Junjie Xu

Ziang Liu, Junjie Xu, Xingjiao Wu et al.

Preference-Based reinforcement learning (PBRL) learns directly from the preferences of human teachers regarding agent behaviors without needing meticulously designed reward functions. However, existing PBRL methods often learn primarily from explicit preferences, neglecting the possibility that teachers may choose equal preferences. This neglect may hinder the understanding of the agent regarding the task perspective of the teacher, leading to the loss of important information. To address this issue, we introduce the Equal Preference Learning Task, which optimizes the neural network by promoting similar reward predictions when the behaviors of two agents are labeled as equal preferences. Building on this task, we propose a novel PBRL method, Multi-Type Preference Learning (MTPL), which allows simultaneous learning from equal preferences while leveraging existing methods for learning from explicit preferences. To validate our approach, we design experiments applying MTPL to four existing state-of-the-art baselines across ten locomotion and robotic manipulation tasks in the DeepMind Control Suite. The experimental results indicate that simultaneous learning from both equal and explicit preferences enables the PBRL method to more comprehensively understand the feedback from teachers, thereby enhancing feedback efficiency. Project page: \url{https://github.com/FeiCuiLengMMbb/paper_MTPL}

Fali Wang, Tianxiang Zhao, Junjie Xu et al.

Graph self-training (GST), which selects and assigns pseudo-labels to unlabeled nodes, is popular for tackling label sparsity in graphs. However, recent study on homophily graphs show that GST methods could introduce and amplify distribution shift between training and test nodes as they tend to assign pseudo-labels to nodes they are good at. As GNNs typically perform better on homophilic nodes, there could be potential shifts towards homophilic pseudo-nodes, which is underexplored. Our preliminary experiments on heterophilic graphs verify that these methods can cause shifts in homophily ratio distributions, leading to \textit{training bias} that improves performance on homophilic nodes while degrading it on heterophilic ones. Therefore, we study a novel problem of reducing homophily ratio distribution shifts during self-training on heterophilic graphs. A key challenge is the accurate calculation of homophily ratios and their distributions without extensive labeled data. To tackle them, we propose a novel Heterophily-aware Distribution Consistency-based Graph Self-Training (HC-GST) framework, which estimates homophily ratios using soft labels and optimizes a selection vector to align pseudo-nodes with the global homophily ratio distribution. Extensive experiments on both homophilic and heterophilic graphs show that HC-GST effectively reduces training bias and enhances self-training performance.

Junjie Xu, Zongyu Wu, Minhua Lin et al.

Recent progress in Graph Neural Networks (GNNs) has greatly enhanced the ability to model complex molecular structures for predicting properties. Nevertheless, molecular data encompasses more than just graph structures, including textual and visual information that GNNs do not handle well. To bridge this gap, we present an innovative framework that utilizes multimodal molecular data to extract insights from Large Language Models (LLMs). We introduce GALLON (Graph Learning from Large Language Model Distillation), a framework that synergizes the capabilities of LLMs and GNNs by distilling multimodal knowledge into a unified Multilayer Perceptron (MLP). This method integrates the rich textual and visual data of molecules with the structural analysis power of GNNs. Extensive experiments reveal that our distilled MLP model notably improves the accuracy and efficiency of molecular property predictions.