Accept papers: link

时序论文一览

Anomaly detection (anomaly, outlier, out-of-distribution, one-class, Malware detection, …)

• Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise

  Vivek Farias (MIT) · Andrew Li (Carnegie Mellon University) · Tianyi Peng (MIT)

• Transfer-Based Semantic Anomaly Detection

  Lucas Deecke (University of Edinburgh) · Lukas Ruff (Aignostics) · Robert Vandermeulen (TU Berlin) · Hakan Bilen (University of Edinburgh)

• Neural Transformation Learning for Deep Anomaly Detection Beyond Images

  Chen Qiu (TU Kaiserslautern/Bosch Center for Artificial Intelligence) · Timo Pfrommer (Bosch Center for Artificial Intelligence) · Marius Kloft (TU Kaiserslautern) · Stephan Mandt (University of California, Irivine) · Maja Rudolph (BCAI)

• Event Outlier Detection in Continuous Time

  Siqi Liu (University of Pittsburgh) · Milos Hauskrecht (University of Pittsburgh)

• Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

  Lily Zhang (New York University) · Mark Goldstein (New York University) · Rajesh Ranganath (New York University)

• Outlier-Robust Optimal Transport

  Debarghya Mukherjee (University of Michigan) · Aritra Guha (Duke University) · Justin Solomon (MIT) · Yuekai Sun (University of Michigan) · Mikhail Yurochkin (IBM Research AI)

• DORO: Distributional and Outlier Robust Optimization

  Runtian Zhai (Carnegie Mellon University) · Chen Dan (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Pradeep Ravikumar (Carnegie Mellon University)

• Consistent regression when oblivious outliers overwhelm

  Tommaso d’Orsi (ETH Zurich) · Gleb Novikov (ETH Zurich) · David Steurer (ETH Zurich)

• Fixed-Parameter and Approximation Algorithms for PCA with Outliers

  Yogesh Dahiya (The Institute of Mathematical Sciences (HBNI), Chennai, India) · Fedor Fomin (University of Bergen) · Fahad Panolan (Indian Institute of Technology Hyderabad) · Kirill Simonov (University of Bergen)

• Generalization Bounds in the Presence of Outliers: a Median-of-Means Study

  Pierre Laforgue (University of Milan) · Guillaume Staerman (Télécom Paris) · Stephan Clémençon (Télécom Paris)

• Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?

  Dinghuai Zhang (Mila) · Kartik Ahuja (Mila) · Yilun Xu (MIT) · Yisen Wang (Peking University) · Aaron Courville (Université de Montréal)

• Out-of-Distribution Generalization via Risk Extrapolation (REx)

  David Krueger (MILA (University of Montreal)) · Ethan Caballero (Mila) · Joern-Henrik Jacobsen (Apple Inc.) · Amy Zhang (FAIR / UC Berkeley) · Jonathan Binas (Mila, Montreal) · Dinghuai Zhang (Mila) · Remi Le Priol (Mila, Université de Montréal) · Aaron Courville (Université de Montréal

• Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization

  Aseem Baranwal (University of Waterloo) · Kimon Fountoulakis (University of Waterloo) · Aukosh Jagannath (University of Waterloo)

• Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

  John Miller (University of California, Berkeley) · Rohan Taori (Stanford University) · Aditi Raghunathan (Stanford) · Shiori Sagawa (Stanford University) · Pang Wei Koh (Stanford University) · Vaishaal Shankar (UC Berkeley) · Percy Liang (Stanford University) · Yair Carmon (Tel Aviv University) · Ludwig Schmidt (Toyota Research Institute)

Time series

• Conformal prediction interval for dynamic time-series

  Chen Xu (Georgia Institute of Technology) · Yao Xie (Georgia Institute of Technology)

• Voice2Series: Reprogramming Acoustic Models for Time Series Classification

  Huck Yang (Georgia Tech) · Yun-Yun Tsai (Columbia University) · Pin-Yu Chen (IBM Research AI)

• Explaining Time Series Predictions with Dynamic Masks

  Jonathan Crabbé (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

• Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

  Kashif Rasul (Zalando Research) · Calvin Seward (Zalando Research) · Ingmar Schuster (Zalando Research) · Roland Vollgraf (Zalando Research)

• Necessary and sufficient conditions for causal feature selection in time series with latent common causes

  Atalanti Mastakouri (Amazon Research Tuebingen) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Dominik Janzing (Amazon)

• Approximation Theory of Convolutional Architectures for Time Series Modelling

  Haotian Jiang (National University of Singapore) · Zhong Li (Peking University) · Qianxiao Li (National University of Singapore; IHPC, Singapore)

• Whittle Networks: A Deep Likelihood Model for Time Series

  Zhongjie Yu (TU Darmstadt) · Fabrizio Ventola (TU Darmstadt) · Kristian Kersting (TU Darmstadt)

• Neural Rough Differential Equations for Long Time Series

  James Morrill (University of Oxford) · Cristopher Salvi (University of Oxford) · Patrick Kidger (University of Oxford) · James Foster (University of Oxford)

• End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series

  Syama Sundar Yadav Rangapuram (Amazon) · Lucien D Werner (California Institute of Technology) · Konstantinos Benidis (Amazon Research) · Pedro Mercado (Amazon Research) · Jan Gasthaus (Amazon Research) · Tim Januschowski (Amazon Research)

• Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

  Yuzhou Chen (Southern Methodist University) · Ignacio Segovia (University of Texas at Dallas) · Yulia R Gel (University of Texas at Dallas)

Heterogeneous (multi-source)

• Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

  Tao Lin (EPFL) · Sai Praneeth Reddy Karimireddy (EPFL) · Sebastian Stich (EPFL) · Martin Jaggi (EPFL)

• Budgeted Heterogeneous Treatment Effect Estimation

  Tian Qin (Nanjing University) · Tian-Zuo Wang (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

• Data-Free Knowledge Distillation for Heterogeneous Federated Learning

  Zhuangdi Zhu (Michigan State University) · Junyuan Hong (Michigan State University) · Jiayu Zhou (Michigan State University)

• Heterogeneous Risk Minimization

  Jiashuo Liu (Tsinghua University) · Zheyuan Hu (Tsinghua University) · Peng Cui (Tsinghua University) · Bo Li (Tsinghua University) · Zheyan Shen (Tsinghua University)

• Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

  Tomoya Murata (NTT DATA Mathematical Systems Inc.) · Taiji Suzuki (The University of Tokyo / RIKEN)

• Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data

  Deepesh Data (UCLA) · Suhas Diggavi (UCLA)

• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation

  Haozhe Feng (State Key Lab of CAD&CG, Zhejiang University) · Zhaoyang You (Zhejiang University) · Minghao Chen (Zhejiang University) · Tianye Zhang (Zhejiang University) · Minfeng Zhu (State Key Lab of CAD&CG, Zhejiang University) · Fei Wu (Zhejiang University, China) · Chao Wu (Zhejiang University) · Wei Chen (State Key Lab of CAD&CG, Zhejiang University)

Graph Representation Learning

• Explainable Automated Graph Representation Learning with Hyperparameter Importance

  Xin Wang (Tsinghua University) · Shuyi Fan (Tsinghua University) · Kun Kuang (Zhejiang University) · wenwu zhu (Tsinghua University)

• Size-Invariant Graph Representations for Graph Classification Extrapolations

  Beatrice Bevilacqua (Purdue University) · Yangze Zhou (Purdue University) · Bruno Ribeiro (Purdue University)

• Generative Causal Explanations for Graph Neural Networks

  Wanyu Lin (Department of Computing, The Hong Kong Polytechnic University) · Hao Lan (University of Toronto) · Baochun Li (University of Toronto)

Sequence

• Near-Optimal Confidence Sequences for Bounded Random Variables

  Arun Kuchibhotla (Carnegie Mellon University) · Qinqing Zheng (Facebook AI Research)

• Off-Policy Confidence Sequences

  Nikos Karampatziakis (Microsoft) · Paul Mineiro (Microsoft) · Aaditya Ramdas (Carnegie Mellon University)

• Learning to Rehearse in Long Sequence Memorization

  Zhu Zhang (DAMO Academy, Alibaba Group,) · Chang Zhou (Alibaba Group) · Jianxin Ma (Alibaba Group) · Zhijie Lin (Zhejiang University) · Jingren Zhou (Alibaba Group) · Hongxia Yang (Alibaba Group) · Zhou Zhao (Zhejiang University)

• Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

  Xiaohui Chen (Tufts University) · Xu Han (Tufts University) · Jiajing Hu (Tufts University) · Francisco R Ruiz (DeepMind) · Liping Liu (Tufts University)

• A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting

  Eli N. Weinstein (Harvard) · Debora Marks (Harvard Medical School)

• Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design

  yue cao (Texas A&M University) · Payel Das (IBM Research AI) · Vijil Chenthamarakshan (IBM Research) · Pin-Yu Chen (IBM Research AI) · Igor Melnyk (IBM) · Yang Shen (Texas A&M University)

• Temporally Correlated Task Scheduling for Sequence Learning

  Xueqing Wu (University of Science and Technology of China) · Lewen Wang (Microsoft Research Asia) · Yingce Xia (Microsoft Research Asia) · Weiqing Liu (Microsoft Research) · Lijun Wu (Microsoft Research) · Shufang Xie (Microsoft Research Asia) · Tao Qin (Microsoft Research Asia) · Tie-Yan Liu (Microsoft Research Asia)

Autoencoder

• Unified Robust Semi-Supervised Variational Autoencoder

  Xu Chen (SAS Inc)

• MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space

  Sophie C Laturnus (University of Tübingen) · Philipp Berens (University of Tübingen)

• Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders

  Adeel Pervez (University of Amsterdam) · Efstratios Gavves (University of Amsterdam )

• Autoencoder Image Interpolation by Shaping the Latent Space

  Alon Oring (IDC) · Zohar Yakhini (Herzliya Interdisciplinary Center) · Yacov Hel-Or (The Interdisciplinary Center, Herzliya)

• BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders

  Dominic Danks (Alan Turing Institute) · Christopher Yau (University of Manchester)

• Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

  Sang Michael Xie (Stanford University) · Tengyu Ma (Stanford University) · Percy Liang (Stanford University)

• Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

  Jaehyeon Kim (Kakao Enterprise) · Jungil Kong (Kakao Enterprise) · Juhee Son (Kakao Enterprise)

Recurrent Neural Network

• Training Recurrent Neural Networks via Forward Propagation Through Time

  Anil Kag (Boston University) · Venkatesh Saligrama (Boston University)

• Re-understanding Finite-State Representations of Recurrent Policy Networks

  Mohamad H Danesh (Oregon State University) · Anurag Koul (Oregon State University) · Alan Fern (Oregon State University) · Saeed Khorram (Oregon State University)

• UnICORNN: A recurrent model for learning very long time dependencies

  T. Konstantin Rusch (ETH Zurich) · Siddhartha Mishra (ETH Zurich)

Correlation analysis (association analysis)

• Inferring serial correlation with dynamic backgrounds

  Song Wei (Georgia Tech) · Yao Xie (Georgia Institute of Technology) · Dobromir Rahnev (Georgia Tech)

• Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

  Gabriele Farina (Carnegie Mellon University) · Andrea Celli (Facebook CDS) · Nicola Gatti (Politecnico di Milano) · Tuomas Sandholm (Carnegie Mellon University)

