Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis

Zhang, Wenlu; Li, Rongjian; Zeng, Tao; Sun, Qian; Kumar, Sudhir; Ye, Jieping; Ji, Shuiwang

doi:10.1145/2783258.2783304

Cited by 96 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of the learning tasks are assumed to be related to each other, and it is found that learning these tasks jointly can lead to performance improvement compared with learning them individually. In general, MTL algorithms can be classified into several categories, including feature learning approach [34,41], low-rank approach [7,16], task clustering approach [47], task relation learning approach [12], and decomposition approach [6]. For example, the cross-stitch network [41] determines the inputs of hidden layers in different tasks by a knowledge transfer matrix; Zhou et.…”

Section: Multi-task Learningmentioning

confidence: 99%

“…In general, MTL algorithms can be classified into several categories, including feature learning approach [34,41], low-rank approach [7,16], task clustering approach [47], task relation learning approach [12], and decomposition approach [6]. For example, the cross-stitch network [41] determines the inputs of hidden layers in different tasks by a knowledge transfer matrix; Zhou et. al [47] aims to cluster tasks by identifying representative tasks which are a subset of the given m tasks, i.e., if task T i is selected by task T j as a representative task, then it is expected that model parameters for T j are similar to those of T i .…”

Section: Multi-task Learningmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

Wang

Zhang²,

Zhao

et al. 2019

The World Wide Web Conference

425

236

View full text Add to dashboard Cite

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by cross&compress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that cross&compress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-theart baselines. MKR is also shown to be able to maintain a decent performance even if user-item interactions are sparse.

show abstract

Section: Multi-task Learningmentioning

confidence: 99%

Section: Multi-task Learningmentioning

confidence: 99%

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

Wang

Zhang²,

Zhao

et al. 2019

The World Wide Web Conference

425

236

View full text Add to dashboard Cite

show abstract

“…In image analysis, previous examples of deep transfer learning applications proved large-scale natural image sets [45] to be useful for pre-training models that serve as generic feature extractors for various types of biological images [14,283,534,535]. More recently, deep learning models predicted protein sub-cellular localization for proteins not originally present in a training set [536].…”

Section: Multimodal Multi-task and Transfer Learningmentioning

confidence: 99%

“…All three techniques can be used together in the same model. For example, Zhang et al [534] combined deep model-based transfer and multi-task learning for cross-domain image annotation. One could imagine extending that approach to multimodal inputs as well.…”

Section: Multimodal Multi-task and Transfer Learningmentioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2017

Preprint

227

248

View full text Add to dashboard Cite

Deep learning, which describes a class of machine learning algorithms, has recently showed impressive results across a variety of domains. Biology and medicine are data rich, but the data are complex and often ill-understood. Problems of this nature may be particularly well-suited to deep learning techniques. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes, and treatment of patients—and discuss whether deep learning will transform these tasks or if the biomedical sphere poses unique challenges. We find that deep learning has yet to revolutionize or definitively resolve any of these problems, but promising advances have been made on the prior state of the art. Even when improvement over a previous baseline has been modest, we have seen signs that deep learning methods may speed or aid human investigation. More work is needed to address concerns related to interpretability and how to best model each problem. Furthermore, the limited amount of labeled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning powering changes at both bench and bedside with the potential to transform several areas of biology and medicine.

show abstract

“…Zhang et al introduced such a symmetric approach named Multitask Relationship Learning (MTRL) [45] which regularizes the parallel learning of multiple tasks and models their relationships in a non-parametric manner as a task covariance matrix. Many other symmetric approaches [21,43,17,14,46,42] have been developed in recent years. Permutations of utilizing different regularization strategies [14], multi-level sharing [42], cross-layer parameter combinations [21] or meshes of all options [25] have been extensively tested, however they are vulnerable to noisy and outlier tasks which when introduced dramatically deteriorate performance.…”

Section: Related Workmentioning

confidence: 99%

Many Task Learning With Task Routing

Strezoski

Noord

Worring

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Typical multi-task learning (MTL) methods rely on architectural adjustments and a large trainable parameter set to jointly optimize over several tasks. However, when the number of tasks increases so do the complexity of the architectural adjustments and resource requirements. In this paper, we introduce a method which applies a conditional feature-wise transformation over the convolutional activations that enables a model to successfully perform a large number of tasks. To distinguish from regular MTL, we introduce Many Task Learning (MaTL) as a special case of MTL where more than 20 tasks are performed by a single model. Our method dubbed Task Routing (TR) is encapsulated in a layer we call the Task Routing Layer (TRL), which applied in an MaTL scenario successfully fits hundreds of classification tasks in one model. We evaluate our method on 5 datasets against strong baselines and state-of-the-art approaches.

show abstract

Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis

Cited by 96 publications

References 23 publications

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

Opportunities and obstacles for deep learning in biology and medicine

Many Task Learning With Task Routing

Contact Info

Product

Resources

About