Whole slide images (WSIs) are gigapixel-scale digital images of H&E-stained tissue samples widely used in pathology. The substantial size and complexity of WSIs pose unique analytical challenges. Multiple Instance Learning (MIL) has emerged as a powerful approach for addressing these challenges, particularly in cancer classification and detection. This survey provides a comprehensive overview of the challenges and methodologies associated with applying MIL to WSI analysis, including attention mechanisms, pseudo-labeling, transformers, pooling functions, and graph neural networks. Additionally, it explores the potential of MIL in discovering cancer cell morphology, constructing interpretable machine learning models, and quantifying cancer grading. By summarizing the current challenges, methodologies, and potential applications of MIL in WSI analysis, this survey aims to inform researchers about the state of the field and inspire future research directions.

Predicting differential gene expression (DGE) from Histone modifications (HM) signal is crucial to understand how HM controls cell functional heterogeneity through influencing differential gene regulation. Most existing prediction methods use fixed-length bins to represent HM signals and transmit these bins into a single machine learning model to predict differential expression genes of single cell type or cell type pair. However, the inappropriate bin length may cause the splitting of the important HM segment and lead to information loss. Furthermore, the bias of single learning model may limit the prediction accuracy. Considering these problems, in this paper, we proposes an Ensemble deep neural networks framework for predicting Differential Gene Expression (EnDGE). EnDGE employs different feature extractors on input HM signal data with different bin lengths and fuses the feature vectors for DGE prediction. Ensemble multiple learning models with different HM signal cutting strategies helps to keep the integrity and consistency of genetic information in each signal segment, and offset the bias of individual models. Besides the popular feature extractors, we also propose a new Residual Network based model with higher prediction accuracy to increase the diversity of feature extractors. Experiments on the real datasets from the Roadmap Epigenome Project (REMC) show that for all cell type pairs, EnDGE significantly outperforms the state-of-the-art baselines for differential gene expression prediction.

Learning the directed acyclic graph (DAG) among causal variables is a fundamental pre-task in causal discovery. Available DAG learning solutions canonically focus on homogeneous nodes with multiple variables and assume i.i.d. samples, how to learn DAG on typical attributed heterogeneous network (AHN) composed with different types of inter-dependent nodes and diverse attributes is a practical but more difficult task. In this paper, we propose HetDAG to identify DAG among nodes from heterogeneous network. HetDAG first embeds different types of node attributes and aggregates these embeddings as the node's raw representation. Then it uses contrastive learning with prior network structure to explore latent relationships between nodes and update the representation. Next, HetDAG introduces an attention-based DAG learning module that takes node representations as input to search DAG and orient edges between nodes. To the best of our knowledge, HetDAG is the first study to learn DAG on heterogeneous networks. Extensive experiments on both semi-synthetic and real data show that HetDAG can learn DAG in an efficacy way and outperforms the state-of-the-art approaches. The results on real biological networks confirm that HetDAG can find out the causal relations between lncRNAs and miRNAs.

Cross-modal hashing can efficiently retrieve data across different modalities and has been successfully applied in various domains. Although many supervised cross-modal hashing methods have been proposed, they generally focus on two modals only and assume that the labels of training data are sufficient and complete. This assumption is not practical in real scenarios. In this article, we propose the weakly supervised cross-modal hashing (WCHash), which takes into account the widely witnessed weakly supervised information (incomplete and insufficient labels) of training data. Specifically, WCHash first optimizes a latent central modality with respect to other modalities. Next, it uses an efficient multi-label weak-label method to enrich the labels of training data and measures the semantic similarity between data points based on the enriched labels. After that, it uses this similarity to guide the correlation maximization between the respective data modals and the central modal and thus achieves the hash functions for cross-modal retrieval. Experimental results on real-world datasets demonstrate that WCHash is more efficient and effective than related state-of-the-art cross-modal hashing methods. WCHash can significantly reduce the complexity of cross-modal hashing on three or more modalities.

Predicting differentially expressed genes (DEGs) from epigenetics signal data is the key to understand how epigenetics controls cell functional heterogeneity by gene regulation. This knowledge can help developing 'epigenetics drugs' for complex diseases like cancers. Most of existing machine learning-based methods suffer defects in prediction accuracy, interpretability or training speed. To address these problems, in this paper, we propose a Multiple Self-Attention model for predicting DEGs on Epigenetic data (Epi-MSA). Epi-MSA first uses convolutional neural networks for neighborhood bins information embedding, and then employs multiple self-attention encoders on different input epigenetics factors data to learn which locations of genes are important for predicting DEGs. Next it trains a soft attention module to pick out which epigenetics factors are significant. The attention mechanism makes the model interpretable, and the pure matrix operation of self-attention enables the model to be parallel calculated and speeds up the training. Experiments on datasets from the Roadmap Epigenome Project and BluePrint Data Analysis Portal (BDAP) show that the performance of Epi-MSA is better than existing competitive methods, and Epi-MSA also has a smaller standard deviation, which shows that Epi-MSA is effective and stable. In addition, Epi-MSA has a good interpretability, this is confirmed by referring its attention weight matrix with existing biological knowledge.

