Wei-Wei Tu
YOU?
Author Swipe
View article: Robust long-tailed learning under label noise
Robust long-tailed learning under label noise Open
Long-tailed learning aims to enhance the generalization performance of underrepresented tail classes. However, previous methods have largely overlooked the prevalence of noisy labels in training data. In this paper, we address the challeng…
View article: Autonomous Spacecraft Threat Avoidance via Trajectory Prediction and Deep Reinforcement Learning
Autonomous Spacecraft Threat Avoidance via Trajectory Prediction and Deep Reinforcement Learning Open
View article: Comparison Of The Motivation Differences Between Script Teaching Mode And Traditional Teaching Mode For International Business Students in Guangdong Communication Polytechnic
Comparison Of The Motivation Differences Between Script Teaching Mode And Traditional Teaching Mode For International Business Students in Guangdong Communication Polytechnic Open
This study examined the differences in motivation between two classes at Guangdong Communication Polytechnic. One class was taught using a traditional teaching method, while the other was instructed using a script teaching mode. This artic…
View article: A Survey on Self-play Methods in Reinforcement Learning
A Survey on Self-play Methods in Reinforcement Learning Open
Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has shown remarkable success in solving complex non-cooperative mul…
View article: Motivation Differences Between Different Groups of International Business Students in Guangdong Communication Polytechnic
Motivation Differences Between Different Groups of International Business Students in Guangdong Communication Polytechnic Open
This study investigated the motivations of 332 students from Guangdong Communication Polytechnic, conceptualizing the students’ motivations for studying international business. The students answered a motivation questionnaire with 30…
View article: DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization Open
Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, o…
View article: MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment
MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment Open
The advent of deep reinforcement learning (DRL) has significantly advanced the field of robotics, particularly in the control and coordination of quadruped robots. However, the complexity of real-world tasks often necessitates the deployme…
View article: Safe Abductive Learning in the Presence of Inaccurate Rules
Safe Abductive Learning in the Presence of Inaccurate Rules Open
Integrating complementary strengths of raw data and logical rules to improve the learning generalization has been recently shown promising and effective, e.g., abductive learning is one generic framework that can learn the perception model…
View article: LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments Open
Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence. However, existing benchmarks for evaluating LLM Agents either use static datasets, poten…
View article: Special designs and competition protocols
Special designs and competition protocols Open
Chapter 12 of the book "AI Competitions and Benchmarks: The Science Behind the Contests"
View article: ANALYSIS AND OPTIMIZATION OF COLLEGE STUDENT'S EDUCATION AND TRAINING BASED ON TALENT MARKET DEMAND
ANALYSIS AND OPTIMIZATION OF COLLEGE STUDENT'S EDUCATION AND TRAINING BASED ON TALENT MARKET DEMAND Open
Research shows that there is a problem of low employment happiness index among Chinese college graduates in employment. Through literature research and market survey, we found that geographical differences and low matching of positions and…
View article: OpenRL: A Unified Reinforcement Learning Framework
OpenRL: A Unified Reinforcement Learning Framework Open
We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers age…
View article: Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models
Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models Open
The rise of deepfake images, especially of well-known personalities, poses a serious threat to the dissemination of authentic information. To tackle this, we present a thorough investigation into how deepfakes are produced and how they can…
View article: Diverse Policies Converge in Reward-free Markov Decision Processe
Diverse Policies Converge in Reward-free Markov Decision Processe Open
Reinforcement learning has achieved great success in many decision-making tasks, and traditional reinforcement learning algorithms are mainly designed for obtaining a single optimal solution. However, recent works show the importance of de…
View article: Automated 3D Pre-Training for Molecular Property Prediction
Automated 3D Pre-Training for Molecular Property Prediction Open
Molecular property prediction is an important problem in drug discovery and\nmaterials science. As geometric structures have been demonstrated necessary for\nmolecular property prediction, 3D information has been combined with various\ngra…
View article: Efficient Stochastic Approximation of Minimax Excess Risk Optimization
