Jianming Huang

Xun Su, Jianming Huang, Yang Yusen et al.

Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from globally fitting the The reward-tilted distribution, which inherently preserves diversity during multi-modal search. However, current applications of SMC to diffusion models face a fundamental dilemma: early-stage noise samples offer high potential for improvement but are difficult to evaluate accurately, whereas late-stage samples can be reliably assessed but are largely irreversible. To address this exploration-exploitation trade-off, we approach the problem from the perspective of the search algorithm and propose two strategies: Funnel Schedule and Adaptive Temperature. These simple yet effective methods are tailored to the unique generation dynamics and phase-transition behavior of diffusion models. By progressively reducing the number of maintained particles and down-weighting the influence of early-stage rewards, our methods significantly enhance sample quality without increasing the total number of Noise Function Evaluations. Experimental results on multiple benchmarks and state-of-the-art text-to-image diffusion models demonstrate that our approach outperforms previous baselines.

Jianming Huang, Hiroyuki Kasai

Graph data, with its structurally variable nature, represents complex real-world phenomena like chemical compounds, protein structures, and social networks. Traditional Graph Neural Networks (GNNs) primarily utilize the message-passing mechanism, but their expressive power is limited and their prediction lacks explainability. To address these limitations, researchers have focused on graph substructures. Subgraph neural networks (SGNNs) and GNN explainers have emerged as potential solutions, but each has its limitations. SGNNs computes graph representations based on the bags of subgraphs to enhance the expressive power. However, they often rely on predefined algorithm-based sampling strategies, which is inefficient. GNN explainers adopt data-driven approaches to generate important subgraphs to provide explanation. Nevertheless, their explanation is difficult to be translated into practical improvements on GNNs. To overcome these issues, we propose a novel self-supervised framework that integrates SGNNs with the generation approach of GNN explainers, named the Reinforcement Walk Exploration SGNN (RWE-SGNN). Our approach features a sampling model trained in an explainer fashion, optimizing subgraphs to enhance model performance. To achieve a data-driven sampling approach, unlike traditional subgraph generation approaches, we propose a novel walk exploration process, which efficiently extracts important substructures, simplifying the embedding process and avoiding isomorphism problems. Moreover, we prove that our proposed walk exploration process has equivalent generation capability to the traditional subgraph generation process. Experimental results on various graph datasets validate the effectiveness of our proposed method, demonstrating significant improvements in performance and precision.

Jianming Huang, Zhongxi Fang, Hiroyuki Kasai

For graph learning tasks, many existing methods utilize a message-passing mechanism where vertex features are updated iteratively by aggregation of neighbor information. This strategy provides an efficient means for graph features extraction, but obtained features after many iterations might contain too much information from other vertices, and tend to be similar to each other. This makes their representations less expressive. Learning graphs using paths, on the other hand, can be less adversely affected by this problem because it does not involve all vertex neighbors. However, most of them can only compare paths with the same length, which might engender information loss. To resolve this difficulty, we propose a new Graph Kernel based on a Longest Common Subsequence (LCS) similarity. Moreover, we found that the widely-used R-convolution framework is unsuitable for path-based Graph Kernel because a huge number of comparisons between dissimilar paths might deteriorate graph distances calculation. Therefore, we propose a novel metric space by exploiting the proposed LCS-based similarity, and compute a new Wasserstein-based graph distance in this metric space, which emphasizes more the comparison between similar paths. Furthermore, to reduce the computational cost, we propose an adjacent point merging operation to sparsify point clouds in the metric space.

Jianming Huang, Hiroyuki Kasai

For graph classification tasks, many traditional kernel methods focus on measuring the similarity between graphs. These methods have achieved great success on resolving graph isomorphism problems. However, in some classification problems, the graph class depends on not only the topological similarity of the whole graph, but also constituent subgraph patterns. To this end, we propose a novel graph embedding method using a multi-layer adjacent point merging model. This embedding method allows us to extract different subgraph patterns from train-data. Then we present a flexible loss function for feature selection which enhances the robustness of our method for different classification problems. Finally, numerical evaluations demonstrate that our proposed method outperforms many state-of-the-art methods.