Soft Representation Learning for Sparse Transfer

Park, Haeju; Yeo, Jinyoung; Wang, Gengyu; Hwang, Seung Won

doi:10.18653/v1/p19-1151

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are the first to apply this idea and revise it for representation learning in GZSL. A novel multi-task representation learning paradigm is proposed that models task-specific and task-shared representations in parallel, unlike existing paradigms [37,38] that use a single MoE for each sub-task and a hierarchical structure. For the sake of clear understanding, we highlight the distinctions between our approach and those counterparts in Table 1.…”

Section: Related Workmentioning

confidence: 99%

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

Wang

Tang

2023

Electronics

View full text Add to dashboard Cite

Generalized Zero-Shot Learning (GZSL) holds significant research importance as it enables the classification of samples from both seen and unseen classes. A prevailing approach for GZSL is learning transferable representations that can generalize well to both seen and unseen classes during testing. This approach encompasses two key concepts: discriminative representations and semantic-relevant representations. “Semantic-relevant” facilitates the transfer of semantic knowledge using pre-defined semantic descriptors, while “discriminative” is crucial for accurate category discrimination. However, these two concepts are arguably inherently conflicting, as semantic descriptors are not specifically designed for image classification. Existing methods often struggle with balancing these two aspects and neglect the conflict between them, leading to suboptimal representation generalization and transferability to unseen classes. To address this issue, we propose a novel partially-shared multi-task representation learning method, termed PS-GZSL, which jointly preserves complementary and sharable knowledge between these two concepts. Specifically, we first propose a novel perspective that treats the learning of discriminative and semantic-relevant representations as optimizing a discrimination task and a visual-semantic alignment task, respectively. Then, to learn more complete and generalizable representations, PS-GZSL explicitly factorizes visual features into task-shared and task-specific representations and introduces two advanced tasks: an instance-level contrastive discrimination task and a relation-based visual-semantic alignment task. Furthermore, PS-GZSL employs Mixture-of-Experts (MoE) with a dropout mechanism to prevent representation degeneration and integrates a conditional GAN (cGAN) to synthesize unseen features for estimating unseen visual features. Extensive experiments and more competitive results on five widely-used GZSL benchmark datasets validate the effectiveness of our PS-GZSL.

show abstract

Section: Related Workmentioning

confidence: 99%

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

Wang

Tang

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…However, they end up highlighting the data sources with more consensus knowledge, which still cannot rigorously define and constrain the accuracy drop for each source in their learning objectives. The second family learns separate models for shared information and specific information, respectively [10,26,35,36,43]. However, the negative transfer may still happen in the models which learn shared information, and is not well defined or formulated in these works.…”

Section: Related Workmentioning

confidence: 99%

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

Liang¹,

Lv²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, incorrect alignments may increase negative transfer; while mitigating negative transfer for one source may result in poorly learned representations for other sources and then decrease alignment accuracy. To handle the entangled challenges, we point out that the key is to optimize information sharing first based on Pareto front optimization, by showing that information sharing significantly influences the Pareto front which depicts lower bounds of negative transfer. Consequently, we proposed an Incentive Compatible Pareto Alignment (ICPA) method to first optimize cross-source alignments based on Pareto front optimization, then mitigate negative transfer constrained on the optimized alignments. This mechanism renders each source can learn based on its true preference without worrying about deteriorating representations of other sources. Specifically, the Pareto front optimization encourages minimizing lower bounds of negative transfer, which optimizes whether and which to align. In detail, we adopt graph neural networks to handle data sparsity in each source and a scalable alignment based on sliced graph matching. Comprehensive empirical evaluation results on four large-scale datasets are provided to demonstrate the effectiveness and superiority of ICPA. Online A/B test results at a search advertising platform also demonstrate the effectiveness of ICPA in production environments. We also release an International Entity Graph (IEG) 1 dataset to facilitate future research.

show abstract

Soft Representation Learning for Sparse Transfer

Cited by 2 publications

References 20 publications

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

Generalized Zero-Shot Image Classification via Partially-Shared Multi-Task Representation Learning

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

Contact Info

Product

Resources

About