Efficient Stochastic Approximation of Minimax Excess Risk Optimization Open
While traditional distributionally robust optimization (DRO) aims to minimize the maximal risk over a set of distributions, Agarwal and Zhang (2022) recently proposed a variant that replaces risk with excess risk. Compared to DRO, the new …
View article: A graph neural network-based interpretable framework reveals a novel DNA fragility–associated chromatin structural unit
A graph neural network-based interpretable framework reveals a novel DNA fragility–associated chromatin structural unit Open
View article: TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play
TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play Open
Multi-agent football poses an unsolved challenge in AI research. Existing work has focused on tackling simplified scenarios of the game, or else leveraging expert demonstrations. In this paper, we develop a multi-agent system to play the f…
View article: Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization Open
Stochastically Extended Adversarial (SEA) model is introduced by Sachs et al. [2022] as an interpolation between stochastic and adversarial online convex optimization. Under the smoothness condition, they demonstrate that the expected regr…
View article: Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation
Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation Open
This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) has shown promising results for solving this issue. However, …
View article: Additional file 2 of A graph neural network-based interpretable framework reveals a novel DNA fragility–associated chromatin structural unit
Additional file 2 of A graph neural network-based interpretable framework reveals a novel DNA fragility–associated chromatin structural unit Open
Additional file 2: Table S1. Robustness evaluation for DSB-GNN against different Hi-C processing parameters. Table S2. Results of ablation experiments. Table S3. Performance comparison between DSB-GNN, LightGBM and Random Forest with diffe…
View article: Transfer and share: semi-supervised learning from long-tailed data
Transfer and share: semi-supervised learning from long-tailed data Open
View article: LTU Attacker for Membership Inference
LTU Attacker for Membership Inference Open
We address the problem of defending predictive models, such as machine learning classifiers (Defender models), against membership inference attacks, in both the black-box and white-box setting, when the trainer and the trained model are pu…
View article: Codabench: Flexible, easy-to-use, and reproducible meta-benchmark platform
Codabench: Flexible, easy-to-use, and reproducible meta-benchmark platform Open
Obtaining a standardized benchmark of computational methods is a major issue in data-science communities. Dedicated frameworks enabling fair benchmarking in a unified environment are yet to be developed. Here, we introduce Codabench, a met…
View article: Bridging the Gap of AutoGraph Between Academia and Industry: Analyzing AutoGraph Challenge at KDD Cup 2020
Bridging the Gap of AutoGraph Between Academia and Industry: Analyzing AutoGraph Challenge at KDD Cup 2020 Open
Graph structured data is ubiquitous in daily life and scientific areas and has attracted increasing attention. Graph Neural Networks (GNNs) have been proved to be effective in modeling graph structured data and many variants of GNN archite…
View article: Transfer and Share: Semi-Supervised Learning from Long-Tailed Data
Transfer and Share: Semi-Supervised Learning from Long-Tailed Data Open
Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced u…
View article: Projection-free Online Learning with Arbitrary Delays
Projection-free Online Learning with Arbitrary Delays Open
Projection-free online learning, which eschews the projection operation via less expensive computations such as linear optimization (LO), has received much interest recently due to its efficiency in handling high-dimensional problems with …
View article: Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020 Open
Graph structured data is ubiquitous in daily life and scientific areas and has attracted increasing attention. Graph Neural Networks (GNNs) have been proved to be effective in modeling graph structured data and many variants of GNN archite…
View article: Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios
Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios Open
Human behavior forecasting during human-human interactions is of utmost importance to provide robotic or virtual agents with social intelligence. This problem is especially challenging for scenarios that are highly driven by interpersonal …
View article: Didn't see that coming: a survey on non-verbal social human behavior forecasting
Didn't see that coming: a survey on non-verbal social human behavior forecasting Open
Non-verbal social human behavior forecasting has increasingly attracted the interest of the research community in recent years. Its direct applications to human-robot interaction and socially-aware human motion generation make it a very at…