• Local Correlation Clustering with Asymmetric Classification Errors

  Jafar Jafarov (University of Chicago) · Sanchit Kalhan (Northwestern University) · Konstantin Makarychev (Northwestern University) · Yury Makarychev (Toyota Technological Institute at Chicago)

• Differentially Private Correlation Clustering

  Mark Bun (Boston University) · Marek Elias (CWI) · Janardhan Kulkarni (Microsoft Research)

• A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions

  Gabriel Mel (Stanford University) · Surya Ganguli (Stanford)

• Correlation Clustering in Constant Many Parallel Rounds

  Vincent Cohen-Addad (Google) · Silvio Lattanzi (Google) · Slobodan Mitrović (MIT) · Ashkan Norouzi-Fard (Google) · Nikos Parotsidis (Google) · Jakub Tarnawski (Microsoft Research)

• Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

  Ning Liu (Midea Group) · Geng Yuan (Northeastern University) · Zhengping Che (Didi Chuxing) · Xuan Shen (Northeastern University) · Xiaolong Ma (Northeastern University) · Qing Jin (Northeastern University) · Jian Ren (Snap Inc.) · Jian Tang (AI Innovation Center, Midea Group) · Sijia Liu (Michigan State University) · Yanzhi Wang (Northeastern University)

• Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

  John Miller (University of California, Berkeley) · Rohan Taori (Stanford University) · Aditi Raghunathan (Stanford) · Shiori Sagawa (Stanford University) · Pang Wei Koh (Stanford University) · Vaishaal Shankar (UC Berkeley) · Percy Liang (Stanford University) · Yair Carmon (Tel Aviv University) · Ludwig Schmidt (Toyota Research Institute)

Causal analysis

• Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning

  Sumedh Sontakke (University of Southern California) · Arash Mehrjou (Max Planck Institute for Intelligent Systems) · Laurent Itti (University of Southern California) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

• Integer Programming for Causal Structure Learning in the Presence of Latent Variables

  Rui Chen (University of Wisconsin-Madison) · Sanjeeb Dash (IBM Research) · Tian Gao (IBM Research)

• How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference

  Amanda Gentzel (University of Massachusetts Amherst) · Purva Pruthi (University of Massachusetts Amherst) · David Jensen (University of Massachusetts Amherst)

• Model-Free and Model-Based Policy Evaluation when Causality is Uncertain

  David Bruns-Smith (UC Berkeley)

• Domain Generalization using Causal Matching

  Divyat Mahajan (Microsoft Research India) · Shruti Tople (Microsoft Research) · Amit Sharma (Microsoft Research)

• Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning

  Yonghan Jung (Purdue University) · Jin Tian (Iowa State University) · Elias Bareinboim (Columbia)

• Valid Causal Inference with (Some) Invalid Instruments

  Jason Hartford (University of British Columbia) · Victor Veitch (Google; University of Chicago) · Dhanya Sridhar (Columbia University) · Kevin Leyton-Brown (University of British Columbia)

• Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding

  Andrew Jesson (University of Oxford) · Sören Mindermann (University of Oxford) · Yarin Gal (University of Oxford) · Uri Shalit (Technion)

• Regularizing towards Causal Invariance: Linear Models with Proxies

  Michael Oberst (MIT) · Nikolaj Thams (University of Copenhagen) · Jonas Peters (University of Copenhagen) · David Sontag (Massachusetts Institute of Technology)

• Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction

  Afsaneh Mastouri (University College London) · Yuchen Zhu (University College London) · Limor Gultchin (University of Oxford) · Anna Korba (CREST/ENSAE) · Ricardo Silva (University College London) · Matt J. Kusner (University College London) · Arthur Gretton (Gatsby Computational Neuroscience Unit) · Krikamol Muandet (Max Planck Institute for Intelligent Systems)

• Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners

  Elias Chaibub Neto (Sage Bionetworks)

Clustering

About distribution

Interpretable [Understanding, explanation, Attribution …]