Exploring how genetic sequences shape phenotypes is a fundamental challenge in biology and a key step toward scalable, hypothesis-driven experimentation. The task is complicated by the large modality gap between sequences and phenotypes, as well as the pleiotropic nature of gene–phenotype relationships. Existing sequence-based efforts focus on the degree to which variants of specific genes alter a limited set of phenotypes, while general gene knockout-induced phenotype abnormality prediction methods heavily rely on curated genetic information as inputs, which limits scalability and generalizability. As a result, the task of broadly predicting the presence of multiple phenotype abnormalities under gene knockout directly from gene sequences remains underexplored. We introduce GenePheno, the first interpretable multi-label prediction framework that predicts knockout-induced phenotypic abnormalities from gene sequences. GenePheno employs a contrastive multi-label learning objective that captures inter-phenotype correlations, complemented by an exclusive regularization that enforces biological consistency. It further incorporates a gene function bottleneck layer, offering human-interpretable concepts that reflect functional mechanisms behind phenotype formation. To support progress in this area, we curate four datasets with canonical gene sequences as input and multi-label phenotypic abnormalities induced by gene knockouts as targets. Across these datasets, GenePheno achieves state-of-the-art gene-centric Fmax and phenotype-centric AUC, and case studies demonstrate its ability to reveal gene functional mechanisms.

Deep learning has significantly advanced numerous fields by training on extensive annotated datasets. However, this data-driven paradigm faces limitations such as limited adaptability and high annotation costs, particularly when precise adherence to detailed, domain-specific guidelines is required in annotation. This challenge raises a critical question: Can models effectively shift from data-driven learning to autonomously leveraging guidelines with minimal annotated examples? To address this, we propose the Guideline-Driven Prompt (GDP) optimization framework, which shifts the learning paradigm from data-driven training to guideline-driven reasoning. GDP leverages Retrieval Augmented Generation (RAG) to retrieve essential fragments from complex guidelines and synthesize them into structured, executable prompts. A tree-based optimization algorithm systematically constructs and refines these prompts, explicitly capturing the intricate logic embedded in professional guidelines through a latent pipeline structure. Empirical evaluations on four datasets ranging from diverse domains and different tasks demonstrate that GDP effectively transitions the learning process from data-intensive methods to a guideline-driven approach in tasks requiring detailed and complex guideline adherence, reducing dependence on extensive annotated datasets.

Haiqing Li, Wenliang Zhong, Yinhao Wu, Hehuan Ma, Yuzhi Guo, Thao M. Dang, Junzhou Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recent advances in discrete diffusion models have demonstrated strong performance in image generation and masked language modeling, yet they remain limited in their capacity for controlled content editing. We propose DICE (Discrete Inversion for Controllable Editing), a novel framework that pioneers precise inversion capabilities for discrete diffusion models, including both masked generative and multinomial diffusion variants. Our key innovation lies in capturing noise sequences and masking patterns during reverse diffusion process, enabling both accurate reconstruction and flexible editing without relying on predefined masks or attention-based manipulations. Through comprehensive experiments across image and text modalities using models such as Paella, VQ-Diffusion, RoBERTa and LLaDA, we demonstrate that DICE successfully maintains high fidelity to the original data while significantly expanding editing capabilities. These results establish new possibilities for fine-grained content manipulation in discrete spaces.

Recently, deep neural networks have greatly advanced undersampled Magnetic Resonance Image (MRI) reconstruction, wherein most studies follow the one-anatomy-one-network fashion, i.e., each expert network is trained and evaluated for a specific anatomy. Apart from inefficiency in training multiple independent models, such convention ignores the shared de-aliasing knowledge across various anatomies which can benefit each other. To explore the shared knowledge, one naive way is to combine all the data from various anatomies to train an all-round network. Unfortunately, despite the existence of the shared de-aliasing knowledge, we reveal that the exclusive knowledge across different anatomies can deteriorate specific reconstruction targets, yielding overall performance degradation. Observing this, in this study, we present a novel deep MRI reconstruction framework with both anatomy-shared and anatomy-specific parameterized learners, aiming to "seek common ground while reserving differences" across different anatomies. Particularly, the primary anatomy-shared learners are exposed to different anatomies to model rich shared de-aliasing knowledge, while the efficient anatomy-specific learners are trained with their target anatomy for exclusive knowledge. Four different implementations of anatomy-specific learners are presented and explored on the top of our framework in two MRI reconstruction networks. Comprehensive experiments on brain, knee and cardiac MRI datasets demonstrate that three of these learners are able to enhance reconstruction performance via multiple anatomy collaborative learning. Extensive studies show that our strategy can also benefit multiple pulse sequence MRI reconstruction by integrating sequence-specific learners.

Exploring the functions of genes and gene products is crucial to a wide range of fields, including medical research, evolutionary biology, and environmental science. However, discovering new functions largely relies on expensive and exhaustive wet lab experiments. Existing methods of automatic function annotation or prediction mainly focus on protein function prediction with sequence, 3D-structures or protein family information. In this study, we propose to tackle the gene function prediction problem by exploring Gene Ontology graph and annotation with BERT (GoBERT) to decipher the underlying relationships among gene functions. Our proposed novel function prediction task utilizes existing functions as inputs and generalizes the function prediction to gene and gene products. Specifically, two pre-train tasks are designed to jointly train GoBERT to capture both explicit and implicit relations of functions. Neighborhood prediction is a self-supervised multi-label classification task that captures the explicit function relations. Specified masking and recovering task helps GoBERT in finding implicit patterns among functions. The pre-trained GoBERT possess the ability to predict novel functions for various gene and gene products based on known functional annotations. Extensive experiments, biological case studies, and ablation studies are conducted to demonstrate the superiority of our proposed GoBERT.

"What I cannot create, I do not understand."Human wisdom reveals that creation is one of the highest forms of learning. For example, Diffusion Models have demonstrated remarkable semantic structure and memory in image generation, understanding, and restoration, which intuitively benefits representation learning. However, current gait networks rarely embrace this perspective, relying primarily on learning by contrasting gait samples under varying complex conditions, leading to semantic inconsistency and uniformity issues. To address these issues, we propose Origins with generative capabilities whose underlying philosophy is that different entities are generated from a unified template, inherently regularizing gait representations within a consistent and diverse semantic space to capture accurate gait differences. Admittedly, learning this unified template is exceedingly challenging, as it requires the comprehensiveness of the template to encompass gait representations with various conditions. Inspired by Diffusion Models, Origins diffuses the unified template into timestep templates for gait generative learning, and meanwhile transfers the unified template for gait representation learning. Especially, gait generative and representation learning serve as a unified framework for end-to-end joint training. Extensive experiments on CASIA-B, CCPG,SUSTech1K, Gait3D, GREW and CCGR-MINI demonstrate that Origins performs unified generative and representation learning, achieving superior performance.

Exploring chemical space to find novel molecules that simultaneously satisfy multiple properties is crucial in drug discovery. However, existing methods often struggle with trading off multiple properties due to the conflicting or correlated nature of chemical properties. To tackle this issue, we introduce InversionGNN framework, an effective yet sample-efficient dual-path graph neural network (GNN) for multi-objective drug discovery. In the direct prediction path of InversionGNN, we train the model for multi-property prediction to acquire knowledge of the optimal combination of functional groups. Then the learned chemical knowledge helps the inversion generation path to generate molecules with required properties. In order to decode the complex knowledge of multiple properties in the inversion path, we propose a gradient-based Pareto search method to balance conflicting properties and generate Pareto optimal molecules. Additionally, InversionGNN is able to search the full Pareto front approximately in discrete chemical space. Comprehensive experimental evaluations show that InversionGNN is both effective and sample-efficient in various discrete multi-objective settings including drug discovery.

SZ3 (0.07MB, PSNR = 29.2) (c)NeurLZ (0.07MB, PSNR = 39.1)

While recent advancements in supervised gait recognition have yielded promising results, these approaches rely heavily on annotated walking data, limiting their generalizability to complex environments. This paper presents a self-supervised gait recognition framework using human poses as input to address this challenge, focusing on high-quality pretrained data and self-supervised learning strategies. We first introduce StreamGait, a large-scale, unlabelled dataset that captures in-the-wild distributions of walking sequences. This dataset is curated from Internet livestreams across diverse geographic and environmental scenarios, reflecting variations in real-world camera angles, weather, and pedestrian behavior. Our framework, MirrorGait, conducts self-supervised learning by integration with 2D-to-3D pose reconstruction to synthesize multi-view perspectives for effective 3D-aware contrastive learning. With specific designs of temporal position embedding and gait partition head on a Transformer backbone, the encoder can readily adapt to the periodic and fine-grained nature of gait. Extensive experiments on three widely used gait datasets, Gait3D, GREW, and OUMVLP-Pose, demonstrate that our method, with minimal fine-tuning on the pretrained model, achieves state-of-the-art performance among pose-based gait recognition approaches. The dataset, code, and models are available at https://github.com/BNU-IVC/StreamGait.

Molecular property prediction aims to learn representations that map chemical structures to functional properties. While multimodal learning has emerged as a powerful paradigm to learn molecular representations, prior works have largely overlooked textual and taxonomic information of molecules for representation learning. We introduce TRIDENT, a novel framework that integrates molecular SMILES, textual descriptions, and taxonomic functional annotations to learn rich molecular representations. To achieve this, we curate a comprehensive dataset of molecule-text pairs with structured, multi-level functional annotations. Instead of relying on conventional contrastive loss, TRIDENT employs a volume-based alignment objective to jointly align tri-modal features at the global level, enabling soft, geometry-aware alignment across modalities. Additionally, TRIDENT introduces a novel local alignment objective that captures detailed relationships between molecular substructures and their corresponding sub-textual descriptions. A momentum-based mechanism dynamically balances global and local alignment, enabling the model to learn both broad functional semantics and fine-grained structure-function mappings. TRIDENT achieves state-of-the-art performance on 18 downstream tasks, demonstrating the value of combining SMILES, textual, and taxonomic functional annotations for molecular property prediction. Our code and data are available at https://github.com/uta-smile/TRIDENT.

daptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.

Hypergraph-based modeling has gained significant attention for capturing complex higher-order interactions among vertices. While random walks serve as fundamental tools for analyzing hypergraphs, existing approaches either fail to fully leverage edge-dependent vertex weights (EDVWs) or lack sufficient expressiveness to model intricate hypergraph structures. To address these limitations, we propose a unified random walk framework that integrates hyperedge degrees and vertex weights, offering a more robust approach to hypergraph modeling. We establish equivalence conditions between hypergraph and graph random walks, leading to a novel unified random-walk-based hypergraph Laplacian that incorporates EDVWs, ensuring expressiveness and desirable spectral properties. Building on this foundation, we introduce the General Hypergraph Spectral Convolution (GHSC) framework, which extends existing Graph Convolutional Neural Networks (GCNNs) for effective hypergraph learning, supporting both edge-independent and edge-dependent vertex weights. Extensive experiments across diverse datasets, including citation networks, visual objects, and protein modeling tasks, demonstrate state-of-the-art performance, with notable improvements in protein structure modeling using EDVW-hypergraphs. This work advances the theoretical understanding of hypergraph random walks and spectral theory while providing a versatile framework for deep hypergraph learning. Code is available at GHSC_H_GNNs.

Learning with noisy labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have a "small loss." However, this assumption often fails to generalize to some real-world cases with imbalanced subpopulations, that is, training subpopulations that vary in sample size or recognition difficulty. Therefore, recent LNL methods face the risk of misclassifying those "informative" samples (e.g., hard samples or samples in the tail subpopulations) into noisy samples, leading to poor generalization performance. To address this issue, we propose a novel LNL method to deal with noisy labels and imbalanced subpopulations simultaneously. It first leverages sample correlation to estimate samples' clean probabilities for label correction and then utilizes corrected labels for distributionally robust optimization (DRO) to further improve the robustness. Specifically, in contrast to previous works using classification loss as the selection criterion, we introduce a feature-based metric that takes the sample correlation into account for estimating samples' clean probabilities. Then, we refurbish the noisy labels using the estimated clean probabilities and the pseudo-labels from the model's predictions. With refurbished labels, we use DRO to train the model to be robust to subpopulation imbalance. Extensive experiments on a wide range of benchmarks demonstrate that our technique can consistently improve state-of-the-art (SOTA) robust learning paradigms against noisy labels, especially when encountering imbalanced subpopulations. We provide our code in https://github.com/chenmc1996/LNL-IS.

In the rapidly evolving field of AI research, foundational models like BERT and GPT have significantly advanced language and vision tasks. The advent of pretrain-prompting models, such as ChatGPT and segment anything model (SAM), has further revolutionized image segmentation. However, their applications in specialized areas, particularly in nuclei segmentation within medical imaging, reveal a key challenge: the generation of high-quality, informative prompts is as crucial as applying state-of-the-art (SOTA) fine-tuning techniques on foundation models. To address this, we introduce segment any cell (SAC), an innovative framework that enhances SAM specifically for nuclei segmentation. SAC integrates a low-rank adaptation (LoRA) within the attention layer of the Transformer to improve the fine-tuning process, outperforming existing SOTA methods. It also introduces an innovative auto-prompt generator that produces effective prompts to guide segmentation, a critical factor in handling the complexities of nuclei segmentation in biomedical imaging. Our extensive experiments demonstrate the superiority of SAC in nuclei segmentation tasks, proving its effectiveness as a tool for pathologists and researchers. Our contributions include a novel prompt generation strategy, automated adaptability for diverse segmentation tasks, the innovative application of low-rank attention adaptation in SAM, and a versatile framework for semantic and instance segmentation challenges.

Recently, generative models based on the diffusion process have emerged as a promising direction for automating the design of molecules. However, directly adding continuous Gaussian noise to discrete graphs leads to the problem that the generated data do not conform to the discrete graph data distribution in the training set. Current graph diffusion models either corrupt discrete data through a transition matrix or relax the discrete data to continuous space for the diffusion process. These approaches make it hard to perform extensible conditional generation, such as adapting to text-based conditions, due to the lack of embedding representations and require significant computation resources due to the diffusion process of the bond type matrix. This paper introduces the Hierarchical Graph Latent Diffusion Model (HGLDM), a novel variant of latent diffusion models that overcomes the problem of applying continuous diffusion models directly to discrete graph data. Meanwhile, based on the latent diffusion framework, HGLDM avoids the issues of computational consumption and lack of embeddings for extensible conditional generation. In addition, by comparing the HGLDM with its variant, the Graph Latent Diffusion Model (GLDM), which only has graph-level embeddings, we validate the advantage of the hierarchical graph structure for capturing the relationship between structure information and molecular properties. We evaluate the performance of our model through various conditional generation tasks, demonstrating its superior performance.

Combinatorial medication recommendation (CMR) is a fundamental task of healthcare, which offers opportunities for clinical physicians to provide more precise prescriptions for patients with intricate health conditions, particularly in the scenarios of long-term medical care. Previous research efforts have sought to extract meaningful information from electronic health records (EHRs) to facilitate combinatorial medication recommendations. Existing learning-based approaches further consider the chemical structures of medications, but ignore the textual medication descriptions in which the functionalities are clearly described. Furthermore, the textual knowledge derived from the EHRs of patients remains largely underutilized. To address these issues, we introduce the Natural Language-Assisted Multi-modal Medication Recommendation (NLA-MMR), a multimodal alignment framework designed to learn knowledge from the patient view and medication view jointly. Specifically, NLA-MMR formulates CMR as an alignment problem from patient and medication modalities. In this vein, we employ pretrained language models (PLMs) to extract in-domain knowledge regarding patients and medications, serving as the foundational representation for both modalities. In the medication modality, we exploit both chemical structures and textual descriptions to create medication representations. In the patient modality, we generate the patient representations based on textual descriptions of diagnosis, procedure, and symptom. Extensive experiments conducted on three publicly accessible datasets demonstrate that NLA-MMR achieves new state-of-the-art performance, with a notable average improvement of 4.72% in Jaccard score.

Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://github.com/richard-peng-xia/CARES.

Vision-language models have been widely explored across a wide range of tasks and achieve satisfactory performance. However, it’s under-explored how to consolidate entity understanding through a varying number of images and to align it with the pre-trained language models for generative tasks. In this paper, we propose MIVC, a general multiple instance visual component to bridge the gap between various image inputs with off-the-shelf vision-language models by aggregating visual representations in a permutation-invariant fashion through a neural network. We show that MIVC could be plugged into the visual-language models to improve the model performance consistently on visual question answering, classification and captioning tasks on a public available e-commerce dataset with multiple images per product. Furthermore, we show that the component provides insight into the contribution of each image to the downstream tasks.

The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR-epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR-epitope interaction networks. In this study, we present $GTE$, a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR-epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR-epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE.

MOTIVATION: Retrosynthesis is a critical task in drug discovery, aimed at finding a viable pathway for synthesizing a given target molecule. Many existing approaches frame this task as a graph-generating problem. Specifically, these methods first identify the reaction center, and break a targeted molecule accordingly to generate the synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or by directly adding appropriate leaving groups. However, both of these strategies have limitations. Adding atoms results in a long prediction sequence that increases the complexity of generation, while adding leaving groups only considers those in the training set, which leads to poor generalization. RESULTS: In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants. Given that chemically meaningful motifs fall between the size of atoms and leaving groups, our model achieves lower prediction complexity than adding atoms and demonstrates superior performance than adding leaving groups. We evaluate our proposed model on a benchmark dataset and show that it significantly outperforms previous state-of-the-art models. Furthermore, we conduct ablation studies to investigate the contribution of each component of our proposed model to the overall performance on benchmark datasets. Experiment results demonstrate the effectiveness of our model in predicting retrosynthesis pathways and suggest its potential as a valuable tool in drug discovery. AVAILABILITY AND IMPLEMENTATION: All code and data are available at https://github.com/szu-ljh2020/MARS.

The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack of interpretation for prediction results, impede further development of GCN. One solution is to recognize a predictive yet compressed subgraph to get rid of the noise and redundancy and obtain the interpretable part of the graph. This setting of subgraph is similar to the information bottleneck (IB) principle, which is less studied on graph-structured data and GCN. Inspired by the IB principle, we propose a novel subgraph information bottleneck (SIB) framework to recognize such subgraphs, named IB-subgraph. However, the intractability of mutual information and the discrete nature of graph data makes the objective of SIB notoriously hard to optimize. To this end, we introduce a bilevel optimization scheme coupled with a mutual information estimator for irregular graphs. Moreover, we propose a continuous relaxation for subgraph selection with a connectivity loss for stabilization. We further theoretically prove the error bound of our estimation scheme for mutual information and the noise-invariant nature of IB-subgraph. Extensive experiments on graph learning and large-scale point cloud tasks demonstrate the superior property of IB-subgraph.

Cervical cytology is a critical screening strategy for early detection of pre-cancerous and cancerous cervical lesions. The challenge lies in accurately classifying various cervical cytology cell types. Existing automated cervical cytology methods are primarily trained on databases covering a narrow range of coarse-grained cell types, which fail to provide a comprehensive and detailed performance analysis that accurately represents real-world cytopathology conditions. To overcome these limitations, we introduce HiCervix, the most extensive, multi-center cervical cytology dataset currently available to the public. HiCervix includes 40,229 cervical cells from 4,496 whole slide images, categorized into 29 annotated classes. These classes are organized within a three-level hierarchical tree to capture fine-grained subtype information. To exploit the semantic correlation inherent in this hierarchical tree, we propose HierSwin, a hierarchical vision transformer-based classification network. HierSwin serves as a benchmark for detailed feature learning in both coarse-level and fine-level cervical cancer classification tasks. In our comprehensive experiments, HierSwin demonstrated remarkable performance, achieving 92.08% accuracy for coarse-level classification and 82.93% accuracy averaged across all three levels. When compared to board-certified cytopathologists, HierSwin achieved high classification performance (0.8293 versus 0.7359 averaged accuracy), highlighting its potential for clinical applications. This newly released HiCervix dataset, along with our benchmark HierSwin method, is poised to make a substantial impact on the advancement of deep learning algorithms for rapid cervical cancer screening and greatly improve cancer prevention and patient outcomes in real-world clinical settings.

It has been discovered that graph convolutional networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in oversmoothing, which isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. In this article, we start by investigating refined measures upon DropEdge-an existing simple yet effective technique to relieve oversmoothing. We term our method as DropEdge++ for its two structure-aware samplers in contrast to DropEdge: layer-dependent (LD) sampler and feature-dependent (FD) sampler. Regarding the LD sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge. We theoretically reveal this phenomenon with mean-edge-number (MEN), a metric closely related to oversmoothing. For the FD sampler, we associate the edge sampling probability with the feature similarity of node pairs and prove that it further correlates the convergence subspace of the output layer with the input features. Extensive experiments on several node classification benchmarks, including both full- and semi-supervised tasks, illustrate the efficacy of DropEdge++ and its compatibility with a variety of backbones by achieving generally better performance over DropEdge and the no-drop version.

AI-aided drug discovery (AIDD) is gaining popularity due to its potential to make the search for new pharmaceuticals faster, less expensive, and more effective. Despite its extensive use in numerous fields (e.g., ADMET prediction, virtual screening), little research has been conducted on the out-of-distribution (OOD) learning problem with noise. We present DrugOOD, a systematic OOD dataset curator and benchmark for AIDD. Particularly, we focus on the drug-target binding affinity prediction problem, which involves both macromolecule (protein target) and small-molecule (drug compound). DrugOOD offers an automated dataset curator with user-friendly customization scripts, rich domain annotations aligned with biochemistry knowledge, realistic noise level annotations, and rigorous benchmarking of SOTA OOD algorithms, as opposed to only providing fixed datasets. Since the molecular data is often modeled as irregular graphs using graph neural network (GNN) backbones, DrugOOD also serves as a valuable testbed for graph OOD learning problems. Extensive empirical studies have revealed a significant performance gap between in-distribution and out-of-distribution experiments, emphasizing the need for the development of more effective schemes that permit OOD generalization under noise for AIDD.

Traditionally, catalog relationship problems in e-commerce stores have been handled as pairwise classification tasks, which limit the ability of machine learning models to learn from the diverse relationships among different entities in the catalog. In this paper, we leverage heterogeneous graphs and Graph Neural Networks (GNNs) for improving catalog relationship inference. We start from investigating how to create multi-entity, multi-relationship graphs from diverse relationship data sources, and then explore how to utilizing GNNs to leverage the knowledge of the constructed graph in a self-supervised fashion. We finally propose a distillation approach to transfer the knowledge learned by GNNs into a pairwise neural network for seamless deployment in the catalog pipeline that relies on pairwise input for inductive relationship inference. Our experiments exhibit that in two of the representative catalog relationship problems, Title Authority/Contributor Authority and Broken Variation, the proposed framework is able to improve the recall at 95% precision of a pairwise baseline by up to 33.6% and 14.0%, respectively. Our findings highlight the effectiveness of this approach in advancing catalog quality maintenance and accurate relationship modeling, with potential for broader industry adoption.

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities.

The performance of deep learning models heavily relies on the quality of the training data. Inadequacies in the training data, such as corrupt input or noisy labels, can lead to the failure of model generalization. Recent studies propose repairing the model by identifying the training samples that contribute to the failure and removing their influence from the model. However, it is important to note that the identified data may contain both beneficial and detrimental information. Simply erasing the information of the identified data from the model can have a negative impact on its performance, especially when accurate data is mistakenly identified as detrimental and removed. To overcome this challenge, we propose a novel approach that leverages the knowledge obtained from a retained clean set. Our method first identifies harmful data by utilizing the clean set, then separates the beneficial and detrimental information within the identified data. Finally, we utilize the extracted beneficial information to enhance the model's performance. Through empirical evaluations, we demonstrate that our method outperforms baseline approaches in both identifying harmful data and rectifying model failures. Particularly in scenarios where identification is challenging and a significant amount of benign data is involved, our method improves performance while the baselines deteriorate due to the erroneous removal of beneficial information.

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learnt from a labeled source domain to an unlabeled target domain. Previous work is mainly built upon convolutional neural networks (CNNs) to learn domain-invariant representations. With the recent exponential increase in applying Vision Transformer (ViT) to vision tasks, the capability of ViT in adapting cross-domain knowledge, however, remains unexplored in the literature. To fill this gap, this paper first comprehensively investigates the performance of ViT on a variety of domain adaptation tasks. Surprisingly, ViT demonstrates superior generalization ability, while the performance can be further improved by incorporating adversarial adaptation. Notwithstanding, directly using CNNs-based adaptation strategies fails to take the advantage of ViT’s intrinsic merits (e.g., attention mechanism and sequential image representation) which play an important role in knowledge transfer. To remedy this, we propose an unified framework, namely Transferable Vision Transformer (TVT), to fully exploit the transferability of ViT for domain adaptation. Specifically, we delicately devise a novel and effective unit, which we term Transferability Adaption Module (TAM). By injecting learned trans- ferabilities into attention blocks, TAM compels ViT focus on both transferable and discriminative features. Besides, we leverage discriminative clustering to enhance feature diversity and separation which are undermined during adversarial domain alignment. To verify its versatility, we perform extensive studies of TVT on four benchmarks and the experimental results demonstrate that TVT attains significant improvements compared to existing state-of-the-art UDA methods.

Despite the success of graph neural networks (GNNs) over the Web in recent years, the typical transductive learning setting for node classification requires GNNs to be retrained frequently, making them vulnerable to poisoning attacks by corrupting the training graph. Poisoning attacks on graphs are, however, non-trivial as the attack space is potentially large, and the discrete graph structure makes the poisoning function non-differentiable. In this paper, we revisit the bi-level optimization problem in graph poisoning and propose a novel graph poisoning method, termed Curriculum Graph Poisoning (CuGPo), inspired by curriculum learning. In contrast to other poisoning attacks that use heuristics or directly optimize the graph, our method learns to generate poisoned graphs from basic adversarial knowledge first and advanced knowledge later. Specifically, for the outer optimization, we utilize the slightly perturbed graphs which represent the easy poisoning task at the beginning, and then enlarge the attack space until the final; for the inner optimization, we firstly exploit the knowledge from the clean graph and then adapt quickly to perturbed graphs to obtain the adversarial knowledge. Extensive experiments demonstrate that CuGPo achieves state-of-the-art performance in graph poisoning attacks.

The rich content in various real-world networks such as social networks, biological networks, and communication networks provides unprecedented opportunities for unsupervised machine learning on graphs. This paper investigates the fundamental problem of preserving and extracting abundant information from graph-structured data into embedding space without external supervision. To this end, we generalize conventional mutual information computation from vector space to graph domain and present a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graph and hidden representation. Except for standard GMI which considers graph structures from a local perspective, our further proposed GMI++ additionally captures global topological properties by analyzing the co-occurrence relationship of nodes. GMI and its extension exhibit several benefits: First, they are invariant to the isomorphic transformation of input graphs-an inevitable constraint in many existing methods; Second, they can be efficiently estimated and maximized by current mutual information estimation methods; Lastly, our theoretical analysis confirms their correctness and rationality. With the aid of GMI, we develop an unsupervised embedding model and adapt it to the specific anomaly detection task. Extensive experiments indicate that our GMI methods achieve promising performance in various downstream tasks, such as node classification, link prediction, and anomaly detection.

With the success of the graph embedding model in both academic and industry areas, the robustness of graph embedding against adversarial attack inevitably becomes a crucial problem in graph learning. Existing works usually perform the attack in a white-box fashion: they need to access the predictions/labels to construct their adversarial loss. However, the inaccessibility of predictions/labels makes the white-box attack impractical for a real graph learning system. This paper promotes current frameworks in a more general and flexible sense -- we consider the ability of various types of graph embedding models to remain resilient against black-box driven attacks. We investigate the theoretical connection between graph signal processing and graph embedding models, and formulate the graph embedding model as a general graph signal process with a corresponding graph filter. Therefore, we design a generalized adversarial attack framework: GF-Attack. Without accessing any labels and model predictions, GF-Attack can perform the attack directly on the graph filter in a black-box fashion. We further prove that GF-Attack can perform an effective attack without assumption on the number of layers/window-size of graph embedding models. To validate the generalization of GF-Attack, we construct GF-Attack on five popular graph embedding models. Extensive experiments validate the effectiveness of GF-Attack on several benchmark datasets.

Finding critical users in social networks is an important issue. The criticalness of a user can be measured by the number of followers who will leave the community together when the user leaves. By taking a social community as a k-core, the problem of finding critical users is to find a set of nodes, U, of size b in a k-core that maximizes the number of nodes to be deleted from the k-core when all nodes in U are deleted. This problem is NP-hard. The state-of-the-art greedy algorithm is with no guarantee on the set of nodes U found. In this paper, we propose a neural network model, called Self-attentive Core Graph Convolution Network (SCGCN), to capture the hidden structure of the criticalness among node combinations that break the engagement of a specific social community. Supervised by sampling node combinations, SCGCN has the ability to inference the criticalness of unseen combinations of nodes. To further reduce the sampling and inference space, we propose a deterministic strategy to prune unpromising nodes on the graph. Our experiments conducted on many real-world graphs show that SCGCN significantly improves the quality of the solution compared with the state-of-the-art greedy algorithm.

Retrosynthetic planning plays an important role in the field of organic chemistry, which could generate a synthetic route for the target product. The synthetic route is a series of reactions which are started from the available molecules. The most challenging problem in the generation of the synthetic route is the large search space of the candidate reactions. Estimating the cost of candidate reactions has been proved effectively to prune the search space, which could achieve a higher accuracy with the same search iteration. And the estimation of one reaction is comprised of the estimations of all its reactants. So, how to estimate the cost of these reactants will directly influence the quality of results. To get a better performance, we propose a new framework, named GNN-Retro, for retrosynthetic planning problem by combining graph neural networks(GNN) and the latest search algorithm. The structure of GNN in our framework could incorporate the information of neighboring molecules, which will improve the estimation accuracy of our framework. The experiments on the USPTO dataset show that our framework could outperform the state-of-the-art methods with a large margin under the same settings.

The protein tertiary structure largely determines its interaction with other molecules. Despite its importance in various structure-related tasks, fully-supervised data are often time-consuming and costly to obtain. Existing pre-training models mostly focus on amino-acid sequences or multiple sequence alignments, while the structural information is not yet exploited. In this paper, we propose a self-supervised pre-training model for learning structure embeddings from protein tertiary structures. Native protein structures are perturbed with random noise, and the pre-training model aims at estimating gradients over perturbed 3D structures. Specifically, we adopt SE(3)-invariant features as model inputs and reconstruct gradients over 3D coordinates with SE(3)-equivariance preserved. Such paradigm avoids the usage of sophisticated SE(3)-equivariant models, and dramatically improves the computational efficiency of pre-training models. We demonstrate the effectiveness of our pre-training model on two downstream tasks, protein structure quality assessment (QA) and protein-protein interaction (PPI) site prediction. Hierarchical structure embeddings are extracted to enhance corresponding prediction models. Extensive experiments indicate that such structure embeddings consistently improve the prediction accuracy for both downstream tasks.

3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models (SSMs) that imposed anatomical constraints and produced high quality surfaces were a core technology. Today’s fully-convolutional networks (FCNs), while dominant, do not offer these capabilities. We present deep implicit statistical shape models (DISSMs), a new approach that marries the representation power of deep networks with the benefits of SSMs. DISSMs use an implicit representation to produce compact and descriptive deep surface embeddings that permit statistical models of anatomical variance. To reliably fit anatomically plausible shapes to an image, we introduce a novel rigid and non-rigid pose estimation pipeline that is modelled as a Markov decision process (MDP). Intra-dataset experiments on the task of pathological liver segmentation demonstrate that DISSMs can perform more robustly than four leading FCN models, including nnU-Net + an adversarial prior: reducing the mean Hausdorff distance (HD) by 7.5-14.3 mm and improving the worst case Dice-Sørensen coefficient (DSC) by 1.2-2.3%. More critically, cross-dataset experiments on an external and highly challenging clinical dataset demonstrate that DISSMs improve the mean DSC and HD by 2.1-5.9% and 9.9-24.5 mm, respectively, and the worst-case DSC by 5.4-7.3%. Supplemental validation on a highly challenging and low-contrast larynx dataset further demonstrate DISSM’s improvements. These improvements are over and above any benefits from representing delineations with high-quality surfaces.

The large-scale whole-slide images (WSIs) facilitate the learning-based computational pathology methods. However, the gigapixel size of WSIs makes it hard to train a conventional model directly. Current approaches typically adopt multiple-instance learning (MIL) to tackle this problem. Among them, MIL combined with graph convolutional network (GCN) is a significant branch, where the sampled patches are regarded as the graph nodes to further discover their correlations. However, it is difficult to build correspondence across patches from different WSIs. Therefore, most methods have to perform non-ordered node pooling to generate the bag-level representation. Direct non-ordered pooling will lose much structural and contextual information, such as patch distribution and heterogeneous patterns, which is critical for WSI representation. In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution. We first deploy a global clustering operation based on the instance features in the dataset to build the correspondence across different WSIs. Then, we perform a local clustering-based sampling strategy to select typical instances belonging to each cluster within the WSI. Finally, we employ the graph convolution to obtain the representation. Since our graph construction strategy ensures the alignment among different WSIs, WSI-level representation can be easily generated and used for the subsequent classification. The experiment results on two cancer subtype classification datasets demonstrate our method achieves better performance compared with the state-of-the-art methods.

Integration of heterogeneous and high-dimensional data (e.g., multiomics) is becoming increasingly important. Existing multimodal classification algorithms mainly focus on improving performance by exploiting the complementarity from different modalities. However, conventional approaches are basically weak in providing trustworthy multimodal fusion, especially for safety-critical applications (e.g., medical diagnosis). For this issue, we propose a novel trustworthy multimodal classification algorithm termed Multimodal Dynamics, which dynamically evaluates both the feature-level and modality-level informativeness for different samples and thus trustworthily integrates multiple modalities. Specifically, a sparse gating is introduced to capture the information variation of each within-modality feature and the true class probability is employed to assess the classification confidence of each modality. Then a transparent fusion algorithm based on the dynamical informativeness estimation strategy is induced. To the best of our knowledge, this is the first work to jointly model both feature and modality variation for different samples to provide trustworthy fusion in multi-modal classification. Extensive experiments are conducted on multimodal medical classification datasets. In these experiments, superior performance and trustworthiness of our algorithm are clearly validated compared to the state-of-the-art methods.

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information (MI) between an image and its matched text. However, simply performing cross-modal alignment (CMA) ignores data potential within each modality, which may result in degraded representations. For instance, although CMA-based models are able to map image-text pairs close together in the embedding space, they fail to ensure that similar inputs from the same modality stay close by. This problem can get even worse when the pre-training data is noisy. In this paper, we propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning. To take advantage of localized and structural information from image and text input, TCL further maximizes the average MI between local regions of image/text and their global summary. To the best of our knowledge, ours is the first work that takes into account local structure information for multi-modality representation learning. Experimental evaluations show that our approach is competitive and achieves the new state of the art on various common downstream vision-language tasks such as image-text retrieval and visual question answering.

Finding critical users whose existence keeps a social community cohesive is an important problem in social networks. Considering a k-core community, finding critical users is to find a set of nodes U, with a given size b, in the community that maximizes the number of nodes to be deleted when nodes$U$are deleted. The problem is NP-complete. The state-of-the-art algorithm is a greedy algorithm without a performance guaran-tee. To improve the performance, we propose a novel learning-based heuristic. A neural network model, Self-attentive Core Graph Convolution Network, SCGCN is learned for inference the criticalness of unseen node combinations. Furthermore, to reduce the inference space, we propose a deterministic strategy to prune unpromising nodes. Our experiments show that SCGCN signifi-cantly improves the quality of the solutions compared with the state-of-the-art algorithms.

Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer. Existing estimation algorithms either require intensive training on target tasks or have difficulties in evaluating the transferability between layers. To this end, we propose a simple, efficient, and effective transferability measure named TransRate. Through a single pass over examples of a target task, TransRate measures the transferability as the mutual information between features of target examples extracted by a pre-trained model and their labels. We overcome the challenge of efficient mutual information estimation by resorting to coding rate that serves as an effective alternative to entropy. From the perspective of feature representation, the resulting TransRate evaluates both completeness (whether features contain sufficient information of a target task) and compactness (whether features of each class are compact enough for good generalization) of pre-trained features. Theoretically, we have analyzed the close connection of TransRate to the performance after transfer learning. Despite its extraordinary simplicity in 10 lines of codes, TransRate performs remarkably well in extensive evaluations on 35 pre-trained models and 16 downstream tasks.

Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating information from local neighborhoods. However, it remains an open question whether the neighborhood information is adequately aggregated for learning representations of nodes with few neighbors. To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node representations of the neighbors conditioned on the central node’s representation and enhance GNN’s expressive power with generated features. Local augmentation is a general framework that can be applied to any GNN model in a plug-and-play manner. It samples feature vectors associated with each node from the learned conditional distribution as additional input for the backbone model at each training iteration. Extensive experiments and analyses show that local augmentation consistently yields performance improvement when applied to various GNN architectures across a diverse set of benchmarks. For example, experiments show that plugging in local augmentation to GCN and GAT improves by an average of 3.4% and 1.6% in terms of test accuracy on Cora, Citeseer, and Pubmed. Besides, our experimental results on large graphs (OGB) show that our model consistently improves performance over backbones. Code is available at https://github.com/SongtaoLiu0823/LAGNN.

Learning good representation of giga-pixel level whole slide pathology images (WSI) for downstream tasks is critical. Previous studies employ multiple instance learning (MIL) to represent WSIs as bags of sampled patches because, for most occasions, only slide-level labels are available, and only a tiny region of the WSI is disease-positive area. However, WSI representation learning still remains an open problem due to: (1) patch sampling on a higher resolution may be incapable of depicting microenvironment information such as the relative position between the tumor cells and surrounding tissues, while patches at lower resolution lose the fine-grained detail; (2) extracting patches from giant WSI results in large bag size, which tremendously increases the computational cost. To solve the problems, this paper proposes a hierarchical-based multimodal transformer framework that learns a hierarchical mapping between pathology images and corresponding genes. Precisely, we randomly extract instant-level patch features from WSIs with different magnification. Then a co-attention mapping between imaging and genomics is learned to uncover the pairwise interaction and reduce the space complexity of imaging features. Such early fusion makes it computationally feasible to use MIL Transformer for the survival prediction task. Our architecture requires fewer GPU resources compared with benchmark methods while maintaining better WSI representation ability. We evaluate our approach on five cancer types from the Cancer Genome Atlas database and achieved an average c-index of 0.673, outperforming the state-of-the-art multimodality methods.

Deep graph learning (DGL) has achieved remarkable progress in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite the progress, how to ensure various DGL algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning which mainly cares about model performance, TwGL considers various reliability and safety aspects of DGL, including but not limited to adversarial robustness, explainability, and privacy protection. Whilst several previous tutorials have been made for the introduction of DGL in KDD, seldom is there a special focus on its safety aspects, including reliability, explainability, and privacy protection capability. This tutorial mainly covers the key achievements of trustworthy graph learning in recent years. Specifically, we will discuss three essential topics, that is, the reliability of DGL against inherent noise, distribution shift and adversarial attack, explainability methods, and privacy protection for DGL. Meanwhile, we will introduce some guidelines for applying DGL to risk-sensitive applications (e.g., AI drug discovery) to ensure GNN models behave in a trustworthy way. We hope our tutorial can offer a comprehensive review of recent advances in this area and also provide some useful suggestions to guide the developers to choose appropriate techniques for their applications.

Weakly-supervised whole-slide image (WSI) classification (WSWC) is a challenging task where a large number of unlabeled patches (instances) exist within each WSI (bag) while only a slide label is given. Despite recent progress for the multiple instance learning (MIL)-based WSI analysis, the major limitation is that it usually focuses on the easy-to-distinguish diagnosis-positive regions while ignoring positives that occupy a small ratio in the entire WSI. To obtain more discriminative features, we propose a novel weakly-supervised classification method based on cross-slide contrastive learning (called SCL-WC), which depends on task-agnostic self-supervised feature pre-extraction and task-specific weakly-supervised feature refinement and aggregation for WSI-level prediction. To enable both intra-WSI and inter-WSI information interaction, we propose a positive-negative-aware module (PNM) and a weakly-supervised cross-slide contrastive learning (WSCL) module, respectively. The WSCL aims to pull WSIs with the same disease types closer and push different WSIs away. The PNM aims to facilitate the separation of tumor-like patches and normal ones within each WSI. Extensive experiments demonstrate state-of-the-art performance of our method in three different classification tasks (e.g., over 2% of AUC in Camelyon16, 5% of F1 score in BRACS, and 3% of AUC in DiagSet). Our method also shows superior flexibility and scalability in weakly-supervised localization and semi-supervised classification experiments (e.g., first place in the BRIGHT challenge). Our code will be available at https://github.com/Xiyue-Wang/SCL-WC.

Click-Through Rate (CTR) prediction, which aims to estimate the probability that a user will click an item, is an essential component of online advertising. Existing methods mainly attempt to mine user interests from users' historical behaviours, which contain users' directly interacted items. Although these methods have made great progress, they are often limited by the recommender system's direct exposure and inactive interactions, and thus fail to mine all potential user interests. To tackle these problems, we propose Neighbor-Interaction based CTR prediction (NI-CTR), which considers this task under a Heterogeneous Information Network (HIN) setting. In short, Neighbor-Interaction based CTR prediction involves the local neighborhood of the target user-item pair in the HIN to predict their linkage. In order to guide the representation learning of the local neighbourhood, we further consider different kinds of interactions among the local neighborhood nodes from both explicit and implicit perspective, and propose a novel Graph-Masked Transformer (GMT) to effectively incorporates these kinds of interactions to produce highly representative embeddings for the target user-item pair. Moreover, in order to improve model robustness against neighbour sampling, we enforce a consistency regularization loss over the neighbourhood embedding. We conduct extensive experiments on two real-world datasets with millions of instances and the experimental results show that our proposed method outperforms state-of-the-art CTR models significantly. Meanwhile, the comprehensive ablation studies verify the effectiveness of every component of our model. Furthermore, we have deployed this framework on the WeChat Official Account Platform with billions of users. The online A/B tests demonstrate an average CTR improvement of 21.9% against all online baselines.

Fake News detection has attracted much attention in recent years. Social context based detection methods attempt to model the spreading patterns of fake news by utilizing the collective wisdom from users on social media. This task is challenging for three reasons: (1) There are multiple types of entities and relations in social context, requiring methods to effectively model the heterogeneity. (2) The emergence of news in novel topics in social media causes distribution shifts, which can significantly degrade the performance of fake news detectors. (3) Existing fake news datasets usually lack of great scale, topic diversity and user social relations, impeding the development of this field. To solve these problems, we formulate social context based fake news detection as a heterogeneous graph classification problem, and propose a fake news detection model named Post-User Interaction Network (PSIN), which adopts a divide-and-conquer strategy to model the post-post, user-user and post-user interactions in social context effectively while maintaining their intrinsic characteristics. Moreover,we adopt an adversarial topic discriminator for topic-agnostic feature learning, in order to improve the generalizability of our method for new-emerging topics. Furthermore, we curate a new dataset for fake news detection, which contains over 27,155 news from 5 topics, 5 million posts, 2 million users and their induced social graph with 0.2 billion edges. It has been published on https://github.com/qwerfdsaplking/MC-Fake. Extensive experiments illustrate that our method outperforms SOTA baselines in both in-topic and out-of-topic settings.

MOTIVATION: The crux of molecular property prediction is to generate meaningful representations of the molecules. One promising route is to exploit the molecular graph structure through graph neural networks (GNNs). Both atoms and bonds significantly affect the chemical properties of a molecule, so an expressive model ought to exploit both node (atom) and edge (bond) information simultaneously. Inspired by this observation, we explore the multi-view modeling with GNN (MVGNN) to form a novel paralleled framework, which considers both atoms and bonds equally important when learning molecular representations. In specific, one view is atom-central and the other view is bond-central, then the two views are circulated via specifically designed components to enable more accurate predictions. To further enhance the expressive power of MVGNN, we propose a cross-dependent message-passing scheme to enhance information communication of different views. The overall framework is termed as CD-MVGNN. RESULTS: We theoretically justify the expressiveness of the proposed model in terms of distinguishing non-isomorphism graphs. Extensive experiments demonstrate that CD-MVGNN achieves remarkably superior performance over the state-of-the-art models on various challenging benchmarks. Meanwhile, visualization results of the node importance are consistent with prior knowledge, which confirms the interpretability power of CD-MVGNN. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this work are available in GitHub at https://github.com/uta-smile/CD-MVGNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction. RESULTS: To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding. AVAILABILITYAND IMPLEMENTATION: The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN.

Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data. However, such latent distribution may incur difficulties in data sampling for GAN methods. In this paper, rather than sampling from the predefined prior distribution, we propose a GAN model with local coordinate coding (LCC), termed LCCGAN, to improve the performance of the image generation. First, we propose an LCC sampling method in LCCGAN to sample meaningful points from the latent manifold. With the LCC sampling method, we can explicitly exploit the local information on the latent manifold and thus produce new data with promising quality. Second, we propose an improved version, namely LCCGAN++, by introducing a higher-order term in the generator approximation. This term is able to achieve better approximation and thus further improve the performance. More critically, we derive the generalization bound for both LCCGAN and LCCGAN++ and prove that a low-dimensional input is sufficient to achieve good generalization performance. Extensive experiments on several benchmark datasets demonstrate the superiority of the proposed method over existing GAN methods.

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods. However, even a well-designed/searched architecture may still contain many nonsignificant or redundant modules/operations (e.g., some intermediate convolution or pooling layers). Such redundancy may not only incur substantial memory consumption and computational cost but also deteriorate the performance. Thus, it is necessary to optimize the operations inside an architecture to improve the performance without introducing extra computational cost. To this end, we have proposed a Neural Architecture Transformer (NAT) method which casts the optimization problem into a Markov Decision Process (MDP) and seeks to replace the redundant operations with more efficient operations, such as skip or null connection. Note that NAT only considers a small number of possible replacements/transitions and thus comes with a limited search space. As a result, such a small search space may hamper the performance of architecture optimization. To address this issue, we propose a Neural Architecture Transformer++ (NAT++) method which further enlarges the set of candidate transitions to improve the performance of architecture optimization. Specifically, we present a two-level transition rule to obtain valid transitions, i.e., allowing operations to have more efficient types (e.g., convolution → separable convolution) or smaller kernel sizes (e.g., 5×5 → 3×3). Note that different operations may have different valid transitions. We further propose a Binary-Masked Softmax (BMSoftmax) layer to omit the possible invalid transitions. Last, based on the MDP formulation, we apply policy gradient to learn an optimal policy, which will be used to infer the optimized architectures. Extensive experiments show that the transformed architectures significantly outperform both their original counterparts and the architectures optimized by existing methods.

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. To this end, we first introduce additional discrimination-aware losses into the network to increase the discriminative power of the intermediate layers. Next, we select the most discriminative channels for each layer by considering the discrimination-aware loss and the reconstruction error, simultaneously. We then formulate channel pruning as a sparsity-inducing optimization problem with a convex objective and propose a greedy algorithm to solve the resultant problem. Note that a channel (3D tensor) often consists of a set of kernels (each with a 2D matrix). Besides the redundancy in channels, some kernels in a channel may also be redundant and fail to contribute to the discriminative power of the network, resulting in kernel level redundancy. To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to further compress deep networks by removing redundant kernels. To avoid manually determining the pruning rate for each layer, we propose two adaptive stopping conditions to automatically determine the number of selected channels/kernels. The proposed adaptive stopping conditions tend to yield more efficient models with better performance in practice. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 model with 30 percent reduction of channels even outperforms the baseline model by 0.36 percent in terms of Top-1 accuracy. We also deploy the pruned models on a smartphone (equipped with a Qualcomm Snapdragon 845 processor). The pruned MobileNetV1 and MobileNetV2 achieve 1.93× and 1.42× inference acceleration on the mobile device, respectively, with negligible performance degradation. The source code and the pre-trained models are available at https://github.com/SCUT-AILab/DCP.

Temporal action localization, which requires a machine to recognize the location as well as the category of action instances in videos, has long been researched in computer vision. The main challenge of temporal action localization lies in that videos are usually long and untrimmed with diverse action contents involved. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage methods) and then perform action recognition/regression on each of them individually, without explicitly exploiting their relations during learning. In this paper, we claim that the relations between action units play an important role in action localization, and a more powerful action detector should not only capture the local content of each action unit but also allow a wider field of view on the context related to it. To this end, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms. To be specific, we first construct a graph, where each action unit is represented as a node and their relations between two action units as an edge. Here, we use two types of relations, one for capturing the temporal connections between different action units, and the other one for characterizing their semantic relationship. Particularly for the temporal connections in two-stage methods, we further explore two different kinds of edges, one connecting the overlapping action units and the other one connecting surrounding but disjointed units. Upon the graph we built, we then apply graph convolutional networks (GCNs) to model the relations among different action units, which is able to learn more informative representations to enhance action localization. Experimental results show that our GCM consistently improves the performance of existing action localization methods, including two-stage methods (e.g., CBR [15] and R-C3D [47]) and one-stage methods (e.g., D-SSAD [22]), verifying the generality and effectiveness of our GCM. Moreover, with the aid of GCM, our approach significantly outperforms the state-of-the-art on THUMOS14 (50.9 percent versus 42.8 percent). Augmentation experiments on ActivityNet also verify the efficacy of modeling the relationships between action units. The source code and the pre-trained models are available at https://github.com/Alvin-Zeng/GCM.

Given one or more query vertices, Community Search (CS) aims to find densely intra-connected and loosely inter-connected structures containing query vertices. Attributed Community Search (ACS), a related problem, is more challenging since it finds communities with both cohesive structures and homogeneous vertex attributes. However, most methods for the CS task rely on inflexible pre-defined structures and studies for ACS treat each attribute independently. Moreover, the most popular ACS strategies decompose ACS into two separate sub-problems, i.e., the CS task and subsequent attribute filtering task. However, in real-world graphs, the community structure and the vertex attributes are closely correlated to each other. This correlation is vital for the ACS problem. In this vein, we argue that the separation strategy cannot fully capture the correlation between structure and attributes simultaneously and it would compromise the final performance. In this paper, we propose Graph Neural Network (GNN) models for both CS and ACS problems, i.e., Query Driven-GNN (QD-GNN) and Attributed Query Driven-GNN (AQD-GNN). In QD-GNN, we combine the local query-dependent structure and global graph embedding. In order to extend QD-GNN to handle attributes, we model vertex attributes as a bipartite graph and capture the relation between attributes by constructing GNNs on this bipartite graph. With a Feature Fusion operator, AQD-GNN processes the structure and attribute simultaneously and predicts communities according to each attributed query. Experiments on real-world graphs with ground-truth communities demonstrate that the proposed models outperform existing CS and ACS algorithms in terms of both efficiency and effectiveness. More recently, an interactive setting for CS is proposed that allows users to adjust the predicted communities. We further verify our approaches under the interactive setting and extend to the attributed context. Our method achieves 2.37% and 6.29% improvements in F1-score than the state-of-the-art model without attributes and with attributes respectively.

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities.

The classification of nuclei in H&E-stained histopathological images is a fundamental step in the quantitative analysis of digital pathology. Most existing methods employ multi-class classification on the detected nucleus instances, while the annotation scale greatly limits their performance. Moreover, they often downplay the contextual information surrounding nucleus instances that is critical for classification. To explicitly provide contextual information to the classification model, we design a new structured input consisting of a content-rich image patch and a target instance mask. The image patch provides rich contextual information, while the target instance mask indicates the location of the instance to be classified and emphasizes its shape. Benefiting from our structured input format, we propose Structured Triplet for representation learning, a triplet learning framework on unlabelled nucleus instances with customized positive and negative sampling strategies. We pre-train a feature extraction model based on this framework with a large-scale unlabeled dataset, making it possible to train an effective classification model with limited annotated data. We also add two auxiliary branches, namely the attribute learning branch and the conventional self-supervised learning branch, to further improve its performance. As part of this work, we will release a new dataset of H&E-stained pathology images with nucleus instance masks, containing 20,187 patches of size 1024 ×1024 , where each patch comes from a different whole-slide image. The model pre-trained on this dataset with our framework significantly reduces the burden of extensive labeling. We show a substantial improvement in nucleus classification accuracy compared with the state-of-the-art methods.

In this article, we study the problem of guaranteed display ads (GDAs) allocation, which requires proactively allocate display ads to different impressions to fulfill their impression demands indicated in the contracts. Existing methods for this problem either assume the impressions that are static or solely consider a specific ad's benefits. Thus, it is hard to generalize to the industrial production scenario where the impressions are dynamical and large-scale, and the overall allocation optimality of all the considered GDAs is required. To bridge this gap, we formulate this problem as a sequential decision-making problem in the scope of multiagent reinforcement learning (MARL), by assigning an allocation agent to each ad and coordinating all the agents for allocating GDAs. The inputs are the states (e.g., the demands of the ad and the remaining time steps for displaying the ads) of each ad and the impressions at different time steps, and the outputs are the display ratios of each ad for each impression. Specifically, we propose a novel hierarchical MARL (HMARL) method that creates hierarchies over the agent policies to handle a large number of ads and the dynamics of impressions. HMARL contains: 1) a manager policy to navigate the agent to choose an appropriate subpolicy and 2) a set of subpolicies that let the agents perform diverse conditioning on their states. Extensive experiments on three real-world data sets from the Tencent advertising platform with tens of millions of records demonstrate significant improvements of HMARL over state-of-the-art approaches.

The immunohistochemistry (IHC) test of biopsy tissue is crucial to develop targeted treatment and evaluate prognosis for cancer patients. The IHC staining slide is usually digitized into the whole-slide image (WSI) with gigapixels for quantitative image analysis. To perform a whole image prediction (e.g., IHC scoring, survival prediction, and cancer grading) from this kind of high-dimensional image, algorithms are often developed based on multi-instance learning (MIL) framework. However, the multi-scale information of WSI and the associations among instances are not well explored in existing MIL based studies. Inspired by the fact that pathologists jointly analyze visual fields at multiple powers of objective for diagnostic predictions, we propose a Pathologist-Tree Network (PTree-Net) to sparsely model the WSI efficiently in multi-scale manner. Specifically, we propose a Focal-Aware Module (FAM) that can approximately estimate diagnosis-related regions with an extractor trained using the thumbnail of WSI. With the initial diagnosis-related regions, we hierarchically model the multi-scale patches in a tree structure, where both the global and local information can be captured. To explore this tree structure in an end-to-end network, we propose a patch Relevance-enhanced Graph Convolutional Network (RGCN) to explicitly model the correlations of adjacent parent-child nodes, accompanied by patch relevance to exploit the implicit contextual information among distant nodes. In addition, tree-based self-supervision is devised to improve representation learning and suppress irrelevant instances adaptively. Extensive experiments are performed on a large-scale IHC HER2 dataset. The ablation study confirms the effectiveness of our design, and our approach outperforms state-of-the-art by a large margin.

Protein secondary structure prediction (PSSP) is an essential task in computational biology. To achieve the accurate PSSP, the general and vital feature engineering is to use multiple sequence alignment (MSA) for Position-Specific Scoring Matrix (PSSM) extraction. However, when only low-quality PSSM can be obtained due to poor sequence homology, previous PSSP accuracy (merely around 65%) is far from practical usage for subsequent tasks. In this paper, we propose a novel PSSM-Distil framework for PSSP on low-quality PSSM, which not only enhances the PSSM feature at a lower level but also aligns the feature distribution at a higher level. In practice, the PSSM-Distil first exploits the proteins with high-quality PSSM to achieve a teacher network for PSSP in a full-supervised way. Under the guidance of the teacher network, the low-quality PSSM and corresponding student network with low discriminating capacity are effectively resolved by feature enhancement through EnhanceNet and distribution alignment through knowledge distillation with contrastive learning. Further, our PSSM-Distil supports the input from a pre-trained protein sequence language BERT model to provide auxiliary information, which is designed to address the extremely low-quality PSSM cases, i.e., no homologous sequence. Extensive experiments demonstrate the proposed PSSM-Distil outperforms state-of-the-art models on PSSP by 6% on average and nearly 8% in extremely low-quality cases on public benchmarks, BC40 and CB513.

Nucleus instance segmentation and classification in histopathological images is an essential prerequisite in pathology diagnosis/prognosis. However, nucleus annotations (e.g., segmentation and labeling) require domain experts, and annotating nuclei at pixel-level is time-consuming and labor-intensive. Moreover, nuclei from different cancer types vary in shapes and appearances. These inter-cancer variations require careful annotations for specific cancer types. Therefore, to minimize the labeling cost, we propose a novel application that considers each cancer type as an individual domain and apply domain adaptation techniques to improve the segmentation/classification performance among different cancer types. Unlike the previous studies that focus on unsupervised or weakly-supervised domain adaptation independently, we would like to discover what kinds of labeling can achieve the most cost-effective domain adaptation performance in nucleus instance segmentation and classification. Specifically, we propose a unified framework that is applicable to different level annotations: no annotations, image-level, and point-level annotations. Cyclic adaptation with pseudo labels and adversarial discriminator are utilized for unsupervised domain alignment. Image-level or point-level annotations are additionally adopted to supervise the nucleus classification and refine the pseudo labels. Experiments demonstrate the effectiveness and efficacy of the proposed framework (jointly using unsupervised and weakly supervised learning) on adapting the segmentation and classification model from one cancer type to 18 other cancer types.

Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph representation which plays an important role in graph classification. In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. Specifically, disentangled graph capsules are established by identifying heterogeneous factors underlying each node, such that their instantiation parameters represent different properties of the same entity. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higher-level capsules (whole) by explicitly considering the structure information among the parts. Experimental studies demonstrate the effectiveness of HGCN and the contribution of each component. Code: https://github.com/uta-smile/HGCN

Molecular property prediction is one fundamental yet challenging task for drug discovery. Many studies have addressed this problem by designing deep learning algorithms, e.g., sequence-based models and graph-based models. However, the underlying data distribution is rarely explored. We discover that there exist easy samples and hard samples in the molecule datasets, and the overall distribution is usually imbalanced. Current research mainly treats them equally during the model training, while we believe that they shall not share the same weights since neural networks training is dominated by the majority class. Therefore, we propose to utilize a self-attention mechanism to generate a learnable weight for each data sample according to the associated gradient norm. The learned attention value is then embedded into the prediction models to construct an attentive loss for the network updating and back-propagation. It is empirically demonstrated that our proposed method can consistently boost the prediction performance for both classification and regression tasks.

Clinical omics, especially gene expression data, have been widely studied and successfully applied for disease diagnosis using machine learning techniques. As genes often work interactively rather than individually, investigating co-functional gene modules can improve our understanding of disease mechanisms and facilitate disease state prediction. To this end, we in this paper propose a novel Multi-Level Enhanced Graph ATtention (MLE-GAT) network to explore the gene modules and intergene relational information contained in the omics data. In specific, we first format the omics data of each patient into co-expression graphs using weighted correlation network analysis (WGCNA) and then feed them to a well-designed multi-level graph feature fully fusion (MGFFF) module for disease diagnosis. For model interpretation, we develop a novel full-gradient graph saliency (FGS) mechanism to identify the disease-relevant genes. Comprehensive experiments show that our proposed MLE-GAT achieves state-of-the-art performance on transcriptomics data from TCGA-LGG/TCGA-GBM and proteomics data from COVID-19/non-COVID-19 patient sera.

Variants of Graph Neural Networks (GNNs) for representation learning have been proposed recently and achieved fruitful results in various fields. Among them, Graph Attention Network (GAT) first employs a self-attention strategy to learn attention weights for each edge in the spatial domain. However, learning the attentions over edges can only focus on the local information of graphs and greatly increases the computational costs. In this paper, we first introduce the attention mechanism in the spectral domain of graphs and present Spectral Graph Attention Network (SpGAT) that learns representations for different frequency components regarding weighted filters and graph wavelets bases. In this way, SpGAT can better capture global patterns of graphs in an efficient manner with much fewer learned parameters than that of GAT. Further, to reduce the computational cost of SpGAT brought by the eigen-decomposition, we propose a fast approximation variant SpGAT-Cheby. We thoroughly evaluate the performance of SpGAT and SpGAT-Cheby in semi-supervised node classification tasks and verify the effectiveness of the learned attentions in the spectral domain.

Nowadays, it is common for a person to possess different identities on multiple social platforms. Social network alignment aims to match the identities that from different networks. Recently, unsupervised network alignment methods have received significant attention since no identity anchor is required. However, to capture the relevance between identities, the existing unsupervised methods generally rely heavily on user profiles, which is unobtainable and unreliable in real-world scenarios. In this paper, we propose an unsupervised alignment framework named Large-Scale Network Alignment (LSNA) to integrate the network information and reduce the requirement on user profile. The embedding module of LSNA, named Cross Network Embedding Model (CNEM), aims to integrate the topology information and the network correlation to simultaneously guide the embedding process. Moreover, in order to adapt LSNA to large-scale networks, we propose a network disassembling strategy to divide the costly large-scale network alignment problem into multiple executable sub-problems. The proposed method is evaluated over multiple real-world social network datasets, and the results demonstrate that the proposed method outperforms the state-of-the-art methods.

Recent studies imply that deep neural networks are vulnerable to adversarial examples, i.e., inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some security-related applications (e.g., semantic segmentation in autonomous cars) and triggers tremendous concerns on the model reliability. For the first time, we comprehensively evaluate the robustness of existing UDA methods and propose a robust UDA approach. It is rooted in two observations: i) the robustness of UDA methods in semantic segmentation remains unexplored, which poses a security concern in this field; and ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits model robustness in classification and recognition tasks, they fail to provide the critical supervision signals that are essential in semantic segmentation. These observations motivate us to propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. Extensive empirical studies on commonly used benchmarks demonstrate that ASSUDA is resistant to adversarial attacks.

In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST). Classic network architectures (NAs) are generally worse than searched NA in ST, which should be the same in AT. In this paper, we argue that NA and AT cannot be handled independently, since given a dataset, the optimal NA in ST would be no longer optimal in AT. That being said, AT is time-consuming itself; if we directly search NAs in AT over large search spaces, the computation will be practically infeasible. Thus, we propose diverse-structured network (DS-Net), to significantly reduce the size of the search space: instead of low-level operations, we only consider predefined atomic blocks, where an atomic block is a time-tested building block like the residual block. There are only a few atomic blocks and thus we can weight all atomic blocks rather than find the best one in a searched block of DS-Net, which is an essential tradeoff between exploring diverse structures and exploiting the best structures. Empirical results demonstrate the advantages of DS-Net, i.e., weighting the atomic blocks.

The surrogate that predicts the performance of hyperparameters has been a key component for sequential model-based hyperparameter optimization. In practical applications, a trial of a hyper-parameter configuration may be so costly that a surrogate is expected to return an optimal configuration with as few trials as possible. Observing that human experts draw on their expertise in a machine learning model by trying configurations that once performed well on other datasets, we are inspired to build a trial-efficient surrogate by transferring the meta-knowledge learned from historical trials on other datasets. We propose an end-to-end surrogate named as Transfer NeuralProcesses (TNP) that learns a comprehensive set of meta-knowledge, including the parameters of historical surrogates, historical trials, and initial configurations for other datasets. Experiments on extensive OpenML datasets and three computer vision datasets demonstrate that the proposed algorithm achieves state-of-the-art performance in at least one order of magnitude less trials.

Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train a well-generalized model initialization which is adapted to each task via the support set. The crux lies in optimizing the generalization capability of the initialization, which is measured by the performance of the adapted model on the query set of each task. Unfortunately, this generalization measure, evidenced by empirical results, pushes the initialization to overfit the meta-training tasks, which significantly impairs the generalization and adaptation to novel tasks. To address this issue, we actively augment a meta-training task with “more data” when evaluating the generalization. Concretely, we propose two task augmentation methods, including MetaMix and Channel Shuffle. MetaMix linearly combines features and labels of samples from both the support and query sets. For each class of samples, Channel Shuffle randomly replaces a subset of their channels with the corresponding ones from a different class. Theoretical studies show how task augmentation improves the generalization of meta-learning. Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.

Recently, the teacher-student knowledge distillation framework has demonstrated its potential in training Graph Neural Networks (GNNs). However, due to the difficulty of training over-parameterized GNN models, one may not easily obtain a satisfactory teacher model for distillation. Furthermore, the inefficient training process of teacher-student knowledge distillation also impedes its applications in GNN models. In this paper, we propose the first teacher-free knowledge distillation method for GNNs, termed GNN Self-Distillation (GNN-SD), that serves as a drop-in replacement of the standard training process. The method is built upon the proposed neighborhood discrepancy rate (NDR), which quantifies the non-smoothness of the embedded graph in an efficient way. Based on this metric, we propose the adaptive discrepancy retaining (ADR) regularizer to empower the transferability of knowledge that maintains high neighborhood discrepancy across GNN layers. We also summarize a generic GNN-SD framework that could be exploited to induce other distillation strategies. Experiments further prove the effectiveness and generalization of our approach, as it brings: 1) state-of-the-art GNN distillation performance with less training cost, 2) consistent and considerable performance enhancement for various popular backbones.

Graph Convolutional Networks (GCNs) are promising deep learning approaches in learning representations for graph-structured data. Despite the proliferation of such methods, it is well known that they are vulnerable to carefully crafted adversarial attacks on the graph structure. In this paper, we first conduct an adversarial vulnerability analysis based on matrix perturbation theory. We prove that the low- frequency components of the symmetric normalized Laplacian, which is usually used as the convolutional filter in GCNs, could be more robust against structural perturbations when their eigenvalues fall into a certain robust interval. Our results indicate that not all low-frequency components are robust to adversarial attacks and provide a deeper understanding of the relationship between graph spectrum and robustness of GCNs. Motivated by the theory, we present GCN-LFR, a general robust co-training paradigm for GCN-based models, that encourages transferring the robustness of low-frequency components with an auxiliary neural network. To this end, GCN-LFR could enhance the robustness of various kinds of GCN-based models against poisoning structural attacks in a plug-and-play manner. Extensive experiments across five benchmark datasets and five GCN-based models also confirm that GCN-LFR is resistant to the adversarial attacks without compromising on performance in the benign situation.

More recently, there has been a surge of interest in employing machine learning approaches to expedite the drug discovery process where virtual screening for hit discovery and ADMET prediction for lead optimization play essential roles. One of the main obstacles to the wide success of machine learning approaches in these two tasks is that the number of compounds labeled with activities or ADMET properties is too small to build an effective predictive model. This paper seeks to remedy the problem by transferring the knowledge from previous assays, namely in-vivo experiments, by different laboratories and against various target proteins. To accommodate these wildly different assays and capture the similarity between assays, we propose a functional rationalized meta-learning algorithm FRML for such knowledge transfer. FRML constructs the predictive model with layers of neural sub-networks or so-called functional regions. Building on this, FRML shares an initialization for the weights of the predictive model across all assays, while customizes it to each assay with a region localization network choosing the pertinent regions. The compositionality of the model improves the capacity of generalization to various and even out-of-distribution tasks. Empirical results on both virtual screening and ADMET prediction validate the superiority of FRML over state-of-the-art baselines powered with interpretability in assay relationship.

In this paper, we consider the problem of unsupervised domain adaptation in the semantic segmentation. There are two primary issues in this field, i.e., what and how to transfer domain knowledge across two domains. Existing methods mainly focus on adapting domain-invariant features (what to transfer) through adversarial learning (how to transfer). Context dependency is essential for semantic segmentation, however, its transferability is still not well understood. Furthermore, how to transfer contextual information across two domains remains unexplored. Motivated by this, we propose a cross-attention mechanism based on self-attention to capture context dependencies between two domains and adapt transferable context. To achieve this goal, we design two cross-domain attention modules to adapt context dependencies from both spatial and channel views. Specifically, the spatial attention module captures local feature dependencies between each position in the source and target image. The channel attention module models semantic dependencies between each pair of cross-domain channel maps. To adapt context dependencies, we further selectively aggregate the context information from two domains. The superiority of our method over existing state-of-the-art methods is empirically proved on "GTA5 to Cityscapes" and "SYNTHIA to Cityscapes".

Deep learning is an important branch of artificial intelligence that has been successfully applied into medicine and two-dimensional ligand design. The three-dimensional (3D) ligand generation in the 3D pocket of protein target is an interesting and challenging issue for drug design by deep learning. Here, the MolAICal software is introduced to supply a way for generating 3D drugs in the 3D pocket of protein targets by combining with merits of deep learning model and classical algorithm. The MolAICal software mainly contains two modules for 3D drug design. In the first module of MolAICal, it employs the genetic algorithm, deep learning model trained by FDA-approved drug fragments and Vinardo score fitting on the basis of PDBbind database for drug design. In the second module, it uses deep learning generative model trained by drug-like molecules of ZINC database and molecular docking invoked by Autodock Vina automatically. Besides, the Lipinski's rule of five, Pan-assay interference compounds (PAINS), synthetic accessibility (SA) and other user-defined rules are introduced for filtering out unwanted ligands in MolAICal. To show the drug design modules of MolAICal, the membrane protein glucagon receptor and non-membrane protein SARS-CoV-2 main protease are chosen as the investigative drug targets. The results show MolAICal can generate the various and novel ligands with good binding scores and appropriate XLOGP values. We believe that MolAICal can use the advantages of deep learning model and classical programming for designing 3D drugs in protein pocket. MolAICal is freely for any nonprofit purpose and accessible at https://molaical.github.io.

Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced. In practice, it is quite difficult to handle imbalanced unlabeled datastream when only a limited budget of labels can be queried for training. To solve this, previous OAL studies adopt either asymmetric losses or queries (an isolated asymmetric strategy) to tackle the imbalance, and use first-order methods to optimize the cost-sensitive measure. However, the isolated strategy limits their performance in class imbalance, while first-order methods restrict their optimization performance. In this article, we propose a novel Online Adaptive Asymmetric Active learning algorithm, based on a new asymmetric strategy (merging both asymmetric losses and queries strategies), and second-order optimization. We theoretically analyze its mistake bound and cost-sensitive metric bounds. Moreover, to better balance performance and efficiency, we enhance our algorithm via a sketching technique, which significantly accelerates the computational speed with quite slight performance degradation. Promising results demonstrate the effectiveness and efficiency of the proposed methods.

Social media has been developing rapidly in public due to its nature of spreading new information, which leads to rumors being circulated. Meanwhile, detecting rumors from such massive information in social media is becoming an arduous challenge. Therefore, some deep learning methods are applied to discover rumors through the way they spread, such as Recursive Neural Network (RvNN) and so on. However, these deep learning methods only take into account the patterns of deep propagation but ignore the structures of wide dispersion in rumor detection. Actually, propagation and dispersion are two crucial characteristics of rumors. In this paper, we propose a novel bi-directional graph model, named Bi-Directional Graph Convolutional Networks (Bi-GCN), to explore both characteristics by operating on both top-down and bottom-up propagation of rumors. It leverages a GCN with a top-down directed graph of rumor spreading to learn the patterns of rumor propagation; and a GCN with an opposite directed graph of rumor diffusion to capture the structures of rumor dispersion. Moreover, the information from source post is involved in each layer of GCN to enhance the influences from the roots of rumors. Encouraging empirical results on several benchmarks confirm the superiority of the proposed method over the state-of-the-art approaches.

With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, most of the current works perform the attack in a white-box fashion: they need to access the model predictions and labels to construct their adversarial loss. However, the inaccessibility of model predictions in real systems makes the white-box attack impractical to real graph learning system. This paper promotes current frameworks in a more general and flexible sense – we demand to attack various kinds of graph embedding model with black-box driven. To this end, we begin by investigating the theoretical connections between graph signal processing and graph embedding models in a principled way and formulate the graph embedding model as a general graph signal process with corresponding graph filter. As such, a generalized adversarial attacker: GF-Attack is constructed by the graph filter and feature matrix. Instead of accessing any knowledge of the target classifiers used in graph embedding, GF-Attack performs the attack only on the graph filter in a black-box attack fashion. To validate the generalization of GF-Attack, we construct the attacker on four popular graph embedding models. Extensive experimental results validate the effectiveness of our attacker on several benchmark datasets. Particularly by using our attack, even small graph perturbations like one-edge flip is able to consistently make a strong attack in performance to different graph embedding models.

In this work, we consider the medical slot filling problem, i.e., the problem of converting medical queries into structured representations which is a challenging task. We analyze the effectiveness of two points: scattered keywords in user utterances and weak supervision with responses. We approach the medical slot filling as a multi-label classification problem with label-embedding attentive model to pay more attention to scattered medical keywords and learn the classification models by weak-supervision from responses. To evaluate the approaches, we annotate a medical slot filling data and collect a large scale unlabeled data. The experiments demonstrate that these two points are promising to improve the task.

Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model and the contribution of each component.

Binary code similarity detection, whose goal is to detect similar binary functions without having access to the source code, is an essential task in computer security. Traditional methods usually use graph matching algorithms, which are slow and inaccurate. Recently, neural network-based approaches have made great achievements. A binary function is first represented as an control-flow graph (CFG) with manually selected block features, and then graph neural network (GNN) is adopted to compute the graph embedding. While these methods are effective and efficient, they could not capture enough semantic information of the binary code. In this paper we propose semantic-aware neural networks to extract the semantic information of the binary code. Specially, we use BERT to pre-train the binary code on one token-level task, one block-level task, and two graph-level tasks. Moreover, we find that the order of the CFG's nodes is important for graph similarity detection, so we adopt convolutional neural network (CNN) on adjacency matrices to extract the order information. We conduct experiments on two tasks with four datasets. The results demonstrate that our method outperforms the state-of-art models.

The secondary structure of proteins is significant for studying the three-dimensional structure and functions of proteins. Several models from image understanding and natural language modeling have been successfully adapted in the protein sequence study area, such as Long Short-term Memory (LSTM) network and Convolutional Neural Network (CNN). Recently, Gated Convolutional Neural Network (GCNN) has been proposed for natural language processing and reduces latency while achieving high levels of sentence scoring. Conditionally Parameterized Convolution (CondConv), which use extra sample-dependant modules to conditionally adjust the convolutional network, have achieved great success in the image processing area. In this paper, we propose a novel Conditionally Parameterized Convolutional network (CondGCNN) which utilize the power of both CondConv and GCNN, and we leverage an ensemble encoder to combine the capabilities of both LSTM and CondGCNN to encode protein sequences to obtain better sequential features from proteins. In addition, due to the similarity between the image segmentation problem and the secondary structure prediction problem, we propose an ASP network (Atrous Spatial Pyramid Pooling (ASPP) based network) as the secondary structure generator in our proposed framework. We have conducted extensive ablation studies over each component in the proposed model to verify its effectiveness. Extensive experiments show that the proposed method can achieve higher performance on protein secondary structure prediction task than existing methods on CB513, Caspll and CASP12 datasets. Our method is expected to be useful for protein structure and further protein functions prediction.

Accurately predicting protein structure properties is essential in analyzing the structure and function of a protein, such as secondary structure, solvent accessibility, and dihedral angles. Multiple Sequence Alignment (MSA), which is a sequence alignment of multiple homologous protein sequences for the target protein, is widely used in the protein structure property prediction. The most popular strategy to exploit MSA is converting it into a position-specific scoring matrice (PSSM), then inputs the PSSM to the relevant prediction networks. PSSM is obtained by simply counting the frequency of amino acids presented at each position in the corresponding MSA, which means, each sequence in the MSA has the same weight to the target protein. However, simply setting the weights of homologous protein sequences of a protein as same cannot sufficiently model the complex relationships between them. Moreover, some sequences within the MSA are redundant, which raises a tantalizing question: can we generate a different weight for each sequence in the MSA and use the weighted PSSM to improve the performance of protein structure property prediction? To help answer this question, we present WeightAln framework, which to our knowledge, is the first attempt to generate learnable MSA weights for protein prediction tasks. We prove the effectiveness of our method by conducting extensive experiments on three protein structure property prediction tasks.

Acquiring labeled data has been widely recognized as a major challenge in molecular property prediction. Since it generally requires a series of specialized biochemical experiments which are time-consuming, costly, as well as labor-intensive. The deficiency of labeled property data makes it difficult to learn a good prediction model. Here, we propose an RNN-based multi-label molecular property prediction method to alleviate the data scarcity issue in two stages: 1) utilize the abundant unlabeled SMILES data to pre-train a seq2seq model whose encoder learns to generate molecular fingerprint based on the given SMILES; and 2) finetune the pre-trained model on the labeled molecular property data. Since labeled data is limited, we train those properties with limited sample size jointly with other properties which contain relatively sufficient samples. This approach brings in the idea of multi-label training, which is able to pre-train and fine-tune the encoder network, as well as train the prediction network with a data augmentation strategy. Extensive experiments on molecular property prediction demonstrate that our proposed method has achieved superior performance compared with the state-of-the-art approaches on properties with limited sample size.

Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insufficient information for the training. As a result, existing methods may often produce sub-optimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method.

Many real data come in the form of non-grid objects, i.e. graphs, from social networks to molecules. Adaptation of deep learning from grid-alike data (e.g. images) to graphs has recently received unprecedented attention from both machine learning and data mining communities, leading to a new cross-domain field---Deep Graph Learning (DGL). Instead of painstaking feature engineering, DGL aims to learn informative representations of graphs in an end-to-end manner. It has exhibited remarkable success in various tasks, such as node/graph classification, link prediction, etc.

In transfer learning, what and where to transfer has been widely studied. Nevertheless, the learned transfer strategies are at high risk of over-fitting, especially when only a few annotated instances are available in the target domain. In this paper, we introduce the concept of transfer ensemble learning, a new direction to tackle the over-fitting of transfer strategies. Intuitively, models with different transfer strategies offer various perspectives on what and where to transfer. Therefore a core problem is to search these diversely transferred models for ensemble so as to achieve better generalization. Towards this end, we propose the Transferability Slider (TranSlider) for transfer ensemble learning. By decreasing the transferability, we obtain a spectrum of base models ranging from pure exploitation of the source model to unconstrained exploration for the target domain. Furthermore, the manner of decreasing transferability with parameter sharing guarantees fast optimization at no additional training cost. Finally, we conduct extensive experiments with various analyses, which demonstrate that TranSlider achieves the state-of-the-art on comprehensive benchmark datasets.

Graph Neural Networks (GNN) and Variational Autoencoders (VAEs) have been widely used in modeling and generating graphs with latent factors. However there is no clear explanation of what these latent factors are and why they perform well. In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Our study connects VAEs based graph generation and balanced graph cut, and provides a new way to understand and improve the internal mechanism of VAEs based graph generation. Specifically, we first interpret the reconstruction term of DGVAE as balanced graph cut in a principled way. Furthermore, motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships. Heatts utilizes the Taylor series for fast computation of Heat kernels and has better low pass characteristics than Graph Convolutional Networks (GCN). Through experiments on graph generation and graph clustering, we demonstrate the effectiveness of our proposed framework.

How to obtain informative representations of molecules is a crucial prerequisite in AI-driven drug design and discovery. Recent researches abstract molecules as graphs and employ Graph Neural Networks (GNNs) for molecular representation learning. Nevertheless, two issues impede the usage of GNNs in real scenarios: (1) insufficient labeled molecules for supervised training; (2) poor generalization capability to new-synthesized molecules. To address them both, we propose a novel framework, GROVER, which stands for Graph Representation frOm self-superVised mEssage passing tRansformer. With carefully designed self-supervised tasks in node-, edge- and graph-level, GROVER can learn rich structural and semantic information of molecules from enormous unlabelled molecular data. Rather, to encode such complex information, GROVER integrates Message Passing Networks into the Transformer-style architecture to deliver a class of more expressive encoders of molecules. The flexibility of GROVER allows it to be trained efficiently on large-scale molecular dataset without requiring any supervision, thus being immunized to the two issues mentioned above. We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules---the biggest GNN and the largest training dataset in molecular representation learning. We then leverage the pre-trained GROVER for molecular property prediction followed by task-specific fine-tuning, where we observe a huge improvement (more than 6% on average) from current state-of-the-art methods on 11 challenging benchmarks. The insights we gained are that well-designed self-supervision losses and largely-expressive pre-trained models enjoy the significant potential on performance boosting.

Recent advances in neural architecture search inspire many channel number search algorithms~(CNS) for convolutional neural networks. To improve searching efficiency, parameter sharing is widely applied, which reuses parameters among different channel configurations. Nevertheless, it is unclear how parameter sharing affects the searching process. In this paper, we aim at providing a better understanding and exploitation of parameter sharing for CNS. Specifically, we propose affine parameter sharing~(APS) as a general formulation to unify and quantitatively analyze existing channel search algorithms. It is found that with parameter sharing, weight updates of one architecture can simultaneously benefit other candidates. However, it also results in less confidence in choosing good architectures. We thus propose a new strategy of parameter sharing towards a better balance between training efficiency and architecture discrimination. Extensive analysis and experiments demonstrate the superiority of the proposed strategy in channel configuration against many state-of-the-art counterparts on benchmark datasets.

Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet, current methods including aggregation-based and alignment-based fusion are still inadequate in balancing the trade-off between inter-modal fusion and intra-modal processing, incurring a bottleneck of performance improvement. To this end, this paper proposes Channel-Exchanging-Network (CEN), a parameter-free multimodal fusion framework that dynamically exchanges channels between sub-networks of different modalities. Specifically, the channel exchanging process is self-guided by individual channel importance that is measured by the magnitude of Batch-Normalization (BN) scaling factor during training. The validity of such exchanging process is also guaranteed by sharing convolutional filters yet keeping separate BN layers across modalities, which, as an add-on benefit, allows our multimodal architecture to be almost as compact as a unimodal network. Extensive experiments on semantic segmentation via RGB-D data and image translation through multi-domain input verify the effectiveness of our CEN compared to current state-of-the-art methods. Detailed ablation studies have also been carried out, which provably affirm the advantage of each component we propose. Our code is available at https://github.com/yikaiw/CEN.

Many approaches have been proposed for time series forecasting, in light of its significance in wide applications including business demand prediction. However, the existing methods suffer from two key limitations. Firstly, most point prediction models only predict an exact value of each time step without flexibility, which can hardly capture the stochasticity of data. Even probabilistic prediction using the likelihood estimation suffers these problems in the same way. Besides, most of them use the auto-regressive generative mode, where ground-truth is provided during training and replaced by the network’s own one-step ahead output during inference, causing the error accumulation in inference. Thus they may fail to forecast time series for long time horizon due to the error accumulation. To solve these issues, in this paper, we propose a new time series forecasting model -- Adversarial Sparse Transformer (AST), based on Generated Adversarial Networks (GANs). Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level. Extensive experiments on several real-world datasets show the effectiveness and efficiency of our method.

Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate or assist in the retrosynthesis analysis, various retrosynthesis prediction algorithms have been proposed. However, most of them are cumbersome and lack interpretability about their predictions. In this paper, we devise a novel template-free algorithm for automatic retrosynthetic expansion inspired by how chemists approach retrosynthesis prediction. Our method disassembles retrosynthesis into two steps: i) identify the potential reaction center of the target molecule through a novel graph neural network and generate intermediate synthons, and ii) generate the reactants associated with synthons via a robust reactant generation model. While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.

It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks. In this paper, we extend adversarial graphs to the problem of community detection which is much more difficult. We focus on black-box attack and aim to hide targeted individuals from the detection of deep graph community detection models, which has many applications in real-world scenarios, for example, protecting personal privacy in social networks and understanding camouflage patterns in transaction networks. We propose an iterative learning framework that takes turns to update two modules: one working as the constrained graph generator and the other as the surrogate community detection model. We also find that the adversarial graphs generated by our method can be transferred to other learning based community detection models.

The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision. This paper investigates how to preserve and extract the abundant information from graph-structured data into embedding space in an unsupervised manner. To this end, we propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. GMI generalizes the idea of conventional mutual information computations from vector space to the graph domain where measuring mutual information from two aspects of node features and topological structure is indispensable. GMI exhibits several benefits: First, it is invariant to the isomorphic transformation of input graphs—an inevitable constraint in many existing graph representation learning algorithms; Besides, it can be efficiently estimated and maximized by current mutual information estimation methods such as MINE; Finally, our theoretical analysis confirms its correctness and rationality. With the aid of GMI, we develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder. Considerable experiments on transductive as well as inductive node classification and link prediction demonstrate that our method outperforms state-of-the-art unsupervised counterparts, and even sometimes exceeds the performance of supervised ones.

The human visual system tends to consider saliency of an object as a whole. Some object-level saliency detection methods have been proposed by leveraging object proposals in bounding boxes, and regarding the entire bounding box as one candidate salient region. However, the bounding boxes can not provide exact object position and a lot of pixels in bounding boxes belong to the background. Consequently, background pixels in bounding box also show high saliency. Besides, acquiring object proposals needs high time cost. In order to compute object-level saliency, we consider region growing from some seed superpixels, to find one surrounding region which probably represents the whole object. The desired surrounding region has similar appearance inside and obvious difference with the outside, which is proposed as maximally stable region (MSR) in this paper. In addition, one effective seed superpixel selection strategy is presented to improve speed. MSR based saliency detection is more robust than pixel or superpixel level methods and object proposal based methods. The proposed method significantly outperforms the state-of-the-art unsupervised methods at 50 FPS. Compared with deep learning based methods, we show worse performance, but with about 1200-1600 times faster, which means better trade-off between performance and speed.

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model training, due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noise (e.g.,mislabeling labels) due to diagnostic difficulties of diseases. To address these, we seek to exploit rich labeled data from relevant domains to help the learning in the target task via Unsupervised Domain Adaptation (UDA). Unlike most UDA methods that rely on clean labeled data or assume samples are equally transferable, we innovatively propose a Collaborative Unsupervised Domain Adaptation algorithm, which conducts transferability-aware adaptation and conquers label noise in a collaborative way. We theoretically analyze the generalization performance of the proposed method, and also empirically evaluate it on both medical and general images. Promising experimental results demonstrate the superiority and generalization of the proposed method.

Factorization Machines (FMs) learn weights for feature interactions, and achieve great success in many data mining tasks. Recently, Locally Linear Factorization Machines (LLFMs) have been proposed to capture the underlying structures of data for better performance. However, one obvious drawback of LLFM is that the local coding is only operated in the original feature space, which limits the model to be applied to high-dimensional and sparse data. In this work, we present a generalized LLFM (GLLFM) which overcomes this limitation by modeling the local coding procedure in a latent space. Moreover, a novel Supervised Variational Encoding (SVE) technique is proposed such that the distance can effectively describe the similarity between data points. Specifically, the proposed GLLFM-SVE trains several local FMs in the original space to model the higher order feature interactions effectively, where each FM associates to an anchor point in the latent space induced by SVE. The prediction for a data point is computed by a weighted sum of several local FMs, where the weights are determined by local coding coordinates with anchor points. Actually, GLLFM-SVE is quite flexible and other Neural Network (NN) based FMs can be easily embedded into this framework. Experimental results show that GLLFM-SVE significantly improves the performance of LLFM. By using NN-based FMs as local predictors, our model outperforms all the state-of-the-art methods on large-scale real-world benchmarks with similar number of parameters and comparable training time.

The recent advances in deep learning have made it possible to generate photo-realistic images by using neural networks and even to extrapolate video frames from an input video clip. In this paper, for the sake of both furthering this exploration and our own interest in a realistic application, we study imageto-video translation and particularly focus on the videos of facial expressions. This problem challenges the deep neural networks by another temporal dimension comparing to the image-to-image translation. Moreover, its single input image fails most existing video generation methods that rely on recurrent models. We propose a user-controllable approach so as to generate video clips of various lengths from a single face image. The lengths and types of the expressions are controlled by users. To this end, we design a novel neural network architecture that can incorporate the user input into its skip connections and propose several improvements to the adversarial training method for the neural network. Experiments and user studies verify the effectiveness of our approach. Especially, we would like to highlight that even for the face images in the wild (downloaded from the Web and the authors’ own photos), our model can generate high-quality facial expression videos of which about 50% are labeled as real by Amazon Mechanical Turk workers.

