Author name cluster

Tianzhe Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

EAAI Journal 2026 Journal Article

Fault prototype weighted guided multi-level dynamic alignment network for partial set domain adaptation fault diagnosis

Bo Liu
Guofa Li
Jialong He
Tianzhe Wang
Rundong Shi

Partial set domain adaptation for fault diagnosis has garnered significant attention due to its alignment with practical engineering applications. However, current research heavily relies on classifier predictions to evaluate sample transferability, where misclassification may hinder the model's ability to distinguish shared and outlier samples. Moreover, the joint alignment at both instance and class level is often neglected, in complex dynamic application scenarios, the contributions of marginal and conditional probability distributions to positive model transfer differ significantly. To address this, a fault prototype weighted guided multi-level dynamic alignment network (FPW-MDAN) is proposed. To mitigate the biasing effect of classifier predictions on cross-domain transferability evaluation, an inter-domain fault prototype correlation guided weighting strategy is developed. This strategy re-weights both instance and class-level probability weights to enhance the robustness of transferability evaluation and correct the model's identification of shared and outlier samples. Building on this weighting strategy, a multi-level weighted dynamic alignment network is constructed, aiming to align the joint probability distribution of cross-domain shared samples from both global and local perspectives, thereby reducing the influence of outlier samples on the transfer process. In addition, the domain classifier alignment strategy is introduced to ensure the consistency of sub-classifiers' predictions for the same samples from target domain and to improve the prediction accuracy of class boundary samples. Finally, comparative experiments and ablation studies were conducted on both public planetary gearbox and self-made parallel gearbox dataset. The experimental results validate the effectiveness and superiority of the proposed method in addressing partial-set domain adaptation for fault diagnosis.

Details DOI

ICLR Conference 2025 Conference Paper

Learning Structured Universe Graph with Outlier OOD Detection for Partial Matching

Zetian Jiang
Jiaxin Lu 0001
Haizhao Fan
Tianzhe Wang
Junchi Yan

Partial matching is a kind of graph matching where only part of two graphs can be aligned. This problem is particularly important in computer vision applications, where challenges like point occlusion or annotation errors often occur when labeling key points. Previous work has often conflated point occlusion and annotation errors, despite their distinct underlying causes. We propose two components to address these challenges: (1) a structured universe graph is learned to connect two input graphs $X_{ij} = X_{iu} X_{ju}^\top$, effectively resolving the issue of point occlusion; (2) an energy-based out-of-distribution detection is designed to remove annotation errors from the input graphs before matching. We evaluated our method on the Pascal VOC and Willow Object datasets, focusing on scenarios involving point occlusion and random outliers. The experimental results demonstrate that our approach consistently outperforms state-of-the-art methods across all tested scenarios, highlighting the accuracy and robustness of our method.

Details

ICLR Conference 2024 Conference Paper

M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering

Jiaxin Lu 0001
Zetian Jiang
Tianzhe Wang
Junchi Yan

Existing graph matching methods typically assume that there are similar structures between graphs and they are matchable. This work addresses a more realistic scenario where graphs exhibit diverse modes, requiring graph grouping before or along with matching, a task termed mixture graph matching and clustering. Specifically, we introduce Minorize-Maximization Matching and Clustering (M3C), a learning-free algorithm that guarantees theoretical convergence through the Minorize-Maximization framework and offers enhanced flexibility via relaxed clustering. Building on M3C, we further develop UM3C, an unsupervised model that incorporates novel edge-wise affinity learning and pseudo label selection. Extensive experimental results on public benchmarks demonstrate that our method outperforms state-of-the-art graph matching and mixture graph matching and clustering approaches in both accuracy and efficiency.

Details

ICLR Conference 2022 Conference Paper

Spanning Tree-based Graph Generation for Molecules

Sungsoo Ahn
Binghong Chen
Tianzhe Wang
Le Song

In this paper, we explore the problem of generating molecules using deep neural networks, which has recently gained much interest in chemistry. To this end, we propose a spanning tree-based graph generation (STGG) framework based on formulating molecular graph generation as a construction of a spanning tree and the residual edges. Such a formulation exploits the sparsity of molecular graphs and allows using compact tree-constructive operations to define the molecular graph connectivity. Based on the intermediate graph structure of the construction process, our framework can constrain its generation to molecular graphs that satisfy the chemical valence rules. We also newly design a Transformer architecture with tree-based relative positional encodings for realizing the tree construction procedure. Experiments on QM9, ZINC250k, and MOSES benchmarks verify the effectiveness of the proposed framework in metrics such as validity, Frechet ChemNet distance, and fragment similarity. We also demonstrate the usefulness of STGG in maximizing penalized LogP value of molecules.

Details

ICLR Conference 2021 Conference Paper

Molecule Optimization by Explainable Evolution

Binghong Chen
Tianzhe Wang
Chengtao Li
Hanjun Dai
Le Song

Optimizing molecules for desired properties is a fundamental yet challenging task in chemistry, material science, and drug discovery. This paper develops a novel algorithm for optimizing molecular properties via an Expectation-Maximization (EM) like explainable evolutionary process. The algorithm is designed to mimic human experts in the process of searching for desirable molecules and alternate between two stages: the first stage on explainable local search which identifies rationales, i.e., critical subgraph patterns accounting for desired molecular properties, and the second stage on molecule completion which explores the larger space of molecules containing good rationales. We test our approach against various baselines on a real-world multi-property optimization task where each method is given the same number of queries to the property oracle. We show that our evolution-by-explanation algorithm is 79% better than the best baseline in terms of a generic metric combining aspects such as success rate, novelty, and diversity. Human expert evaluation on optimized molecules shows that 60% of top molecules obtained from our methods are deemed successful.

Details

AAAI Conference 2020 Conference Paper

Multiple Graph Matching and Clustering via Decayed Pairwise Matching Composition

Tianzhe Wang
Zetian Jiang
Junchi Yan

Jointly matching of multiple graphs is challenging and recently has been an active topic in machine learning and computer vision. State-of-the-art methods have been devised, however, to our best knowledge there is no effective mechanism that can explicitly deal with the matching of a mixture of graphs belonging to multiple clusters, e. g. , a collection of bikes and bottles. Seeing its practical importance, we propose a novel approach for multiple graph matching and clustering. Firstly, for the traditional multi-graph matching setting, we devise a composition scheme based on a tree structure, which can be seen as in the between of two strong multigraph matching solvers, i. e. , MatchOpt (Yan et al. 2015a) and CAO (Yan et al. 2016a). In particular, it can be more robust than MatchOpt against a set of diverse graphs and more ef- ﬁcient than CAO. Then we further extend the algorithm to the multiple graph matching and clustering setting, by adopting a decaying technique along the composition path, to discount the meaningless matching between graphs in different clusters. Experimental results show the proposed methods achieve excellent trade-off on the traditional multi-graph matching case, and outperform in both matching and clustering accuracy, as well as time efﬁciency.

PDF Details

ICLR Conference 2020 Conference Paper

Once-for-All: Train One Network and Specialize it for Efficient Deployment

Han Cai
Chuang Gan 0001
Tianzhe Wang
Zhekai Zhang
Song Han 0003

We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized neural network and train it from scratch for each case, which is computationally prohibitive (causing $CO_2$ emission as much as 5 cars' lifetime) thus unscalable. In this work, we propose to train a once-for-all (OFA) network that supports diverse architectural settings by decoupling training and search, to reduce the cost. We can quickly get a specialized sub-network by selecting from the OFA network without additional training. To efficiently train OFA networks, we also propose a novel progressive shrinking algorithm, a generalized pruning method that reduces the model size across many more dimensions than pruning (depth, width, kernel size, and resolution). It can obtain a surprisingly large number of sub-networks ($> 10^{19}$) that can fit different hardware platforms and latency constraints while maintaining the same level of accuracy as training independently. On diverse edge devices, OFA consistently outperforms state-of-the-art (SOTA) NAS methods (up to 4.0% ImageNet top1 accuracy improvement over MobileNetV3, or same accuracy but 1.5x faster than MobileNetV3, 2.6x faster than EfficientNet w.r.t measured latency) while reducing many orders of magnitude GPU hours and $CO_2$ emission. In particular, OFA achieves a new SOTA 80.0% ImageNet top-1 accuracy under the mobile setting ($<$600M MACs). OFA is the winning solution for the 3rd Low Power Computer Vision Challenge (LPCVC), DSP classification track and the 4th LPCVC, both classification track and detection track. Code and 50 pre-trained models (for many devices & many latency constraints) are released at https://github.com/mit-han-lab/once-for-all.

Details