[2022 Spring] Paper Review

Paper Review 1

• [ICDM 21] AS-GCN : Adoptive Semantic Architecture of Graph Convolutional Networks for Text-Rich Networks

• [KDD 19] Deep Anomaly Detection with Deviation Network

• [NeurIPS 19] Latent ODEs for Irregularly-Sampled Time Series

• [NeurIPS 20] Graph Meta Learning via Local Subgraphs

• [ICCV 21] Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

• [CHI 21] FaceSight; Enabling Hand-to-Face Gesture Interaction on AR Glasses with a Downward-Facing Camera Vision

• [WACV 22] Boosting Contrastive Self-Supervised Learning with False Negative Cancellation

• [ICDM 20] CITIES - Contextual Inference of Tail-item Embeddings for Sequential Recommendation

• [ICML 20] Deep Reinforcement Learning amidst Lifelong Non-Stationarity

• [KDD 21] Unsupervised Detection of Adversarial Examples with Model Explanations

• [ICLR 22] When Vision Transformer Outperform ResNet Without Pre-Training Or Strong Data Augmentation

• [ICLR 22] Finetuning Language Models are Zero-shot Learners

• [CVPR 21] Sequential Graph Convolutional Network for Active Learning

• [ICLR 18] Deep Neural Networks as Gaussian Processes

• [CVPR 18] Deep Depth Completion of a Single RGB-D Image

• [WWW 22] Modeling User Behavior with Graph Convolution for Personalized Product Search

• [ICLR 21] Self-Supervised Learning from a Multi-View Perspective

• [AAAI 21] Towards Effective Context for Meta-Reinforcement Learning- an Approach based on Contrastive Learning

• [ICCV 21] Interpretable Image Recognition by Constructing Transparent Embedding Space

• [NeurIPS 21] Meta-learning Sparse Implicit Neural Representations

• [ECCV 18] Choose Your Neuron- Incorporating Domain Knowledge through Neuron-Importance

• [ICML 21] GRAND_Graph Neural Diffusion

• [AAAI 20] Graph Neural Ordinary Differential Equations

• [NeurIPS 20] Emergent Complextity and Zero-shot Transfer via Unsupervised Environment Design

• [NeurIPS 21] Fast Axiomatic Attributions for Neural Networks

• [ICLR 21] COIN- COmpression with Implicit Neural Networks

• [NeurIPS 21] Edge Representation Learning with Hypergraphs

• [ICML 21] E(n) Equivariant Graph Neural Networks

• [AAAI 21] Data Augmentation for Graph Neural Networks

• [NeurIPS 21] Learning Large Neighborhood Search Policy for Integer Programming

• [ICLR 21] WHAT SHOULD NOT BE CONTRAST IN CONTRASTIVE LEARNING

• [ICLR 22] Equivariant Subgraph Aggregation Networks

• [NeurIPS 20] Not all unlabeled data are euqal - Learning to weight data in semi-superviwd learning

• [ICML 21] Slot Machines- Discovering Winning Combinations of Random Weights in Neural Networks

• [ICML 20] Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders

• [NeurIPS 19] Varitional Graph Recurrent Neural Network

Paper Review 2

• [ICML 19] Position-aware Graph Neural Networks
• [CVPR 19] One-class Novelty Detection Using GANs with Constrained Latent Representations
• [CVPR 21] Points as Queries- Weakly Semi-supervised Object Detection by Points
• [ICLR 22] Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization
• [ICDE 20] Price-aware Recommendation with Graph Convolutional Networks
• [CVPR 21] Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning
• [ICLR 22] How attentive are graph neural network?
• [AAAI 21] Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay
• [ICML 19] How does Disagreement Help Generalization against Label Corruption?
• [WSDM 20] Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• [ICLR 22] PF-GNN- Differentiable particle filtering based approximation of universal graph representations
• [RecSys 20] Long-tail Session-based Recommendation
• [ICLR 22] Handling Distribution Shifts on Graphs_An Invariance Perspective
• [NeurIPS 21] A 3D Molecule Generative Model for Structure-Based Drug Design
• [WWW 20] Structural Deep Clustering Network
• [NeurIPS 21] Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
• [NeurIPS 21] Pay Attention to MLPs
• [NeurIPS 21] Are Transformers More Robust Than CNNs?
• [ICLR 20] AugMix - A Simple Data Processing Method to Improve Robustness and Uncertainty
• [AAAI 20] Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• [ICLR 21] Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• [DCC 22] Neural JPEG- End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder
• [NeurIPS 21] Conformal Time-Series Forecasting
• [CHI 19] Continuous Alertness Assessments; Using EOG Glasses to Unobtrusively Monitor Fatigue Levels In-The-Wild
• [AAAI 21] Overcoming Catastrophic Forgetting in Graph Neural Networks
• [ICML 20] Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
• [CVPR 22] When Does Contrastive Visual Representation Learning Work?
• [AAAI 20] Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• [AAAI 22] MAPDP- Cooperative Multi-Agent Reinforcement Learning to Solve Pickup and Delivery Problems
• [ICLR 20] Mixup Inference Better Exploiting Mixup to Defend Adversarial Attacks
• [ICLR 22] Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks
• [CVPR 22] Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
• [NeurIPS 20] EvloveGraph- Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
• [CVPR 21] CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models
• [CoRL 21] Motivating Physical Activity via Competitive Human-Robot Interaction
• [ICLR 22] Spanning Tree-based Graph Generation for Molecules