One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation be-´ comes an appealing objective because of its operational meaning and desirable properties. However, the strict whitening constraints formalized in the HGR maximal correlation limit its application. To address this problem, this paper proposes Soft-HGR, a novel framework to extract informative features from multiple data modalities. Specifically, our framework prevents the “hard” whitening constraints, while simultaneously preserving the same feature geometry as in the HGR maximal correlation. The objective of Soft-HGR is straightforward, only involving two inner products, which guarantees the efficiency and stability in optimization. We further generalize the framework to handle more than two modalities and missing modalities. When labels are partially available, we enhance the discriminative power of the feature representations by making a semi-supervised adaptation. Empirical evaluation implies that our approach learns more informative feature mappings and is more efficient to optimize.

In this paper, we present a sample distributed greedy pursuit method for non-convex sparse learning under cardinality constraint. Given the training samples uniformly randomly partitioned across multiple machines, the proposed method alternates between local inexact sparse minimization of a Newton-type approximation and centralized global results aggregation. Theoretical analysis shows that for a general class of convex functions with Lipschitze continues Hessian, the method converges linearly with contraction factor scaling inversely to the local data size; whilst the communication complexity required to reach desirable statistical accuracy scales logarithmically with respect to the number of machines for some popular statistical learning models. For nonconvex objective functions, up to a local estimation error, our method can be shown to converge to a local stationary sparse solution with sub-linear communication complexity. Numerical results demonstrate the efficiency and accuracy of our method when applied to large-scale sparse learning tasks including deep neural nets pruning

For constrained nonconvex minimization problems, we propose a meta stochastic projection-free optimization algorithm, named Normalized Frank Wolfe Updating, that can take any Gradient Estimator (GE) as input. For this algorithm, we prove its convergence rate, regardless of the choice of GE. Using a sophisticated GE, this algorithm can significantly improve the Stochastic First order Oracle (SFO) complexity. Further, a new second order GE strategy is proposed to incorporate curvature information, which enjoys theoretical advantage over the first order ones. Besides, this paper also provides a lower bound of Linear-optimization Oracle (LO) queried to achieve an approximate stationary point. Simulation studies validate our analysis under various parameter settings.

The communication overhead has become a significant bottleneck in data-parallel network with the increasing of model size and data samples. In this work, we propose a new algorithm LPC-SVRG with quantized gradients and its acceleration ALPC-SVRG to effectively reduce the communication complexity while maintaining the same convergence as the unquantized algorithms. Specifically, we formulate the heuristic gradient clipping technique within the quantization scheme and show that unbiased quantization methods in related works [3, 33, 38] are special cases of ours. We introduce double sampling in the accelerated algorithm ALPC-SVRG to fully combine the gradients of full-precision and low-precision, and then achieve acceleration with fewer communication overhead. Our analysis focuses on the nonsmooth composite problem, which makes our algorithms more general. The experiments on linear models and deep neural networks validate the effectiveness of our algorithms.

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to enforce the class-level distribution alignment across the source and target domains. These methods, however, are vulnerable to the error accumulation and thus incapable of preserving cross-domain category consistency, as the pseudo-labeling accuracy is not guaranteed explicitly. In this paper, we propose the Progressive Feature Alignment Network (PFAN) to align the discriminative features across domains progressively and effectively, via exploiting the intra-class variation in the target domain. To be specific, we first develop an Easy-to-Hard Transfer Strategy (EHTS) and an Adaptive Prototype Alignment (APA) step to train our model iteratively and alternatively. Moreover, upon observing that a good domain adaptation usually requires a non-saturated source classifier, we consider a simple yet efficient way to retard the convergence speed of the source classification loss by further involving a temperature variate into the soft-max function. The extensive experimental results reveal that the proposed PFAN exceeds the state-of-the-art performance on three UDA datasets.

Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using GraphConvolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14(49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships.

Fatorization machines (FM) are a popular model class to learn pairwise interactions by a low-rank approximation. Different from existing FM-based approaches which use a fixed rank for all features, this paper proposes a Rank-Aware FM (RaFM) model which adopts pairwise interactions from embeddings with different ranks. The proposed model achieves a better performance on real-world datasets where different features have significantly varying frequencies of occurrences. Moreover, we prove that the RaFM model can be stored, evaluated, and trained as efficiently as one single FM, and under some reasonable conditions it can be even significantly more efficient than FM. RaFM improves the performance of FMs in both regression tasks and classification tasks while incurring less computational burden, therefore also has attractive potential in industrial applications.

Deep networks have achieved impressive performance in various domains, but their applications are largely limited by the prohibitive computational overhead. In this paper, we propose a novel algorithm, namely collaborative channel pruning (CCP), to reduce the computational overhead with negligible performance degradation. The joint impact of pruned/preserved channels on the loss function is quantitatively analyzed, and such interchannel dependency is exploited to determine which channels to be pruned. The channel selection problem is then reformulated as a constrained 0-1 quadratic optimization problem, and the Hessian matrix, which is essential in constructing the above optimization, can be efficiently approximated. Empirical evaluation on two benchmark data sets indicates that our proposed CCP algorithm achieves higher classification accuracy with similar computational complexity than other stateof-the-art channel pruning algorithms

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. As a result, the proposed approach not only addresses the challenge via the knowledge customization to different clusters of tasks, but also preserves knowledge generalization among a cluster of similar tasks. To tackle the changing of task relationship, in addition, we extend the hierarchical structure to a continual learning environment. The experimental results show that our approach can achieve state-of-the-art performance in both toy-regression and few-shot image classification problems.

There has been a prominent emergence of work on video prediction, aiming to extrapolate the future video frames from the past. Existing temporal-based methods are limited to certain numbers of frames. In this paper, we study video prediction from a single still image in the facial expression domain, a.k.a, facial image-to-video translation. Our main approach, dubbed AffineGAN, associates each facial image with an expression intensity and leverages an affine transformation in the latent space. AffineGAN allows users to control the number of frames to predict as well as the expression intensity for each of them. Unlike previous intensity-based methods, We derive an inverse formulation to the affine transformation, enabling automatic inference of the facial expression intensities from videos --- manual annotation is not only tedious but also ambiguous as people express in various ways and have different opinions about the intensity of a facial image. Both quantitative and qualitative results verify the superiority of AffineGAN over the state of the arts. Notably, in a Turing test with web faces, more than 50% of the facial expression videos generated by AffineGAN are considered real by the Amazon Mechanical Turk workers. This work could improve users' communication experience by enabling them to conveniently and creatively produce expression GIFs, which are popular art forms in online messaging and social networks.

Dynamic Time Warping (DTW) is widely used as a similarity measure in various domains. Due to its invariance against warping in the time axis, DTW provides more meaningful discrepancy measurements between two signals than other dis- tance measures. In this paper, we propose a novel component in an artificial neural network. In contrast to the previous successful usage of DTW as a loss function, the proposed framework leverages DTW to obtain a better feature extraction. For the first time, the DTW loss is theoretically analyzed, and a stochastic backpropogation scheme is proposed to improve the accuracy and efficiency of the DTW learning. We also demonstrate that the proposed framework can be used as a data analysis tool to perform data decomposition.

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods. However, even a well-searched architecture may still contain many non-significant or redundant modules or operations (e.g., convolution or pooling), which may not only incur substantial memory consumption and computation cost but also deteriorate the performance. Thus, it is necessary to optimize the operations inside an architecture to improve the performance without introducing extra computation cost. Unfortunately, such a constrained optimization problem is NP-hard. To make the problem feasible, we cast the optimization problem into a Markov decision process (MDP) and seek to learn a Neural Architecture Transformer (NAT) to replace the redundant operations with the more computationally efficient ones (e.g., skip connection or directly removing the connection). Based on MDP, we learn NAT by exploiting reinforcement learning to obtain the optimization policies w.r.t. different architectures. To verify the effectiveness of the proposed strategies, we apply NAT on both hand-crafted architectures and NAS based architectures. Extensive experiments on two benchmark datasets, i.e., CIFAR-10 and ImageNet, demonstrate that the transformed architecture by NAT significantly outperforms both its original form and those architectures optimized by existing methods.

Bayesian optimisation is a popular technique for hyperparameter learning but typically requires initial exploration even in cases where similar prior tasks have been solved. We propose to transfer information across tasks using learnt representations of training datasets used in those tasks. This results in a joint Gaussian process model on hyperparameters and data representations. Representations make use of the framework of distribution embeddings into reproducing kernel Hilbert spaces. The developed method has a faster convergence compared to existing baselines, in some cases requiring only a few evaluations of the target objective.

This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervisions, LfO is more practical in leveraging previously inapplicable resources (e.g., videos), yet more challenging due to the incomplete expert guidance. In this paper, we investigate LfO and its difference with LfD in both theoretical and practical perspectives. We first prove that the gap between LfD and LfO actually lies in the disagreement of inverse dynamics models between the imitator and expert, if following the modeling approach of GAIL. More importantly, the upper bound of this gap is revealed by a negative causal entropy which can be minimized in a model-free way. We term our method as Inverse-Dynamics-Disagreement-Minimization (IDDM) which enhances the conventional LfO method through further bridging the gap to LfD. Considerable empirical results on challenging benchmarks indicate that our method attains consistent improvements over other LfO counterparts.

Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a protein in a protein-protein interaction network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. For example, in a social network, a group of people with shared interests forms a user group, whereas a number of user groups are interconnected via interactions or common members. We study the node classification problem in the hierarchical graph where a “node” is a graph instance, e.g., a user group in the above example. As labels are usually limited in real-world data, we design two novel semi-supervised solutions named SEmi-supervised grAph cLassification via Cautious/Active Iteration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative framework that takes turns to build or update two classifiers, one working at the graph instance level and the other at the hierarchical graph level. To simplify the representation of the hierarchical graph, we propose a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors. Through experiments on synthetic data and Tencent QQ group data, we demonstrate that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations.

Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity and (ii) weighted misclassification cost. However, previous existing methods only considered first-order information of data stream. It is insufficient in practice, since many recent studies have proved that incorporating second-order information enhances the prediction performance of classification models. Thus, we propose a family of cost-sensitive online classification algorithms with adaptive regularization in this paper. We theoretically analyze the proposed algorithms and empirically validate their effectiveness and properties in extensive experiments. Then, for better trade off between the performance and efficiency, we further introduce the sketching technique into our algorithms, which significantly accelerates the computational speed with quite slight performance loss. Finally, we apply our algorithms to tackle several online anomaly detection tasks from real world. Promising results prove that the proposed algorithms are effective and efficient in solving cost-sensitive online classification problems in various real-world domains.

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efficiently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrated the superior performance improvement on both convergence speed and predictive accuracy.

End-to-end optimization of multi-instance learning (MIL) using neural networks is an important problem with many applications, in which a core issue is how to design a permutation-invariant pooling function without losing much instance-level information. Inspired by the dynamic routing in recent capsule networks, we propose a novel dynamic pooling function for MIL. It is an adaptive scheme for both key instance selection and modeling the contextual information among instances in a bag. The dynamic pooling iteratively updates the instance contribution to its bag. It is permutation-invariant and can interpret instance-to-bag relationship. The proposed dynamic pooling based multi-instance neural network has been validated on many MIL tasks and outperforms other MIL methods.

Despite the recent success of end-to-end learned representations, hand-crafted optical flow features are still widely used in video analysis tasks. To fill this gap, we propose TVNet, a novel end-to-end trainable neural network, to learn optical-flow-like features from data. TVNet subsumes a specific optical flow solver, the TV-L1 method, and is initialized by unfolding its optimization iterations as neural layers. TVNet can therefore be used directly without any extra learning. Moreover, it can be naturally concatenated with other task-specific networks to formulate an end-to-end architecture, thus making our method more efficient than current multi-stage approaches by avoiding the need to pre-compute and store features on disk. Finally, the parameters of the TVNet can be further fine-tuned by end-to-end training. This enables TVNet to learn richer and task-specific patterns beyond exact optical flow. Extensive experiments on two action recognition benchmarks verify the effectiveness of the proposed approach. Our TVNet achieves better accuracies than all compared methods, while being competitive with the fastest counterpart in terms of features extraction time.

Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.

In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain. Determining the optimal one that maximizes the performance improvement requires either exhaustive exploration or considerable expertise. Meanwhile, it is widely accepted in educational psychology that human beings improve transfer learning skills of deciding what to transfer through meta-cognitive reflection on inductive transfer learning practices. Motivated by this, we propose a novel transfer learning framework known as Learning to Transfer (L2T) to automatically determine what and how to transfer are the best by leveraging previous transfer learning experiences. We establish the L2T framework in two stages: 1) we learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer are the best for a future pair of domains by optimizing the reflection function. We also theoretically analyse the algorithmic stability and generalization bound of L2T, and empirically demonstrate its superiority over several state-of-the-art transfer learning algorithms.

Large-scale distributed optimization is of great importance in various applications. For data-parallel based distributed learning, the inter-node gradient communication often becomes the performance bottleneck. In this paper, we propose the error compensated quantized stochastic gradient descent algorithm to improve the training efficiency. Local gradients are quantized to reduce the communication overhead, and accumulated quantization error is utilized to speed up the convergence. Furthermore, we present theoretical analysis on the convergence behaviour, and demonstrate its advantage over competitors. Extensive experiments indicate that our algorithm can compress gradients by a factor of up to two magnitudes without performance degradation.

This paper investigates Online Active Learning (OAL) for imbalanced unlabeled datastream, where only a budget of labels can be queried to optimize some cost-sensitive performance measure. OAL can solve many real-world problems, such as anomaly detection in healthcare, finance and network security. In these problems, there are two key challenges: the query budget is often limited; the ratio between two classes is highly imbalanced. To address these challenges, existing work of OAL adopts either asymmetric losses or queries (an isolated asymmetric strategy) to tackle the imbalance, and uses first-order methods to optimize the cost-sensitive measure. However, they may incur two deficiencies: (1) the poor ability in handling imbalanced data due to the isolated asymmetric strategy; (2) relative slow convergence rate due to the first-order optimization. In this paper, we propose a novel Online Adaptive Asymmetric Active (OA3) learning algorithm, which is based on a new asymmetric strategy (merging both the asymmetric losses and queries strategies), and second-order optimization. We theoretically analyze its bounds, and also empirically evaluate it on four real-world online anomaly detection tasks. Promising results confirm the effectiveness and robustness of the proposed algorithm in various application domains.

Dense event captioning aims to detect and describe all events of interest contained in a video. Despite the advanced development in this area, existing methods tackle this task by making use of dense temporal annotations, which is dramatically source-consuming. This paper formulates a new problem: weakly supervised dense event captioning, which does not require temporal segment annotations for model training. Our solution is based on the one-to-one correspondence assumption, each caption describes one temporal segment, and each temporal segment has one caption, which holds in current benchmark datasets and most real world cases. We decompose the problem into a pair of dual problems: event captioning and sentence localization and present a cycle system to train our model. Extensive experimental results are provided to demonstrate the ability of our model on both dense event captioning and sentence localization in videos.

Graph Convolutional Networks (GCNs) have become a crucial tool on learning representations of graph vertices. The main challenge of adapting GCNs on large-scale graphs is the scalability issue that it incurs heavy cost both in computation and memory due to the uncontrollable neighborhood expansion across layers. In this paper, we accelerate the training of GCNs through developing an adaptive layer-wise sampling method. By constructing the network layer by layer in a top-down passway, we sample the lower layer conditioned on the top one, where the sampled neighborhoods are shared by different parent nodes and the over expansion is avoided owing to the fixed-size sampling. More importantly, the proposed sampler is adaptive and applicable for explicit variance reduction, which in turn enhances the training of our method. Furthermore, we propose a novel and economical approach to promote the message passing over distant nodes by applying skip connections. Intensive experiments on several benchmarks verify the effectiveness of our method regarding the classification accuracy while enjoying faster convergence speed.

Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. To overcome these drawbacks, we investigate a simple-yet-effective method, called discrimination-aware channel pruning, to choose those channels that really contribute to discriminative power. To this end, we introduce additional losses into the network to increase the discriminative power of intermediate layers and then select the most discriminative channels for each layer by considering the additional loss and the reconstruction error. Last, we propose a greedy algorithm to conduct channel selection and parameter optimization in an iterative way. Extensive experiments demonstrate the effectiveness of our method. For example, on ILSVRC-12, our pruned ResNet-50 with 30% reduction of channels even outperforms the original model by 0.39% in top-1 accuracy.

Factorization Machine (FM) is a supervised learning approach with a powerful capability of feature engineering. It yields state-of-the-art performances in various batch learning tasks where all the training data is made available prior to the training. However, in real-world applications where the data arrives sequentially in a streaming manner, the high cost of re-training with batch learning algorithms has posed formidable challenges in the online learning scenario. The initial challenge is that no prior formulations of FM could directly fulfill the requirements in Online Convex Optimization (OCO) -- the paramount framework for online learning algorithm design. To address this aforementioned challenge, we invent a new convexification scheme leading to a Compact Convexified FM (CCFM) that seamlessly meets the requirements in OCO. However for learning Compact Convexified FM (CCFM) in the online learning settings, most existing algorithms suffer from expensive projection operations. To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm that eschews the projection operation with efficient linear optimization steps. In support of the proposed OCCFM in terms of its theoretical foundation, we prove that the developed algorithm achieves a sub-linear regret bound. To evaluate the empirical performance of OCCFM, we conduct extensive experiments on 6 real-world datasets for online regression and online classification tasks. The experimental results show that OCCFM outperforms the state-of-art online learning methods for FM.

Similarity measure is an essential component in image registration. In this article, we propose a novel similarity measure for registration of two or more images. The proposed method is motivated by the fact that optimally registered images can be sparsified hierarchically in the gradient domain and frequency domain with the separation of sparse errors. One of the key advantages of the proposed similarity measure is its robustness in dealing with severe intensity distortions, which widely exist on medical images, remotely sensed images and natural photos due to differences of acquisition modalities or illumination conditions. Two efficient algorithms are proposed to solve the batch image registration and pair registration problems in a unified framework. We have validated our method on extensive and challenging data sets. The experimental results demonstrate the robustness, accuracy and efficiency of our method over nine traditional and state-of-the-art algorithms on synthetic images and a wide range of real-world applications.

Recently with the explosive growth of visual content on the Internet, large-scale image search has attracted intensive attention. It has been shown that mapping high-dimensional image descriptors to compact binary codes can lead to considerable efficiency gains in both storage and performing similarity computation of images. However, most existing methods still suffer from expensive training devoted to large-scale binary code learning. To address this issue, we propose a sub-selection based matrix manipulation algorithm, which can significantly reduce the computational cost of code learning. As case studies, we apply the sub-selection algorithm to several popular quantization techniques including cases using linear and nonlinear mappings. Crucially, we can justify the resulting sub-selective quantization by proving its theoretic properties. Extensive experiments are carried out on three image benchmarks with up to one million samples, corroborating the efficacy of the sub-selective quantization method in terms of image retrieval.

Object proposals generation plays an important role in computer vision. A good object proposals generation model should assign obviously high and low objectness score to the window that contains complete objects and incomplete objects, respectively. However, some existing methods such as local contrast based models usually fail to satisfy this requirement. In this letter, we propose MBDSal Box, a minimum barrier distance (MBD) based saliency box for locating object proposals. MBDSal Box consists of three components: item: First, a window saliency computation module that calculates the MBD saliency of each sliding window; second, a window refinement module that provides more accurate bounding boxes by a marker based watershed algorithm; third, a window scoring module which combines multiple features to compute the final objectness score. The experimental results carried on PASCAL VOC 2007 and Microsoft COCO 2014 datasets show that our model achieves better performance than the state-of-the-art models with competitive speed.

Structured sparse learning has become a popular and mature research field. Among all structured sparse models, we found an interesting fact that most structured sparse properties could be captured by convolution operators, most famous ones being total variation and wavelet sparsity. This finding has naturally brought us to a generalization termed as Convolutional Sparsity. While this generalization bridges the convolution and sparse learning theory, we are able to propose a general, efficient, hyperparameter-free optimization algorithm framework for convolutional sparse models, thanks to the analysis theory of convolution operators. The convergence of the general, hyperparameter-free algorithm has been comprehensively analyzed, with a non-ergodic rate of O(1/ϵ2) and ergodic rate of O(1/ϵ), where ϵ is the desired accuracy. Extensive experiments confirm the superior performance of our general algorithm in various convolutional sparse models, even better than some application-specialistic algorithms.

We propose a fast first-order method to solve multi-term nonsmooth composite convex minimization problems by employing a recent proximal average approximation technique and a novel adaptive parameter tuning technique. Thanks to this powerful parameter tuning technique, the proximal gradient step can be performed with a much larger stepsize in the algorithm implementation compared with the prior PA-APG method, which is the core to enable significant improvements in practical performance. Moreover, by choosing the approximation parameter adaptively, the proposed method is shown to enjoy the O(1/k) iteration complexity theoretically without needing any extra computational cost, while the PA-APG method incurs much more iterations for convergence. The preliminary experimental results on overlapping group Lasso and graph-guided fused Lasso problems confirm our theoretic claim well, and indicate that the proposed method is almost five times faster than the state-of-the-art PA-APG method and therefore suitable for higher-precision required optimization.

Image-based precision medicine techniques can be used to better treat cancer patients. However, the gigapixel resolution of Whole Slide Histopathological Images (WSIs) makes traditional survival models computationally impossible. These models usually adopt manually labeled discriminative patches from region of interests (ROIs) and are unable to directly learn discriminative patches from WSIs. We argue that only a small set of patches cannot fully represent the patients survival status due to the heterogeneity of tumor. Another challenge is that survival prediction usually comes with insufficient training patient samples. In this paper, we propose an effective Whole Slide Histopathological Images Survival Analysis framework (WSISA) to overcome above challenges. To exploit survival-discriminative patterns from WSIs, we first extract hundreds of patches from each WSI by adaptive sampling and then group these images into different clusters. Then we propose to train an aggregation model to make patient-level predictions based on cluster-level Deep Convolutional Survival (DeepConvSurv) prediction results. Different from existing state-of-the-arts image-based survival models which extract features using some patches from small regions of WSIs, the proposed framework can efficiently exploit and utilize all discriminative patterns in WSIs to predict patients survival status. To the best of our knowledge, this has not been shown before. We apply our method to the survival predictions of glioma and non-small-cell lung cancer using three datasets. Results demonstrate the proposed framework can significantly improve the prediction performance compared with the existing state-of-the-arts survival methods.

Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatio-temporal data in various disciplines. Though rich in modeling, analyzing LDSs is not free of difficulty, mainly because LDSs do not comply with Euclidean geometry and hence conventional learning techniques can not be applied directly. In this paper, we propose an efficient projected gradient descent method to minimize a general form of a loss function and demonstrate how clustering and sparse coding with LDSs can be solved by the proposed method efficiently. To this end, we first derive a novel canonical form for representing the parameters of an LDS, and then show how gradient-descent updates through the projection on the space of LDSs can be achieved dexterously. In contrast to previous studies, our solution avoids any approximation in LDS modeling or during the optimization process. Extensive experiments reveal the superior performance of the proposed method in terms of the convergence and classification accuracy over state-of-the-art techniques.

In the past decades, Spectral Clustering (SC) has become one of the most effective clustering approaches. Although it has been widely used, one significant drawback of SC is its expensive computation cost. Many efforts have been devoted to accelerating SC algorithms and promising results have been achieved. However, most of the existing algorithms rely on the assumption that data can be stored in the computer memory. When data cannot fit in the memory, these algorithms will suffer severe performance degradations. In order to overcome this issue, we propose a novel sequential SC algorithm for tackling large-scale clustering with limited computational resources, \textit{e.g.}, memory. We begin with investigating an effective way of approximating the graph affinity matrix via leveraging a bipartite graph. Then we choose a smart graph construction and optimization strategy to avoid random access to data. These efforts lead to an efficient SC algorithm whose memory usage is independent of the number of input data points. Extensive experiments carried out on large datasets demonstrate that the proposed sequential SC algorithm is up to a thousand times faster than the state-of-the-arts.

Traditional Cox proportional hazard model for survival analysis are based on structured features like patients' sex, smoke years, BMI, etc. With the development of medical imaging technology, more and more unstructured medical images are available for diagnosis, treatment and survival analysis. Traditional survival models utilize these unstructured images by extracting human-designed features from them. However, we argue that those hand-crafted features have limited abilities in representing highly abstract information. In this paper, we for the first time develop a deep convolutional neural network for survival analysis (DeepConvSurv) with pathological images. The deep layers in our model could represent more abstract information compared with hand-crafted features from the images. Hence, it will improve the survival prediction performance. From our extensive experiments on the National Lung Screening Trial (NLST) lung cancer data, we show that the proposed DeepConvSurv model improves significantly compared with four state-of-the-art methods.

Imaging-genetic data mapping is important for clinical outcome prediction like survival analysis. In this paper, we propose a supervised conditional Gaussian graphical model (SuperCGGM) to uncover survival associated mapping between pathological images and genetic data. The proposed method integrates heterogeneous modal data into the survival model by weighted projection within the data. To obtain a sparse solution, we employ l-1 regularization to the partial log likelihood loss function and propose a cyclic coordinate ascent algorithm to solve it. It also gives a way to bridge the gap between the supervised model with conditional Gaussian graphical model (CGGM). Compared to nine state-of-the-art methods like SuperPCA, CGGM, etc., our method is superior due to its ability of integrating diverse information from heterogeneous modal data in a supervised way. The extensive experiments also show the strong power of SuperCGGM in mapping survival associated image and gene expression signatures.

Group sparse representation (GSR) exploits group structure in data and works well on many problems. However, the group structure must be manually given in advance. In many practical scenarios such as classification, samples are grouped according to their labels. Constructing a consistent group structure in such cases is not easy. The reasons are: 1) samples may be incorrectly labeled; and 2) label assigning in big data is time-consuming and expensive. In this paper, we propose and formulate a new problem, semi-supervised group sparse representation (SS-GSR) to support group sparse representation among both labeled and unlabeled data, while learning a more robust group structure, which can be further exploited to more effectively represent other unlabeled data. We develop a model to tackle the SS-GSR problem, based on the manifold assumption in subspace segmentation that samples in the same group lie close in feature space and span the same subspace. We also propose an alternating algorithm to solve the model. Finally, we validate the model via extensive experiments.

In this paper, we propose an algorithm for missing value recovery of visual data such as image or video. These missing values may result from the corruption in acquisition process, or user-specified unexpected outliers. This problem exists in wide range of applications. We use the nuclear norm (NN) regularization to enforce the global consistency of the image, while the total variation (TV) regularization is used to encourage the locally consistent in image intensity domain. This model can be applied in very challenging scenarios, where only very small amount of data is available. However, it is very difficult to efficiently solve these two regularizations simultaneously by convex programming due to its composite structure and non-smoothness. To this end, we propose an efficient proximal-splitting algorithm for joint NN/TV minimization. The proposed algorithm is theoretically guaranteed to achieve a convergence rate of O(1/N) for N iterations, which is much faster than O(1/√N) by the black-box first-order method for solving the non-smooth optimization problem. In our experiments, we demonstrate the superior performance of our algorithm on image completion compared with seven state-of-the-art algorithms.

This paper addresses the problem of facial landmark localization and tracking from a single camera. We present a two-stage cascaded deformable shape model to effectively and efficiently localize facial landmarks with large head pose variations. In initialization stage, we propose a group sparse optimized mixture model to automatically select the most salient facial landmarks. By introducing 3D face shape model, we apply procrustes analysis to provide pose-aware landmark initialization. In landmark localization stage, the first step uses mean-shift local search with constrained local model to rapidly approach the global optimum. The second step uses component-wise active contours to discriminatively refine the subtle shape variation. Our framework simultaneously handles face detection, pose-robust landmark localization and tracking in real time. Extensive experiments are conducted on both laboratory environmental databases and face-in-the-wild databases. The results reveal that our approach consistently outperforms state-of-the-art methods for face alignment and tracking.

In this paper, we address the problem of large-scale multi-view spectral clustering. In many real-world applications, data can be represented in various heterogeneous features or views. Different views often provide different aspects of information that are complementary to each other. Several previous methods of clustering have demonstrated that better accuracy can be achieved using integrated information of all the views than just using each view individually. One important class of such methods is multi-view spectral clustering, which is based on graph Laplacian. However, existing methods are not applicable to large-scale problem for their high computational complexity. To this end, we propose a novel large-scale multi-view spectral clustering approach based on the bipartite graph. Our method uses local manifold fusion to integrate heterogeneous features. To improve efficiency, we approximate the similarity graphs using bipartite graphs. Furthermore, we show that our method can be easily extended to handle the out-of-sample problem. Extensive experimental results on five benchmark datasets demonstrate the effectiveness and efficiency of the proposed method, where our method runs up to nearly 3000 times faster than the state-of-the-art methods.

The definition of the similarity measure is an essential component in image registration. In this paper, we propose a novel similarity measure for registration of two or more images. The proposed method is motivated by that the optimally registered images can be deeply sparsified in the gradient domain and frequency domain, with the separation of a sparse tensor of errors. One of the key advantages of the proposed similarity measure is its robustness to severe intensity distortions, which widely exist on medical images, remotely sensed images and natural photos due to the difference of acquisition modalities or illumination conditions. Two efficient algorithms are proposed to solve the batch image registration and pair registration problems in a unified framework. We validate our method on extensive challenging datasets. The experimental results demonstrate the robustness, accuracy and efficiency of our method over 9 traditional and state-of-the-art algorithms on synthetic images and a wide range of real-world applications.

Detecting deception in interpersonal dialog is challenging since deceivers take advantage of the give-and-take of interaction to adapt to any sign of skepticism in an interlocutor's verbal and nonverbal feedback. Human detection accuracy is poor, often with no better than chance performance. In this investigation, we consider whether automated methods can produce better results and if emphasizing the possible disruption in interactional synchrony can signal whether an interactant is truthful or deceptive. We propose a data-driven and unobtrusive framework using visual cues that consists of face tracking, head movement detection, facial expression recognition, and interactional synchrony estimation. Analysis were conducted on 242 video samples from an experiment in which deceivers and truth-tellers interacted with professional interviewers either face-to-face or through computer mediation. Results revealed that the framework is able to automatically track head movements and expressions of both interlocutors to extract normalized meaningful synchrony features and to learn classification models for deception recognition. Further experiments show that these features reliably capture interactional synchrony and efficiently discriminate deception from truth.

In this paper, we present a new idea to analyze facial expression by exploring some common and specific information among different expressions. Inspired by the observation that only a few facial parts are active in expression disclosure (e.g., around mouth, eye), we try to discover the common and specific patches which are important to discriminate all the expressions and only a particular expression, respectively. A two-stage multitask sparse learning (MTSL) framework is proposed to efficiently locate those discriminative patches. In the first stage MTSL, expression recognition tasks are combined to located common patches. Each of the tasks aims to find dominant patches for each expression. Secondly, two related tasks, facial expression recognition and face verification tasks, are coupled to learn specific facial patches for individual expression. The two-stage patch learning is performed on patches sampled by multiscale strategy. Extensive experiments validate the existence and significance of common and specific patches. Utilizing these learned patches, we achieve superior performances on expression recognition compared to the state-of-the-arts.

In this paper, we propose a novel method for image fusion with a high-resolution panchromatic image and a low-resolution multispectral (Ms) image at the same geographical location. The fusion is formulated as a convex optimization problem which minimizes a linear combination of a least-squares fitting term and a dynamic gradient sparsity regularizer. The former is to preserve accurate spectral information of the Ms image, while the latter is to keep sharp edges of the high-resolution panchromatic image. We further propose to simultaneously register the two images during the fusing process, which is naturally achieved by virtue of the dynamic gradient sparsity property. An efficient algorithm is then devised to solve the optimization problem, accomplishing a linear computational complexity in the size of the output image in each iteration. We compare our method against six state-of-the-art image fusion methods on Ms image data sets from four satellites. Extensive experimental results demonstrate that the proposed method substantially outperforms the others in terms of both spatial and spectral qualities. We also show that our method can provide high-quality products from coarsely registered real-world IKONOS data sets. Finally, a MATLAB implementation is provided to facilitate future research.

Recently with the explosive growth of visual content on the Internet, large-scale image search has attracted intensive attention. It has been shown that mapping highdimensional image descriptors to compact binary codes can lead to considerable efficiency gains in both storage and similarity computation of images. However, most existing methods still suffer from expensive training devoted to large-scale binary code learning. To address this issue, we propose a sub-selection based matrix manipulation algorithm which can significantly reduce the computational cost of code learning. As case studies, we apply the sub-selection algorithm to two popular quantization techniques PCA Quantization (PCAQ) and Iterative Quantization (ITQ). Crucially, we can justify the resulting sub-selective quantization by proving its theoretic properties. Extensive experiments are carried out on three image benchmarks with up to one million samples, corroborating the efficacy of the sub-selective quantization method in terms of image retrieval.

In this paper, we propose a novel algorithm for structured sparsity reconstruction. This algorithm is based on the iterative reweighted least squares (IRLS) framework, and accelerated by the preconditioned conjugate gradient method. The convergence rate of the proposed algorithm is almost the same as that of the traditional IRLS algorithms, that is, exponentially fast. Moreover, with the devised preconditioner, the computational cost for each iteration is significantly less than that of traditional IRLS algorithms, which makes it feasible for large scale problems. Besides the fast convergence, this algorithm can be flexibly applied to standard sparsity, group sparsity, and overlapping group sparsity problems. Experiments are conducted on a practical application compressive sensing magnetic resonance imaging. Results demonstrate that the proposed algorithm achieves superior performance over 9 state-of-the-art algorithms in terms of both accuracy and computational cost.

In this paper, we propose a novel method for image fusion from a high resolution panchromatic image and a low resolution multispectral image at the same geographical location. Different from previous methods, we do not make any assumption about the upsampled multispectral image, but only assume that the fused image after downsampling should be close to the original multispectral image. This is a severely ill-posed problem and a dynamic gradient sparsity penalty is thus proposed for regularization. Incorporating the intra- correlations of different bands, this penalty can effectively exploit the prior information (e.g. sharp boundaries) from the panchromatic image. A new convex optimization algorithm is proposed to efficiently solve this problem. Extensive experiments on four multispectral datasets demonstrate that the proposed method significantly outperforms the state-of-the-arts in terms of both spatial and spectral qualities.

This paper presents a method to perform sparse representation based classification (SRC) in a more accurate and efficient way. In this method, training data is first mapped into different feature spaces and multiple dictionaries are built by utilizing a Fisher discriminative based method. These dictionaries can be considered as efficient representations of the data which are then used in a multimodal SRC framework to classify test samples. In comparison to the original SRC method where only one modality of training space is utilized, the proposed method classifies test samples in a more accurate and efficient way. Experimental results from two different face datasets show that the proposed multimodal method has higher recognition rate compared to single-modality SRC based methods. The accuracy of the proposed method is also compared to other multi-modality classifiers and the results confirm that higher recognition rates are achieved in comparison with other common classification algorithms.

Sparsity based techniques have become very popular in machine learning, medical imaging and computer vision. Recently, with the emerging and development of structured sparsity, signals can be recovered more accurately. However, solving structured sparsity problems often involves much higher computational complexity. Few of existing works can reduce the computational complexity of such problems. Especially for overlapping group sparsity, the computational complexity for each entry is linear to the degree of overlapping, making it infeasible for large-scale problems. In this paper, we propose novel algorithms to efficiently address this issue, where the computational complexity for each entry is always O(1) and independent to the degree of overlapping. Experiments on 1D signal and 2D image demonstrate the effectiveness and efficiency of our methods. This work may inspire more scalable algorithms for structured sparsity.

In this paper, we present an efficient and robust image representation method that can handle misalignment, occlusion and big noises with lower computational cost. It is motivated by the sub-selection technique, which uses partial observations to efficiently approximate the original high dimensional problems. While it is very efficient, their method can not handle many real problems in practical applications, such as misalignment, occlusion and big noises. To this end, we propose a robust sub-representation method, which can effectively handle these problems with an efficient scheme. While its performance guarantee was theoretically proved, numerous experiments on practical applications have further demonstrated that the proposed method can lead to significant performance improvement in terms of speed and accuracy.

Head pose estimation from images is a challenging task with extensive applications. It has been attracting research attentions over decades and numerous approaches have been proposed. Among them, manifold embedding based methods, which assume that the pose variations lie on a low-dimensional manifold embedded in the high-dimensional feature space, have achieved great success. However, previous manifold embedding based methods have two drawbacks: first, they lack the capability to simultaneously deal with multiple pose-unrelated factors in a uniform way, second, they suffer from limited representation ability for out-of-sample testing inputs. In this paper we propose a novel head pose estimation method to address these problems. By learning the mapping from a uniform geometry representation to individual instance manifolds, this approach allows us to parameterize various pose-unrelated factors under a uniform framework. Our approach is a generative model which guarantees the reasonable and effective representation of new testing input. Besides, by employing eigen instance bases instead of full instance bases arisen from the training data, we can effectively compact the size of the trained model and significantly simplify the computational complexity of the testing process. Experiments on public databases such as CMU-MultiPIE and BU-4DFE, and quantitative comparisons with other state-of-the-art methods show the effectiveness of our approach.

Feature matching is an important problem and has extensive uses in computer vision. However, existing feature matching methods support either a specific or a small set of transformation models. In this paper, we propose a unified feature matching framework which supports a large family of transformation models. We call the family of transformation models the affine-function family, in which all transformations can be expressed by affine functions with convex constraints. In this framework, the goal is to recover transformation parameters for every feature point in a template point set to calculate their optimal matching positions in an input image. Given pairwise feature dissimilarity values between all points in the template set and the input image, we create a convex dissimilarity function for each template point. Composition of such convex functions with any transformation model in the affine-function family is shown to have an equivalent convex optimization form that can be optimized efficiently. Four example transformation models in the affine-function family are introduced to show the flexibility of our proposed framework. Our framework achieves 0.0 percent matching errors for both CMU House and Hotel sequences following the experimental setup in [6].

Diffuse optical tomography (DOT) is a noninvasive technique which measures hemodynamic changes in the tissue with near infrared light, which has been increasingly used to study brain functions. Due to the nature of light propagation in the tissue, the reconstruction problem is severely ill-posed. For linearized DOT problems, sparsity regularization has achieved promising results over conventional Tikhonov regularization in recent experimental research. As extensions to standard sparsity, it is widely known that structured sparsity based methods are often superior in terms of reconstruction accuracy, when the data follows some structures. In this paper, we exploit the structured sparsity of diffuse optical images. Based on the functional specialization of the brain, it is observed that the in vivo absorption changes caused by a specific brain function would be clustered in certain region(s) and not randomly distributed. Thus, a new algorithm is proposed for this clustered sparsity reconstruction (CSR). Results of numerical simulations and phantom experiments have demonstrated the superiority of the proposed method over the state-of-the-art methods. An example from human in vivo measurements further confirmed the advantages of the proposed CSR method.

This paper addresses the problem of facial landmark localization and tracking from a single camera. We present a two-stage cascaded deformable shape model to effectively and efficiently localize facial landmarks with large head pose variations. For face detection, we propose a group sparse learning method to automatically select the most salient facial landmarks. By introducing 3D face shape model, we use procrustes analysis to achieve pose-free facial landmark initialization. For deformation, the first step uses mean-shift local search with constrained local model to rapidly approach the global optimum. The second step uses component-wise active contours to discriminatively refine the subtle shape variation. Our framework can simultaneously handle face detection, pose-free landmark localization and tracking in real time. Extensive experiments are conducted on both laboratory environmental face databases and face-in-the-wild databases. All results demonstrate that our approach has certain advantages over state-of-the-art methods in handling pose variations.

Online learned tracking is widely used for its adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent literature demonstrates that appropriate combinations of trackers can help balance the stability and flexibility requirements. We have developed a robust tracking algorithm using a local sparse appearance model (SPT) and K-Selection. A static sparse dictionary and a dynamically updated online dictionary basis distribution are used to model the target appearance. A novel sparse representation-based voting map and a sparse constraint regularized mean shift are proposed to track the object robustly. Besides these contributions, we also introduce a new selection-based dictionary learning algorithm with a locally constrained sparse representation, called K-Selection. Based on a set of comprehensive experiments, our algorithm has demonstrated better performance than alternatives reported in the recent literature.

In this paper, we present a new idea to analyze facial expression by exploring some common and specific information among different expressions. Inspired by the observation that only a few facial parts are active in expression disclosure (e.g., around mouth, eye), we try to discover the common and specific patches which are important to discriminate all the expressions and only a particular expression, respectively. A two-stage multi-task sparse learning (MTSL) framework is proposed to efficiently locate those discriminative patches. In the first stage MTSL, expression recognition tasks, each of which aims to find dominant patches for each expression, are combined to located common patches. Second, two related tasks, facial expression recognition and face verification tasks, are coupled to learn specific facial patches for individual expression. Extensive experiments validate the existence and significance of common and specific patches. Utilizing these learned patches, we achieve superior performances on expression recognition compared to the state-of-the-arts.

We address the problem of tracking human faces under various poses and lighting conditions. Reliable face tracking is a challenging task. The shapes of the faces may change dramatically with various identities, poses and expressions. Moreover, poor lighting conditions may cause a low contrast image or cast shadows on faces, which will significantly degrade the performance of the tracking system. In this paper, we develop a framework to track face shapes by using both color and depth information. Since the faces in various poses lie on a nonlinear manifold, we build piecewise linear face models, each model covering a range of poses. The low-resolution depth image is captured by using Microsoft Kinect, and is used to predict head pose and generate extra constraints at the face boundary. Our experiments show that, by exploiting the depth information, the performance of the tracking system is significantly improved.

We develop a non-intrusive system for monitoring fatigue by tracking eyelids with a single web camera. Tracking slow eyelid closures is one of the most reliable ways to monitor fatigue during critical performance tasks. The challenges come from arbitrary head movement, occlusion, reflection of glasses, motion blurs, etc. We model the shape of eyes using a pair of parameterized parabolic curves, and fit the model in each frame to maximize the total likelihood of the eye regions. Our system is able to track face movement and fit eyelids reliably in real time. We test our system with videos captured from both alert and drowsy subjects. The experiment results prove the effectiveness of our system.

In Compressive Sensing Magnetic Resonance Imaging (CS-MRI), one can reconstruct a MR image with good quality from only a small number of measurements. This can significantly reduce MR scanning time. According to structured sparsity theory, the measurements can be further reduced to $\mathcal{O}(K+\log n)$ for tree-sparse data instead of $\mathcal{O}(K+K\log n)$ for standard $K$-sparse data with length $n$. However, few of existing algorithms has utilized this for CS-MRI, while most of them use Total Variation and wavelet sparse regularization. On the other side, some algorithms have been proposed for tree sparsity regularization, but few of them has validated the benefit of tree structure in CS-MRI. In this paper, we propose a fast convex optimization algorithm to improve CS-MRI. Wavelet sparsity, gradient sparsity and tree sparsity are all considered in our model for real MR images. The original complex problem is decomposed to three simpler subproblems then each of the subproblems can be efficiently solved with an iterative scheme. Numerous experiments have been conducted and show that the proposed algorithm outperforms the state-of-the-art CS-MRI algorithms, and gain better reconstructions results on real MR images than general tree based solvers or algorithms.

Automatically assigning relevant text keywords to images is an important problem. Many algorithms have been proposed in the past decade and achieved good performance. Efforts have focused upon model representations of keywords, whereas properties of features have not been well investigated. In most cases, a group of features is preselected, yet important feature properties are not well used to select features. In this paper, we introduce a regularization-based feature selection algorithm to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task. Using this group-sparsity-based method, the whole group of features [e.g., red green blue (RGB) or hue, saturation, and value (HSV)] is either selected or removed. Thus, we do not need to extract this group of features when new data comes. A novel approach is also proposed to iteratively obtain similar and dissimilar pairs from both the keyword similarity and the relevance feedback. Thus, keyword similarity is modeled in the annotation framework. We also show that our framework can be employed in image retrieval tasks by selecting different image pairs. Extensive experiments are designed to compare the performance between features, feature combinations, and regularization-based feature selection methods applied on the image annotation task, which gives insight into the properties of features in the image annotation task. The experimental results demonstrate that the group-sparsity-based method is more accurate and stable than others.

Online learned tracking is widely used for it's adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent literature demonstrates that appropriate combinations of trackers can help balance stability and flexibility requirements. We have developed a robust tracking algorithm using a local sparse appearance model (SPT). A static sparse dictionary and a dynamically online updated basis distribution model the target appearance. A novel sparse representation-based voting map and sparse constraint regularized mean-shift support the robust object tracking. Besides these contributions, we also introduce a new dictionary learning algorithm with a locally constrained sparse representation, called K-Selection. Based on a set of comprehensive experiments, our algorithm has demonstrated better performance than alternatives reported in the recent literature.

Image appearance cues are often used to derive object shapes, which is usually one of the key steps of image understanding tasks. However, when image appearance cues are weak or misleading, shape priors become critical to infer and refine the shape derived by these appearance cues. Effective modeling of shape priors is challenging because: 1) shape variation is complex and cannot always be modeled by a parametric probability distribution; 2) a shape instance derived from image appearance cues (input shape) may have gross errors; and 3) local details of the input shape are difficult to preserve if they are not statistically significant in the training data. In this paper we propose a novel Sparse Shape Composition model (SSC) to deal with these three challenges in a unified framework. In our method, training shapes are adaptively composed to infer/refine an input shape. The a-priori information is thus implicitly incorporated on-the-fly. Our model leverages two sparsity observations of the input shape instance: 1) the input shape can be approximately represented by a sparse linear combination of training shapes; 2) parts of the input shape may contain gross errors but such errors are usually sparse. Using L1 norm relaxation, our model is formulated as a convex optimization problem, which is solved by an efficient alternating minimization framework. Our method is extensively validated on two real world medical applications, 2D lung localization in X-ray images and 3D liver segmentation in low-dose CT scans. Compared to state-of-the-art methods, our model exhibits better performance in both studies.

This paper proposes a sparsity driven shape registration method for occluded facial feature localization. Most current shape registration methods search landmark locations which comply both shape model and local image appearances. However, if the shape is partially occluded, the above goal is inappropriate and often leads to distorted shape results. In this paper, we introduce an error term to rectify the locations of the occluded landmarks. Under the assumption that occlusion takes a small proportion of the shape, we propose a sparse optimization algorithm that iteratively approaches the optimal shape. The experiments in our synthesized face occlusion database prove the advantage of our method.

This paper presents a new eye localization method via Multiscale Sparse Dictionaries (MSD). We built a pyramid of dictionaries that models context information at multiple scales. Eye locations are estimated at each scale by fitting the image through sparse coefficients of the dictionary. By using context information, our method is robust to various eye appearances. The method also works efficiently since it avoids sliding a search window in the image during localization. The experiments in BioID database prove the effectiveness of our method.

In this paper, we propose a novel object matching method to match an object to its instance in an input scene image, where both the object template and the input scene image are represented by groups of feature points. We relax each template point's discrete feature cost function to create a convex function that can be optimized efficiently. Such continuous and convex functions with different regularization terms are able to create different convex optimization models handling objects undergoing (i) global transformation, (ii) locally affine transformation, and (iii) articulated transformation. These models can better constrain each template point's transformation and therefore generate more robust matching results. Unlike traditional object or feature matching methods with “hard” node-to-node results, our proposed method allows template points to be transformed to any location in the image plane. Such a property makes our method robust to feature point occlusion or mis-detection. Our extensive experiments demonstrate the robustness and flexibility of our method.

3D parametric deformable models have been used to extract volumetric object boundaries and they generate smooth boundary surfaces as results. However, in some segmentation cases, such as cerebral cortex with complex folds and creases, and human lung with high curvature boundary, parametric deformable models often suffer from over-smoothing or decreased mesh quality during model deformation. To address this problem, we propose a 3D Laplacian-driven parametric deformable model with a new internal force. Derived from a Mesh Laplacian, the internal force exerted on each control vertex can be decomposed into two orthogonal vectors based on the vertex's tangential plane. We then introduce a weighting function to control the contributions of the two vectors based on the model mesh's geometry. Deforming the new model is solving a linear system, so the new model can converge very efficiently. To validate the model's performance, we tested our method on various segmentation cases and compared our model with Finite Element and Level Set deformable models.

Automatically assigning relevant text keywords to images is an important problem. Many algorithms have been proposed in the past decade and achieved good performance. Efforts have focused upon model representations of keywords, but properties of features have not been well investigated. In most cases, a group of features is preselected, yet important feature properties are not well used to select features. In this paper, we introduce a regularization based feature selection algorithm to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task. A novel approach is also proposed to iteratively obtain similar and dissimilar pairs from both the keyword similarity and the relevance feedback. Thus keyword similarity is modeled in the annotation framework. Numerous experiments are designed to compare the performance between features, feature combinations and regularization based feature selection methods applied on the image annotation task, which gives insight into the properties of features in the image annotation task. The experimental results demonstrate that the group sparsity based method is more accurate and stable than others.

This paper investigates a new learning formulation called dynamic group sparsity. It is a natural extension of the standard sparsity concept in compressive sensing, and is motivated by the observation that in some practical sparse data the nonzero coefficients are often not random but tend to be clustered. Intuitively, better results can be achieved in these cases by reasonably utilizing both clustering and sparsity priors. Motivated by this idea, we have developed a new greedy sparse recovery algorithm, which prunes data residues in the iterative process according to both sparsity and group clustering priors rather than only sparsity as in previous methods. The proposed algorithm can recover stably sparse data with clustering trends using far fewer measurements and computations than current state-of-the-art algorithms with provable guarantees. Moreover, our algorithm can adaptively learn the dynamic group structure and the sparsity number if they are not available in the practical applications. We have applied the algorithm to sparse recovery and background subtraction in videos. Numerous experiments with improved performance over previous methods further validate our theoretical proofs and the effectiveness of the proposed algorithm.

This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity concept in statistical learning and compressive sensing. By allowing arbitrary structures on the feature set, this concept generalizes the group sparsity idea. A general theory is developed for learning with structured sparsity, based on the notion of coding complexity associated with the structure. Moreover, a structured greedy algorithm is proposed to efficiently solve the structured sparsity problem. Experiments demonstrate the advantage of structured sparsity over standard sparsity.

Sparse representation in compressive sensing is gaining increasing attention due to its success in various applications. As we demonstrate in this paper, however, image sparse representation is sensitive to image plane transformations such that existing approaches can not reconstruct the sparse representation of a geometrically transformed image. We introduce a simple technique for obtaining transformation-invariant image sparse representation. It is rooted in two observations: 1) if the aligned model images of an object span a linear subspace, their transformed versions with respect to some group of transformations can still span a linear subspace in a higher dimension; 2) if a target (or test) image, aligned with the model images, lives in the above subspace, its pre-alignment versions would get closer to the subspace after applying estimated transformations with more and more accurate parameters. These observations motivate us to project a potentially unaligned target image to random projection manifolds defined by the model images and the transformation model. Each projection is then separated into the aligned projection target and a residue due to misalignment. The desired aligned projection target is then iteratively optimized by gradually diminishing the residue. In this framework, we can simultaneously recover the sparse representation of a target image and the image plane transformation between the target and the model images. We have applied the proposed methodology to two applications: face recognition, and dynamic texture registration. The improved performance over previous methods that we obtain demonstrates the effectiveness of the proposed approach.

We address the problem of registering a sequence of images in a moving dynamic texture video. This involves optimization with respect to camera motion, the average image, and the dynamic texture model. This problem is highly ill-posed and almost impossible to have good solutions without priors. In this paper, we introduce powerful priors for this problem, based on two simple observations: 1) registration should simplify the dynamic texture model while preserving all useful information. It motivates us to compute a prior for the dynamic texture by marginalizing over specific dynamics in the space of all stable auto-regressive sequences; 2) the statistics of derivative filter responses in the average image can be significantly changed by registration, and better registration should lead to a sharper average image. This offers us the prior of requiring the derivative distribution of the estimated average image to be close to that learned from the input image sequence. With these priors, a new registration approach is proposed by marginalizing over the "nuisance" variables under a Bayesian framework. And superior motion estimation results are obtained by jointly optimizing over the registration parameters, the average image, and the dynamic texture model. Experimental results on real video sequences of moving dynamic textures show convincing performance of the proposed approach.

Noise removal is an important problem for iris recognition. If the iris regions were not correctly segmented in iris images, segmented iris regions possibly include noises, namely eyelashes, eyelids, reflections and pupil. Noises influence the features of both noise regions and their neighboring regions, which will result in poor recognition performance. To solve this problem, this paper proposes a method for removing noises and impainting iris images. The whole procedure includes three steps: 1) localization and normalization, 2) noise removal based on phase congruency and 3) iris image impainting. A series of experiments show that the proposed method has encouraging performance for improving the recognition accuracy.

Iris recognition is one of the most reliable personal identification methods. The potential requirement of obtaining high accuracy is that users supply iris images with good quality. It is thus necessary for an iris recognition system to operate the possibly blurred iris images due to less cooperation of users and camera with low resolution. This paper proposes a new algorithm for resolution enhancement of iris images captured by the low resolution camera in less cooperative situations. The prior probability relation between the information of different frequency bands of iris features useful for recognition is firstly learned. Then, it is incorporated into resolution enhancement algorithms to recover the lost information for the seriously blurred images. A large number of experiments on the CASIA iris database demonstrate the validity of the proposed approach.