With the wide application of machine learning driven automated decisions (e.g., education, loan approval, and hiring) in daily life, it is critical to address the problem of discriminatory behavior toward certain individuals or groups. Early studies focused on defining the correlation/association-based notions, such as statistical parity, equalized odds, etc. However, recent studies reflect that it is necessary to use causality to address the problem of fairness. This review provides an exhaustive overview of notions and methods for detecting and eliminating algorithmic discrimination from a causality perspective. The review begins by introducing the common causality-based definitions and measures for fairness. We then review causality-based fairness-enhancing methods from the perspective of pre-processing, in-processing and post-processing mechanisms, and conduct a comprehensive analysis of the advantages, disadvantages, and applicability of these mechanisms. In addition, this review also examines other domains where researchers have observed unfair outcomes and the ways they have tried to address them. There are still many challenges that hinder the practical application of causality-based fairness notions, specifically the difficulty of acquiring causal graphs and identifiability of causal effects. One of the main purposes of this review is to spark more researchers to tackle these challenges in the near future.

Multiview multi-instance multilabel learning (M3L) is a framework for modeling complex objects. In this framework, each object (or bag) contains one or more instances, is represented with different feature views, and simultaneously annotated with a set of nonexclusive semantic labels. Given the multiplicity of the studied objects, traditional M3L methods generally demand a large number of labeled bags to train a predictive model to annotate bags (or instances) with semantic labels. However, annotating sufficient bags is very expensive and often impractical. In this article, we present an active learning-based M3L approach (M3AL) to reduce the labeling costs of bags and to improve the performance as much as possible. M3AL first adapts the multiview self-representation learning to evacuate the shared and individual information of bags and to learn the shared/individual similarities between bags across/within views. Next, to avoid scrutinizing all the possible labels, M3AL introduces a new query strategy that leverages the shared and individual information, and the diverse instance distribution of bags across views, to select the most informative bag-label pair for the query. Experimental studies on benchmark data sets show that M3AL can significantly reduce the query costs while achieving a better performance than other related competitive methods at the same cost.

Crowdsourcing can harness human intelligence to handle computer-hard tasks in a relatively economic way. The collected answers from various crowd workers are of different qualities, due to the task difficulty, worker capability, incentives and other factors. To maintain high-quality answers while reducing the cost, various strategies have been developed by modeling tasks, workers, or both. Nevertheless, they typically deem that the capability of workers is static when assigning/completing all the tasks. However, in actual fact, crowd workers can improve their capability by gradually completing easy to hard tasks, alike human beings’ intrinsic self-paced learning ability. In this paper, we study crowdsourcing with self-paced workers, whose capability can be progressively improved as they scrutinize and complete tasks from to easy to hard. We introduce a Self-paced Crowd-worker model (SPCrowder). In SPCrowder, workers firstly do a set of golden tasks with known truths, which serve as feedbacks to assist workers capturing the raw modes of tasks and to stimulate the self-paced learning. This also helps to estimate workers’ quality and tasks’ difficulty. SPCrowder then uses a task difficulty model to dynamically measure the difficulty of tasks and rank them from easy to hard and assign tasks to self-paced workers by maximizing a benefit criterion. By doing so, a normal worker can be capable to handle hard tasks after completing some easier and related tasks. We conducted extensive experiments on semi-simulated and real crowdsourcing datasets, SPCrowder outperforms competitive methods in quality control and budget saving. Crowd workers indeed hold the self-paced learning ability, which boosts the quality and save the budget.

In multiview multilabel learning, each object is represented by several heterogeneous feature representations and is also annotated with a set of discrete nonexclusive labels. Previous studies typically focus on capturing the shared latent patterns among multiple views, while not sufficiently considering the diverse characteristics of individual views, which can cause performance degradation. In this article, we propose a novel approach [individuality- and commonality-based multiview multilabel learning (ICM2L)] to explicitly explore the individuality and commonality information of multilabel multiple view data in a unified model. Specifically, a common subspace is learned across different views to capture the shared patterns. Then, multiple individual classifiers are exploited to explore the characteristics of individual views. Next, an ensemble strategy is adopted to make a prediction. Finally, we develop an alternative solution to jointly optimize our model, which can enhance the robustness of the proposed model toward rare labels and reinforce the reciprocal effects of individuality and commonality among heterogeneous views, and thus further improve the performance. Experiments on various real-word datasets validate the effectiveness of ICM2L against the state-of-the-art solutions, and ICM2L can leverage the individuality and commonality information to achieve an improved performance as well as to enhance the robustness toward rare labels.

