M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality (M3HF), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, M3HF leverages both expert and non-expert feedback to continuously refine agents' policies. During training, we strategically pause agent learning for human evaluation, parse feedback using large language models to assign it appropriately and update reward functions through predefined templates and adaptive weight by using weight decay and performance-based adjustments. Our approach enables the integration of nuanced human insights across various levels of quality, enhancing the interpretability and robustness of multi-agent cooperation. Empirical results in challenging environments demonstrate that M3HF significantly outperforms state-of-the-art methods, effectively addressing the complexities of reward design in MARL and enabling broader human participation in the training process.

$\text{M}^3\text{HF}$: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\text{M}^3\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\text{M}^3\text{HF}$ leverages both expert and non-expert feedback to continuously refine agents' policies. During training, we strategically pause agent learning for human evaluation, parse feedback using large language models to assign it appropriately and update reward functions through predefined templates and adaptive weight by using weight decay and performance-based adjustments. Our approach enables the integration of nuanced human insights across various levels of quality, enhancing the interpretability and robustness of multi-agent cooperation. Empirical results in challenging environments demonstrate that $\text{M}^3\text{HF}$ significantly outperforms state-of-the-art methods, effectively addressing the complexities of reward design in MARL and enabling broader human participation in the training process.

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the model's output, and probing a small portion of each batch effectively identifies crucial weights, enabling tailored dynamic pruning for different batches. It comprises three main stages: probing, history-informed pruning, and full inference. In the probing stage, PP selects a small yet crucial set of hidden states, based on residual importance, to run a few model layers ahead. During the history-informed pruning stage, PP strategically integrates the probing states with historical states. Subsequently, it structurally prunes weights based on the integrated states and the PP importance score, a metric developed specifically to assess the importance of each weight channel in maintaining performance. In the final stage, full inference is conducted on the remaining weights. A major advantage of PP is its compatibility with existing models, as it operates without requiring additional neural network modules or fine-tuning. Comprehensive evaluations of PP on LLaMA-2/3 and OPT models reveal that even minimal probing-using just 1.5% of FLOPs-can substantially enhance the efficiency of structured pruning of LLMs. For instance, when evaluated on LLaMA-2-7B with WikiText2, PP achieves a 2.56 times lower ratio of performance degradation per unit of runtime reduction compared to the state-of-the-art method at a 40% pruning ratio. Our code is available at https://github.com/Qi-Le1/Probe_Pruning.

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

Diffusion models have made significant advancements in recent years. However, their performance often deteriorates when trained or fine-tuned on imbalanced datasets. This degradation is largely due to the disproportionate representation of majority and minority data in image-text pairs. In this paper, we propose a general fine-tuning approach, dubbed PoGDiff, to address this challenge. Rather than directly minimizing the KL divergence between the predicted and ground-truth distributions, PoGDiff replaces the ground-truth distribution with a Product of Gaussians (PoG), which is constructed by combining the original ground-truth targets with the predicted distribution conditioned on a neighboring text embedding. Experiments on real-world datasets demonstrate that our method effectively addresses the imbalance problem in diffusion models, improving both generation accuracy and quality.

Boolean Product Graph Neural Networks

Graph Neural Networks (GNNs) have recently achieved significant success, with a key operation involving the aggregation of information from neighboring nodes. Substantial researchers have focused on defining neighbors for aggregation, predominantly based on observed adjacency matrices. However, in many scenarios, the explicitly given graphs contain noise, which can be amplified during the messages-passing process. Therefore, many researchers have turned their attention to latent graph inference, specifically learning a parametric graph. To mitigate fluctuations in latent graph structure learning, this paper proposes a novel Boolean product-based graph residual connection in GNNs to link the latent graph and the original graph. It computes the Boolean product between the latent graph and the original graph at each layer to correct the learning process. The Boolean product between two adjacency matrices is equivalent to triangle detection. Accordingly, the proposed Boolean product graph neural networks can be interpreted as discovering triangular cliques from the original and the latent graph. We validate the proposed method in benchmark datasets and demonstrate its ability to enhance the performance and robustness of GNNs.

Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learning

Graph Neural Networks (GNNs) have achieved notable success in the analysis of non-Euclidean data across a wide range of domains. However, their applicability is constrained by the dependence on the observed graph structure. To solve this problem, Latent Graph Inference (LGI) is proposed to infer a task-specific latent structure by computing similarity or edge probability of node features and then apply a GNN to produce predictions. Even so, existing approaches neglect the noise from node features, which affects generated graph structure and performance. In this work, we introduce a novel method called Probability Passing to refine the generated graph structure by aggregating edge probabilities of neighboring nodes based on observed graph. Furthermore, we continue to utilize the LGI framework, inputting the refined graph structure and node features into GNNs to obtain predictions. We name the proposed scheme as Probability Passing-based Graph Neural Network (PPGNN). Moreover, the anchor-based technique is employed to reduce complexity and improve efficiency. Experimental results demonstrate the effectiveness of the proposed method.

ZeroDDI: A Zero-Shot Drug-Drug Interaction Event Prediction Method with Semantic Enhanced Learning and Dual-Modal Uniform Alignment

Drug-drug interactions (DDIs) can result in various pharmacological changes, which can be categorized into different classes known as DDI events (DDIEs). In recent years, previously unobserved/unseen DDIEs have been emerging, posing a new classification task when unseen classes have no labelled instances in the training stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE) task. However, existing computational methods are not directly applicable to ZS-DDIE, which has two primary challenges: obtaining suitable DDIE representations and handling the class imbalance issue. To overcome these challenges, we propose a novel method named ZeroDDI for the ZS-DDIE task. Specifically, we design a biological semantic enhanced DDIE representation learning module, which emphasizes the key biological semantics and distills discriminative molecular substructure-related semantics for DDIE representation learning. Furthermore, we propose a dual-modal uniform alignment strategy to distribute drug pair representations and DDIE semantic representations uniformly in a unit sphere and align the matched ones, which can mitigate the issue of class imbalance. Extensive experiments showed that ZeroDDI surpasses the baselines and indicate that it is a promising tool for detecting unseen DDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.

CEST-KAN: Kolmogorov-Arnold Networks for CEST MRI Data Analysis

Purpose: This study aims to propose and investigate the feasibility of using Kolmogorov-Arnold Network (KAN) for CEST MRI data analysis (CEST-KAN). Methods: CEST MRI data were acquired from twelve healthy volunteers at 3T. Data from ten subjects were used for training, while the remaining two were reserved for testing. The performance of multi-layer perceptron (MLP) and KAN models with the same network settings were evaluated and compared to the conventional multi-pool Lorentzian fitting (MPLF) method in generating water and multiple CEST contrasts, including amide, relayed nuclear Overhauser effect (rNOE), and magnetization transfer (MT). Results: The water and CEST maps generated by both MLP and KAN were visually comparable to the MPLF results. However, the KAN model demonstrated higher accuracy in extrapolating the CEST fitting metrics, as evidenced by the smaller validation loss during training and smaller absolute error during testing. Voxel-wise correlation analysis showed that all four CEST fitting metrics generated by KAN consistently exhibited higher Pearson coefficients than the MLP results, indicating superior performance. Moreover, the KAN models consistently outperformed the MLP models in varying hidden layer numbers despite longer training time. Conclusion: In this study, we demonstrated for the first time the feasibility of utilizing KAN for CEST MRI data analysis, highlighting its superiority over MLP in this task. The findings suggest that CEST-KAN has the potential to be a robust and reliable post-analysis tool for CEST MRI in clinical settings.

Towards Domain Adaptive Neural Contextual Bandits

Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from mice (as a source domain) and humans (as a target domain). Unfortunately, adapting a contextual bandit algorithm from a source domain to a target domain with distribution shift still remains a major challenge and largely unexplored. In this paper, we introduce the first general domain adaptation method for contextual bandits. Our approach learns a bandit model for the target domain by collecting feedback from the source domain. Our theoretical analysis shows that our algorithm maintains a sub-linear regret bound even adapting across domains. Empirical results show that our approach outperforms the state-of-the-art contextual bandit algorithms on real-world datasets.

Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf

Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework.