Author name cluster

Bo Huang

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.

17 papers

2 author rows

AAAI Conference 2026 Conference Paper

Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection

Mingyang Chen
Jiawei Du
Bo Huang
Yi Wang
Xiaobo Zhang
Wei Wang

Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. This omission may hinder the constructed subset from capturing subtle yet critical distributional structures that underpin effective model training. In this work, we propose a novel, theoretically grounded approach that leverages diffusion models to estimate data likelihood via reconstruction deviation induced by partial reverse denoising. Specifically, we establish a formal connection between reconstruction error and data likelihood, grounded in the Evidence Lower Bound (ELBO) of Markovian diffusion processes, thereby enabling a principled, distribution-aware scoring criterion for data selection. Complementarily, we introduce an efficient information-theoretic method to identify the optimal reconstruction timestep, ensuring that the deviation provides a reliable signal indicative of underlying data likelihood. Extensive experiments on ImageNet demonstrate that reconstruction deviation offers an effective scoring criterion, consistently outperforming existing baselines across selection ratios, and closely matching full-data training using only 50% of the data. Further analysis shows that the likelihood-informed nature of our score reveals informative insights in data selection, shedding light on the interplay between data distributional characteristics and model learning preferences.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SSCL: Adversarially Guided Image Compression via Semantic and Spectral Consistency Learning

Wei Jiang
Yongqi Zhai
Jiayu Yang
Bohao Feng
Wenqiang Wang
Bo Huang
Lin Ding
Ronggang Wang

Perceptual image compression has recently gained increasing attention, as it aims to reconstruct visually realistic images using generative models. Most existing methods adopt patch-based generative adversarial networks (PatchGAN) for one-step image generation, where adversarial training helps the decoder learn the distribution of natural images. However, this strategy is often coarse-grained, as it focuses mainly on patch-level consistency and overlooks global structural and semantic details. To address this limitation, we propose a simple yet effective Semantic and Spectral Consistency Learning (SSCL) strategy, which complements existing patch-based approaches for more accurate distribution alignment. For semantic consistency, we leverage semantic vision models to extract semantic features. The semantic discriminator, aware of the specific semantics of each image, provides more adaptive and precise feedback. This guides the encoder to retain meaningful information and helps the decoder synthesize detailed textures, without requiring explicit semantic transmission or additional modules. For spectral consistency, we introduce a frequency discriminator that focuses on high-frequency components, helping to reduce artifacts based on spectral priors. Experiments show that SSCL outperforms existing perceptual codecs in terms of visual quality. Compared to MS-ILLM, SSCL achieves 45% to 60% bit-rate savings on CLIC2020 and Kodak datasets, measured by FID and DISTS.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

Yuxin Jiang
Bo Huang
Yufei Wang 0005
Xingshan Zeng
Liangyou Li
Yasheng Wang
Xin Jiang 0002
Lifeng Shang

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the generation of the winning response and the losing response within pairwise data are typically isolated, leading to weak correlations between them as well as suboptimal alignment performance. To address this issue, we propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC. Firstly, we increase the consistency and informativeness of the pairwise preference signals through targeted modifications, synthesizing a pseudo-winning response by improving the losing response with the winning response as a reference. Secondly, we identify that DPO alone is insufficient to model these correlations and capture nuanced variations. Therefore, we propose learning token-level correlations by dynamically leveraging the policy model's confidence during training. Comprehensive experiments on QA, math, and instruction-following tasks demonstrate the effectiveness of our approach, significantly surpassing competitive baselines, including DPO. Additionally, our in-depth quantitative analysis reveals the reasons behind our method's superior performance over DPO and showcases its versatility to other DPO variants.

Details

ICML Conference 2025 Conference Paper

Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models

Dihan Zheng
Bo Huang

Fluorescence microscopy is ubiquitously used in cell biology research to characterize the cellular role of a protein. To help elucidate the relationship between the amino acid sequence of a protein and its cellular function, we introduce CELL-Diff, a unified diffusion model facilitating bidirectional transformations between protein sequences and their corresponding microscopy images. Utilizing reference cell morphology images and a protein sequence, CELL-Diff efficiently generates corresponding protein images. Conversely, given a protein image, the model outputs protein sequences. CELL-Diff integrates continuous and diffusion models within a unified framework and is implemented using a transformer-based network. We train CELL-Diff on the Human Protein Atlas (HPA) dataset and fine-tune it on the OpenCell dataset. Experimental results demonstrate that CELL-Diff outperforms existing methods in generating high-fidelity protein images, making it a practical tool for investigating subcellular protein localization and interactions.

Details

IJCAI Conference 2025 Conference Paper

Going Beyond Consistency: Target-oriented Multi-view Graph Neural Network

Sujia Huang
Lele Fu
Shuman Zhuang
Yide Qiu
Bo Huang
Zhen Cui
Tong Zhang

Multi‐view learning has emerged as a pivotal research area driven by the growing heterogeneity of real‐world data, and graph neural network-based models, modeling multi-view data as multi-view graphs, have achieved remarkable performance by revealing its deep semantics. However, by assuming cross‐view consistency, most approaches collect not only task-relevant (determinative) semantics but also symbiotic yet task-irrelevant (incidental) factors are collected to obscure model inference. Furthermore, these approaches often lack rigorous theoretical analysis that bridges training data to test data. To address these issues, we propose Target-oriented Graph Neural Network (TGNN), a novel framework that goes beyond traditional consistency by prioritizing task-relevant information, ensuring alignment with the target. Specifically, TGNN employs a class-level dual-objective loss to minimize the classification similarity between determinative and incidental factors, accentuating the former while suppressing the latter during model inference. Meanwhile, to ensure consistency between the learned semantics and predictions in representation learning, we introduce a penalty term that aims to amplify the divergence between these two types of factors. Furthermore, we derive an upper bound on the loss discrepancy between training and test data, providing formal guarantees for generalization to test domains. Extensive experiments conducted on three types of multi-view datasets validate the superiority of TGNN.

PDF Details DOI

EAAI Journal 2025 Journal Article

Multilingual entity alignment by abductive knowledge reasoning on multiple knowledge graphs

Muhammad Usman Akhtar
Jin Liu
Zhiwen Xie
Xiaohui Cui
Xiao Liu
Bo Huang

Objectives: Entity alignment (EA) seeks to identify similar real-world objects in different multilingual knowledge graphs (KGs), also known as ontology alignment. EA assists in handling a wide range of language semantics and in building integrated knowledge bases. However, most mainstream studies have focused on structural information, paying little attention to insufficient contextual information and limited handling of complex relationships. This paper aims to address these limitations and improve EA performance and efficiency. Methods: This paper investigates multilingual EA techniques and proposes a novel Abductive Knowledge Reasoning (AKR) model to address these issues. AKR can compute complex relationship semantics context by reasoning and enrich counterpart entity contextual information through centrality calculation, which helps connect distant entities in multilingual KGs. Novelty: The proposed AKR model introduces a new approach to EA by integrating centrality calculation and relational semantics reasoning. This method overcomes the limitations of existing EA techniques by effectively handling insufficient contextual information and complex relationships in multilingual KGs. Findings: AKR outperforms all state-of-the-art EA models across five datasets. AKR achieves H i t @ 1 score of 79. 4%, for entity alignment between Chinese-to-English knowledge graphs representing 19. 9% improvement over the best-performing translation-based model, Neighborhood-Aware Attentional Representation Entity Alignment, and a 5. 0% improvement over the best-performing graph neural network-based model, Relational Semantics Augmentation.

Details DOI

NeurIPS Conference 2025 Conference Paper

WKV-sharing embraced random shuffle RWKV high-order modeling for pan-sharpening

Man Zhou
Xuanhua He
Danfeng Hong
Bo Huang

Pan-sharpening aims to generate a spatially and spectrally enriched multi-spectral image by integrating complementary cross-modality information from low-resolution multi-spectral image and texture-rich panchromatic counterpart. In this work, we propose a WKV-sharing embraced random shuffle RWKV high-order modeling paradigm for pan-sharpening from Bayesian perspective, coupled with random weight manifold distribution training strategy derived from Functional theory to regularize the solution space adhering to the following principles: 1) Random-shuffle RWKV. Recently, the Vision RWKV model, with its inherent linear complexity in global modeling, has inspired us to explore its untapped potential in pan-sharpening tasks. However, its attention mechanism, relying on a recurrent bidirectional scanning strategy, suffers from biased effects and demands significant processing time. To address this, we propose a novel Bayesian-inspired scanning strategy called Random Shuffle, complemented by a theoretically-sound inverse shuffle to preserve information coordination invariance, effectively eliminating biases associated with fixed sequence scanning. The Random Shuffle approach mitigates preconceptions in global 2D dependencies in mathematical expectation, providing the model with an unbiased prior. In line with similar spirit of Dropout, we introduce a testing methodology based on Monte Carlo averaging to ensure the model’s output aligns more closely with expected results. 2) WKV-sharing high-order. Regarding KV’s attention score calculation in spatial mixer of RWKV, we leverage WKV-sharing mechanism to transfer KV activations across RWKV layers, achieving lower latency and improved trainability, and revisit the channel mixer in RWKV, originally a first-order weighting function, and redevelop its high-order potential by sharing the gate mechanism across RWKV layer. Comprehensive experiments across pan-sharpening benchmarks demonstrate our model’s effectiveness, consistently outperforming state-of-the-art alternatives

PDF Details

EAAI Journal 2024 Journal Article

A multi-task learning model for recommendation based on fusion of dynamic and static neighbors

Bo Huang
Sirui Zheng
Hamido Fujita
Jin Liu

To improve recommendation performance, this study introduces self-supervised learning into recommendation systems and proposes a multi-task learning recommendation framework that combines static neighbor and dynamic neighbor contrastive learning. Specifically, this study considers node relationships at both the graph and embedding levels, which can be defined in two aspects: (1) Static neighbors, which are positive nodes obtained by integrating information from user-item interaction graphs and social graphs. (2) Dynamic neighbors refer to nodes at the encoding level that are similar, but not necessarily the same, at each iteration; hence, they are termed dynamic neighbors. By employing static neighbor contrastive learning and dynamic neighbor contrastive learning as auxiliary tasks for the main recommendation task, we optimized the user and item embeddings. Through extensive experiments using multiple real datasets, we validate the effectiveness of the proposed approach and its components.

Details DOI

AAMAS Conference 2024 Conference Paper

Engaging the Elderly in Exercise with Agents: A Gamified Stationary Bike System for Sarcopenia Management

Yang Qiu
Ping Chen
Huiguo Zhang
Bo Huang
Di Wang
Zhiqi Shen

This paper introduces a portable, gamified exercise system with an embedded agent, specifically designed to aid the elderly in lowerbody workouts using stationary bikes. The system integrates a custom-made Internet of Things (IoT) sensing unit, a gamified application, and an agent-embedded backend platform. By leveraging real-time feedback along with historical user data, the agent actively contributes to exercise safety and adherence by customizing the intensity of workouts and managing break periods. This novel approach aims to make cycling exercise for sarcopenia prevention and intervention more engaging and effective, promoting regular participation and potentially improving health outcomes.

PDF

EAAI Journal 2023 Journal Article

2C2S: A two-channel and two-stream transformer based framework for offline signature verification

Jian-Xin Ren
Yu-Jie Xiong
Hongjian Zhan
Bo Huang

Recently, with the outstanding performance of the transformer in NLP, approaches that employ the transformer to address vision problem is becoming a research focus. However, transformer-based research rarely focuses on signature verification. To fill this gap, this paper proposes a two-channel and two-stream transformer approach (2C2S) to cope with the signature verification problem. 2C2S is composed of original and central streams. The original stream receives the original signature pair as input, and the central stream receives the signature pair generated by cropping the central at the original pair as input. In order to establish the associations among feature channels, a squeeze-and-excitation operation is applied between two standard Swin Transformer blocks. Moreover, an up-sampling enhancement module directly steers the model to focus on useful information. The verification accuracy of 2C2S on SUES-SiG and several publically available datasets: CEDAR, BHSig-B, and BHSig-H, reaches 93. 25%, 90. 68%, 100%, and 72. 22%, respectively. Extensive experiments illustrate that the proposed framework is competitive with the existing techniques for offline handwritten signature verification.

Details DOI

NeurIPS Conference 2023 Conference Paper

CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

Emaad Khwaja
Yun Song
Aaron Agarunov
Bo Huang

We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and vice versa). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, not only capturing the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling de novo protein design. We train and finetune CELL-E 2 on two large-scale datasets of human proteins. We also demonstrate how to use CELL-E 2 to create hundreds of novel nuclear localization signals (NLS). Results and interactive demos are featured at https: //bohuanglab. github. io/CELL-E_2/.

PDF Details

AAAI Conference 2022 Conference Paper

Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data

Shenwang Jiang
Jianan Li
Ying Wang
Bo Huang
Zhang Zhang
Tingfa Xu

Corrupted labels and class imbalance are commonly encountered in practically collected training data, which easily leads to over-fitting of deep neural networks (DNNs). Existing approaches alleviate these issues by adopting a sample re-weighting strategy, which is to re-weight sample by designing weighting function. However, it is only applicable for training data containing only either one type of data biases. In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data. How to handle them simultaneously is a key but under-explored problem. In this paper, we find that these two types of biased samples, though have similar transient loss, have distinguishable trend and characteristics in loss curves, which could provide valuable priors for sample weight assignment. Motivated by this, we delve into the loss curves and propose a novel probe-and-allocate training strategy: In the probing stage, we train the network on the whole biased training data without intervention, and record the loss curve of each sample as an additional attribute; In the allocating stage, we feed the resulting attribute to a newly designed curve-perception network, named CurveNet, to learn to identify the bias type of each sample and assign proper weights through meta-learning adaptively. The training speed of meta learning also blocks its application. To solve it, we propose a method named skip layer meta optimization (SLMO) to accelerate training speed by skipping the bottom layers. Extensive synthetic and real experiments well validate the proposed method, which achieves state-of-the-art performance on multiple challenging benchmarks.

PDF Details

AAAI Conference 2021 Conference Paper

Adversarial Defence by Diversified Simultaneous Training of Deep Ensembles

Bo Huang
Zhiwei Ke
Yi Wang
Wei Wang
Linlin Shen
Feng Liu

Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual classifiers. Recent studies showed that it is viable to increase adversarial robustness by promoting diversity over an ensemble of models. In this paper, we propose adversarial defence by encouraging ensemble diversity on learning high-level feature representations and gradient dispersion in simultaneous training of deep ensemble networks. We perform extensive evaluations under white-box and blackbox attacks including transferred examples and adaptive attacks. Our approach achieves a significant gain of up to 52% in adversarial robustness, compared with the baseline and the state-of-the-art method on image benchmarks with complex data scenes. The proposed approach complements the defence paradigm of adversarial training, and can further boost the performance. The source code is available at https: //github. com/ALIS-Lab/AAAI2021-PDD.

PDF Details

EAAI Journal 2019 Journal Article

DD-CycleGAN: Unpaired image dehazing via Double-Discriminator Cycle-Consistent Generative Adversarial Network

Jingming Zhao
Juan Zhang
Zhi Li
Jenq-Neng Hwang
Yongbin Gao
Zhijun Fang
Xiaoyan Jiang
Bo Huang

Despite the recent progress in image dehazing, the task remains tremendous challenging. To improve the performance of haze removal, we propose a scheme for haze removal based on Double-Discriminator Cycle-Consistent Generative Adversarial Network (DD-CycleGAN), which leverages CycleGAN to translate a hazy image to the corresponding haze-free image. Unlike other methods, it does not need pairs of haze and their corresponding haze-free images for training. Extensive experiments demonstrate that the proposed method achieves significant improvements over the existing methods, both quantitatively as well as qualitatively. And our method can also achieve good effects qualitatively when applied to the real scenes too.