Multi‐instance learning (MIL) can model complex bags (samples) that are further made of diverse instances (subsamples). In typical MIL, the labels of bags are known while those of individual instances are unknown and to be specified. In this paper we propose an imbalanced deep multi‐instance learning approach (IDMIL‐III) and apply it to predict genome‐wide isoform–isoform interactions (IIIs). This prediction task is crucial for precisely understanding the interactome between proteoforms and to reveal their functional diversity. The current solutions typically formulate the prediction of IIIs as a MIL problem by pairing two genes as a “bag” and any two isoforms spliced from these two genes as “instances.” The key instances (interacting isoform pairs) trigger the label of the positive (interacting) gene bags, which is important for identifying the IIIs. Furthermore, the prediction task was simplified as a balanced classification problem, which in practice is a rather imbalanced one. To address these issues, IDMIL‐III fuses RNA‐seq, nucleotide sequence, amino acid sequence and exon array data, and further introduces a novel loss function to separately model the loss of positive pairs and of negative pairs, and thus to avoid the expected loss dominated by majority negative pairs. In addition, it includes an attention strategy to identify positive isoform pairs from a positive gene bag. Extensive experimental results prove the effectiveness of IDMIL‐III on predicting IIIs. Particularly, IDMIL‐III achieves an F1 value as 95.4%, at least 3.8% higher than those of competitive methods at the gene‐level; and obtains an F1 as 29.8%, at least 2.4% higher than the state‐of‐the‐art methods at the isoform‐level. The code of IDMIL‐III is available at http://mlda.swu.edu.cn/codes.php?name=IDMIL-III.

Crowdsourcing is an economic and efficient strategy aimed at collecting annotations of data through an online platform. Crowd workers with different expertise are paid for their service, and the task requester usually has a limited budget. How to collect reliable annotations for multilabel data and how to compute the consensus within budget are an interesting and challenging, but rarely studied, problem. In this article, we propose a novel approach to accomplish active multilabel crowd consensus (AMCC). AMCC accounts for the commonality and individuality of workers and assumes that workers can be organized into different groups. Each group includes a set of workers who share a similar annotation behavior and label correlations. To achieve an effective multilabel consensus, AMCC models workers' annotations via a linear combination of commonality and individuality and reduces the impact of unreliable workers by assigning smaller weights to their groups. To collect reliable annotations with reduced cost, AMCC introduces an active crowdsourcing learning strategy that selects sample-label-worker triplets. In a triplet, the selected sample and label are the most informative for the consensus model, and the selected worker can reliably annotate the sample at a low cost. Our experimental results on multilabel data sets demonstrate the advantages of AMCC over state-of-the-art solutions on computing crowd consensus and on reducing the budget by choosing cost-effective triplets.

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances. Current MIML solutions still focus on a single-type of objects and assumes an IID distribution of training data. But these objects are linked with objects of other types, %(i.e., pictures in Facebook link with various users), which also encode the semantics of target objects. In addition, they generally need abundant labeled data for training. To effectively mine interdependent MIML objects of different types, we propose a network embedding and meta learning based approach (MetaMIML). MetaMIML introduces the context learner with network embedding to capture semantic information of objects of different types, and the task learner to extract the meta knowledge for fast adapting to new tasks. In this way, MetaMIML can naturally deal with MIML objects at data level improving, but also exploit the power of meta-learning at the model enhancing. Experiments on benchmark datasets demonstrate that MetaMIML achieves a significantly better performance than state-of-the-art algorithms.

Clustering is a fundamental data exploration task which aims at discovering the hidden grouping structure in the data. The traditional clustering methods typically compute a single partition. However, there often exist different and equally meaningful clusterings in complex data. To solve this issue, multiple clustering approaches have emerged with the goal of exploring alternative clusterings from different perspectives. Existing solutions to this problem mainly focus on one-way clustering, that is, they cluster either the samples or the features. However, for many practical tasks, it is meaningful and desirable to explore alternative two-way clusterings (or co-clusterings), which capture not only the sample cluster structure but also the feature cluster structure. To tackle this interesting and unresolved task, we introduce an approach, called multiple co-clusterings (MultiCCs), to generate multiple alternative co-clusterings at the same time. MultiCC takes advantage of matrix tri-factorization to seek the co-clustering indicator matrices for samples and features and defines the row and column redundancy quantification terms to enforce diversity among co-clusterings based on these indicator matrices. After that, it integrates matrix tri-factorization and two nonredundancy terms into a unified objective function and gives an alternative optimization procedure to optimize the objective function. Extensive experimental results demonstrate that MultiCC performs significantly better than the existing multiple clustering methods. In addition, MultiCC can find out interesting co-clusters, which cannot be made by those comparing methods.

This paper investigates the application of graph neural networks (GNN) in Mergers and Acquisitions (M&A) prediction, which aims to quantify the relationship between companies, their founders, and investors. M&A is a critical management strategy to decide if the company is to grow or downsize, and M&A prediction has been a challenging research topic in the past few decades. However, the traditional methods of predicting M&A probability are only based on the company's fundamentals, such as revenue, profit, or news. Instead, GNN takes full advantage of those relationship data to expand feature dimension and improve the prediction result. Our M&A prediction solution integrates with the topic model for text analysis, advanced feature engineering, and several tricks to boost GNN. The approach achieves a high Area-Under-Curve score (AUC) 0.952, which is better than the previous record 0.888. The true positive rate is 83% with a low false positive rate 7.8%, which performance is better than the previous benchmark record 70.9%/10.6%.

Co-clustering aims at discovering groups of both objects and features from a given data matrix. Co-clustering ensembles can produce robust co-clusters by combining multiple base co-clusterings. However, current co-clustering ensemble solutions either ignore the constraints resulting from feature-to-feature and object-to-object relevance information, or ignore feature-to-object relevance information. In this paper, we advocate that all three information sources contribute to the achievement of good consensus solutions, and propose a co-clustering ensemble (CoCE) approach based on multiple relevance measures. CoCE first evaluates the quality of base co-clusters and consequently measures feature-to-object relevance. The latter, along with feature-to-feature and object-to-object relevance measures, contribute to the definition of a hybrid graph. The consensus process uses the resulting hybrid graph; it's formulated as a trace minimization problem and introduces a block-wise matrix multiplication technique to perform the optimization. Experimental results on various datasets show that CoCE not only frequently outperforms other related co-clustering ensembles, but also has reduced runtime cost and is more robust to poor base co-clusterings.

Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels, and only some of the labels are relevant. The PML problem is practical in real-world scenarios, as it is difficult and even impossible to obtain precisely labeled samples. Several PML solutions have been proposed to combat with the prone misled by the irrelevant labels concealed in the candidate labels, but they generally focus on the smoothness assumption in feature space or low-rank assumption in label space, while ignore the negative information between features and labels. Specifically, if two instances have largely overlapped candidate labels, irrespective of their feature similarity, their ground-truth labels should be similar; while if they are dissimilar in the feature and candidate label space, their ground-truth labels should be dissimilar with each other. To achieve a credible predictor on PML data, we propose a novel approach called PML-LFC (Partial Multi-label Learning with Label and Feature Collaboration). PML-LFC estimates the confidence values of relevant labels for each instance using the similarity from both the label and feature spaces, and trains the desired predictor with the estimated confidence values. PML-LFC achieves the predictor and the latent label matrix in a reciprocal reinforce manner by a unified model, and develops an alternative optimization procedure to optimize them. Extensive empirical study on both synthetic and real-world datasets demonstrates the superiority of PML-LFC.

MOTIVATION:Alternative splicing contributes to the functional diversity of protein species and the proteoforms translated from alternatively spliced isoforms of a gene actually execute the biological functions. Computationally predicting the functions of genes has been studied for decades. However, how to distinguish the functional annotations of isoforms, whose annotations are essential for understanding developmental abnormalities and cancers, is rarely explored. The main bottleneck is that functional annotations of isoforms are generally unavailable and functional genomic databases universally store the functional annotations at the gene level. RESULTS:We propose IsoFun to accomplish Isoform Function prediction based on bi-random walks on a heterogeneous network. IsoFun firstly constructs an isoform functional association network based on the expression profiles of isoforms derived from multiple RNA-seq datasets. Next, IsoFun uses the available Gene Ontology annotations of genes, gene-gene interactions and the relations between genes and isoforms to construct a heterogeneous network. After this, IsoFun performs a tailored bi-random walk on the heterogeneous network to predict the association between GO terms and isoforms, thus accomplishing the prediction of GO annotations of isoforms. Experimental results show that IsoFun significantly outperforms the state-of-the-art algorithms and improves the area under the receiver-operating curve (AUROC) and the area under the precision-recall curve (AUPRC) by 17% and 44% at the gene-level, respectively. We further validated the performance of IsoFun on the genes ADAM15 and BCL2L1. IsoFun accurately differentiates the functions of respective isoforms of these two genes. AVAILABILITY AND IMPLEMENTATION:The code of IsoFun is available at http://mlda.swu.edu.cn/codes.php? name=IsoFun. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.

Hashing has been widely adopted for large-scale data retrieval in many domains due to its low storage cost and high retrieval speed. Existing cross-modal hashing methods optimistically assume that the correspondence between training samples across modalities is readily available. This assumption is unrealistic in practical applications. In addition, existing methods generally require the same number of samples across different modalities, which restricts their flexibility. We propose a flexible cross-modal hashing approach (FlexCMH) to learn effective hashing codes from weakly paired data, whose correspondence across modalities is partially (or even totally) unknown. FlexCMH first introduces a clustering-based matching strategy to explore the structure of each cluster and, thus, to find the potential correspondence between clusters (and samples therein) across modalities. To reduce the impact of an incomplete correspondence, it jointly optimizes the potential correspondence, the cross-modal hashing functions derived from the correspondence, and a hashing quantitative loss in a unified objective function. An alternative optimization technique is also proposed to coordinate the correspondence and hash functions and reinforce the reciprocal effects of the two objectives. Experiments on public multimodal data sets show that FlexCMH achieves significantly better results than state-of-the-art methods, and it, indeed, offers a high degree of flexibility for practical cross-modal hashing tasks.

Crowdsourcing is a relatively inexpensive and efficient mechanism to collect annotations of data from the open Internet. Crowdsourcing workers are paid for the provided annotations, but the task requester usually has a limited budget. It is desirable to wisely assign the appropriate task to the right workers, so the overall annotation quality is maximized while the cost is reduced. In this article, we propose a novel task assignment strategy (CrowdWT) to capture the complex interactions between tasks and workers, and properly assign tasks to workers. CrowdWT first develops a Worker Bias Model (WBM) to jointly model the worker’s bias, the ground truths of tasks, and the task features. WBM constructs a mapping between task features and worker annotations to dynamically assign the task to a group of workers, who are more likely to give correct annotations for the task. CrowdWT further introduces a Task Difficulty Model (TDM), which builds a Kernel ridge regressor based on task features to quantify the intrinsic difficulty of tasks and thus to assign the difficult tasks to more reliable workers. Finally, CrowdWT combines WBM and TDM into a unified model to dynamically assign tasks to a group of workers and recall more reliable and even expert workers to annotate the difficult tasks. Our experimental results on two real-world datasets and two semi-synthetic datasets show that CrowdWT achieves high-quality answers within a limited budget, and has the best performance against competitive methods.

Heterogeneous network based data fusion can encode diverse inter- and intra-relations between objects, and has been sparking increasing attention in recent years. Matrix factorization based data fusion models have been invented to fuse multiple data sources. However, these models generally suffer from the widely-witnessed insufficient relations between nodes and from information loss when heterogeneous attributes of diverse network nodes are transformed into ad-hoc homologous networks for fusion. In this paper, we introduce a general data fusion model called Attributed Heterogeneous Network Fusion (AHNF). AHNF firstly constructs an attributed heterogeneous network composed with different types of nodes and the diverse attribute vectors of these nodes. It uses indicator matrices to differentiate the observed inter-relations from the latent ones, and thus reduces the impact of insufficient relations between nodes. Next, it collaboratively factorizes multiple adjacency matrices and attribute data matrices of the heterogeneous network into low-rank matrices to explore the latent relations between these nodes. In this way, both the network topology and diverse attributes of nodes are fused in a coordinated fashion. Finally, it uses the optimized low-rank matrices to approximate the target relational data matrix of objects and to effectively accomplish the relation prediction. We apply AHNF to predict the lncRNA-disease associations using diverse relational and attribute data sources. AHNF achieves a larger area under the receiver operating curve 0.9367 (by at least 2.14%), and a larger area under the precision-recall curve 0.5937 (by at least 28.53%) than competitive data fusion approaches. AHNF also outperforms competing methods on predicting de novo lncRNA-disease associations, and precisely identifies lncRNAs associated with breast, stomach, prostate, and pancreatic cancers. AHNF is a comprehensive data fusion framework for universal attributed multi-type relational data. The code and datasets are available at http://mlda.swu.edu.cn/codes.php?name=AHNF.