclweb.org/anthology/N16-1181.pdf)** Jacob Andreas (University of California, Berkeley); Marcus Rohrbach (University of California, Berkeley); Trevor Darrell (University of California, Berkeley); Dan Klein (University of California, Berkeley) |
- Unsupervised Morphology Induction Using Word Embeddings
- this website
EACL
- Error Analysis and the Role of Morphology - main.270v2.pdf)** Goran Glavaš (University of Mannheim); Ivan Vulić (University of Cambridge) |

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

Awesome-Best-Papers

KDD

WWW

ICCV

WSDM

CVPR

AAAI

SIGIR

IJCAI

NeurIPS

ICML

ICLR

CIKM

ICDM

RecSys

ECCV

ACL

EMNLP

NAACL

EACL