Details DOI

IJCAI Conference 2019 Conference Paper

Model-Agnostic Adversarial Detection by Random Perturbations

Bo Huang
Yi Wang
Wei Wang

Adversarial examples induce model classification errors on purpose, which has raised concerns on the security aspect of machine learning techniques. Many existing countermeasures are compromised by adaptive adversaries and transferred examples. We propose a model-agnostic approach to resolve the problem by analysing the model responses to an input under random perturbations, and study the robustness of detecting norm-bounded adversarial distortions in a theoretical framework. Extensive evaluations are performed on the MNIST, CIFAR-10 and ImageNet datasets. The results demonstrate that our detection method is effective and resilient against various attacks including black-box attacks and the powerful CW attack with four adversarial adaptations.

PDF Details

JMLR Journal 2015 Journal Article

Supervised Learning via Euler's Elastica Models

Tong Lin
Hanlin Xue
Ling Wang
Bo Huang
Hongbin Zha

This paper investigates the Euler's elastica (EE) model for high-dimensional supervised learning problems in a function approximation framework. In 1744 Euler introduced the elastica energy for a 2D curve on modeling torsion-free thin elastic rods. Together with its degenerate form of total variation (TV), Euler's elastica has been successfully applied to low- dimensional data processing such as image denoising and image inpainting in the last two decades. Our motivation is to apply Euler's elastica to high-dimensional supervised learning problems. To this end, a supervised learning problem is modeled as an energy functional minimization under a new geometric regularization scheme, where the energy is composed of a squared loss and an elastica penalty. The elastica penalty aims at regularizing the approximated function by heavily penalizing large gradients and high curvature values on all level curves. We take a computational PDE approach to minimize the energy functional. By using variational principles, the energy minimization problem is transformed into an Euler-Lagrange PDE. However, this PDE is usually high-dimensional and can not be directly handled by common low-dimensional solvers. To circumvent this difficulty, we use radial basis functions (RBF) to approximate the target function, which reduces the optimization problem to finding the linear coefficients of these basis functions. Some theoretical properties of this new model, including the existence and uniqueness of solutions and universal consistency, are analyzed. Extensive experiments have demonstrated the effectiveness of the proposed model for binary classification, multi-class classification, and regression tasks. [abs] [ pdf ][ bib ] &copy JMLR 2015. ( edit, beta )

PDF Details

ICML Conference 2014 Conference Paper

Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery

Cun Mu
Bo Huang
John Wright 0001
Donald Goldfarb

Recovering a low-rank tensor from incomplete information is a recurring problem in signal processing and machine learning. The most popular convex relaxation of this problem minimizes the sum of the nuclear norms (SNN) of the unfolding matrices of the tensor. We show that this approach can be substantially suboptimal: reliably recovering a K-way n\timesn\times⋯\times n tensor of Tucker rank (r, r, \ldots, r) from Gaussian measurements requires Ω( r n^K-1 ) observations. In contrast, a certain (intractable) nonconvex formulation needs only O(r^K + nrK) observations. We introduce a simple, new convex relaxation, which partially bridges this gap. Our new formulation succeeds with O(r^⌊K/2 ⌋n^⌈K/2 ⌉) observations. The lower bound for the SNN model follows from our new result on recovering signals with multiple structures (e. g. sparse, low rank), which indicates the significant suboptimality of the common approach of minimizing the sum of individual sparsity inducing norms (e. g. \ell_1, nuclear norm). Our new tractable formulation for low-rank tensor recovery shows how the sample complexity can be reduced by designing convex regularizers that exploit several structures jointly.

Details