An official website of the United States government
Graph Neural Networks (GNN) have proven successful for graph-related tasks. However, many GNNs methods require labeled data, which is challenging to obtain. To tackle this, graph contrastive learning (GCL) have gained attention. GCL learns by contrasting similar nodes (positives) and dissimilar nodes (negatives). Current GCL methods, using data augmentation for positive samples and random selection for negative samples, can be sub-optimal due to limited positive samples and the possibility of false-negative samples. In this study, we propose an enhanced objective addressing these issues. We first introduce an ideal objective with all positive and no false-negative samples, then transform it probabilistically based on sampling distributions. We next model these distributions with node similarity and derive an enhanced objective. Comprehensive experiments have shown the effectiveness of the proposed enhanced objective for a broad set of GCL models.
more »
« less
This content will become publicly available on May 2, 2026
Enhancing Contrastive Representation Learning through Data
Contrastive learning learns input representation by pushing similar data together and pulling dissimilar data away, along with data augmentation and pretext task construction. It enhances the large model learning due to its ability to use a large amount of unlabeled data. It has been suc- cessfully applied to large language models, pre-trained image models, and multimodal models. In addition, contrastive learning learns a representation from modeling the explainable structure of the latent space, which has a broad application in scientific discovery and interpretable Artificial Intelligence (AI). The primary focus of this thesis is to explore contrastive learning from a data construction perspective in real-world problems to fill the gap between the principle of contrastive learning and its application. The challenges, such as sampling bias and data quality, will largely affect the representations learned by contrastive learning. This thesis analyzes the data construction chanlledges and limitations in 1) the negative sampling of knowledge graph embedding (KGE), 2) high-quliaty preference data labeling of Large Language Models (LLMs) alignment, 3) data augmentation in Non-linear dynamic system modeling, and 4) data properties in functions of mesange RNA (mRNA) sequence. To solve the challenges 1), a hardness and structure-based objective function was proposed by considering sampling bias in hard negative sampling. For challenge 2), the similarity of response embedding is used to evaluate the quality of preference pairs to mitigate the labeling error of humans when they face an ambiguous response pair. Chal- lenge 3) is solved by systematically considering the physical system and contrastive learning. A data augmentation strategy by partitioning the full sequence is used for learning the transition matrix in the latent linear space. Challenge 4) is common to see in the biological domain due to the high cost of lab experiments. Pre-trained model will advantage the limited dataset su- pervised learning by learning general features from domain knowledge. A contrastive learning based teacher-student framework is proposed for mRNA sequence learning by contrasting the unmasked sequence and the hard-masked sequence. By providing careful data construction or data sampling, contrastive learning will be boosted to solve tasks in reality. For the KGE, the novel contrastive loss function learns the boundary between negative samples and positive samples to improve the link prediction task in the knowl- edge graph; For the LLM alignment, in the same labeling cost, the selected dissimilar responses will improve the vanilla direct preference optimization (DPO) alignment; The data augmentation with contrastive loss play crucial role to learn more accuracy dynamic system, which explained by the learned the continiues eigenfunction; By considering the tearch-student framework with hard-masked strategy, the pre-trained model achieve the state-of-the-art result by fine-tuning on limited downstrame task data. Overall, this thesis provides a broad data-driven contrastive learning methodology to enhance representation learning in different domains. The methodology consists of a imprived objective function in the face of data bias, a better data selection reducing labeling error, and proper data augmentation for a particular application domain. This methodology improve the learning result compare to traditional method.
more »
« less
- Award ID(s):
- 2244574
- PAR ID:
- 10615942
- Publisher / Repository:
- ProQuest Dissertation
- Date Published:
- Subject(s) / Keyword(s):
- contrastive learning AI machine learning self-supervised learning
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Contrastive learning is an effective unsupervised method in graph representation learning. The key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle. Recently, the data-augmentation-based contrastive learning method has advanced to show great power in the visual domain, and some works have extended this method from images to graphs. However, unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and it is much harder to provide high-quality contrastive samples, which leaves much space for improvement. In this work, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method,Adversarial Graph Contrastive Learning(ArieL), to extract informative contrastive samples within reasonable constraints. We develop a new technique calledinformation regularizationfor stable training and use subgraph sampling for scalability. We generalize our method from node-level contrastive learning to the graph level by treating each graph instance as a super-node.ArieLconsistently outperforms the current graph contrastive learning methods for both node-level and graph-level classification tasks on real-world datasets. We further demonstrate thatArieLis more robust in the face of adversarial attacks.more » « less
-
Contrastive learning is a self-supervised representation learning method that achieves milestone performance in various classification tasks. However, due to its unsupervised fashion, it suffers from the false negative sample problem: randomly drawn negative samples that are assumed to have a different label but actually have the same label as the anchor. This deteriorates the performance of contrastive learning as it contradicts the motivation of contrasting semantically similar and dissimilar pairs. This raised the attention and the importance of finding legitimate negative samples, which should be addressed by distinguishing between 1) true vs. false negatives; 2) easy vs. hard negatives. However, previous works were limited to the statistical approach to handle false negative and hard negative samples with hyperparameters tuning. In this paper, we go beyond the statistical approach and explore the connection between hard negative samples and data bias. We introduce a novel debiased contrastive learning method to explore hard negatives by relative difficulty referencing the bias-amplifying counterpart. We propose triplet loss for training a biased encoder that focuses more on easy negative samples. We theoretically show that the triplet loss amplifies the bias in self-supervised representation learning. Finally, we empirically show the proposed method improves downstream classification performance.more » « less
-
Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely on pairs of AI-generated responses ranked according to human annotation. The response pair annotation process might bring human bias. Building a correct preference dataset is the costly part of the alignment pipeline. To improve annotation efficiency and quality in the LLMs alignment, we propose REAL:Response Embedding-based Alignment for LLMs, a strategy for constructing a high-quality training dataset that focuses on acquiring the less ambiguous preference pairs for labeling out of a set of response candidates. Our selection process is based on the similarity of embedding responses independently of prompts, which guarantees the selection process in an off-policy setting, avoiding adaptively measuring the similarity during the training. Experimental results on real-world dataset SHP2 and synthetic HH-RLHF benchmarks indicate that choosing dissimilar response pairs enhances the direct alignment of LLMs while reducing inherited labeling errors. The model aligned with dissimilar response pairs obtained a better margin and win rate on the dialogue task. Our findings suggest that focusing on distinct pairs can reduce the label error and improve LLM alignment efficiency, saving up to 65% of annotators’ work. The code of the work can be found https://github.com/ honggen-zhang/REAL-Alignment.more » « less
-
Data augmentation is critical to the empirical success of modern self-supervised representation learning, such as contrastive learning and masked language modeling. However, a theoretical understanding of the exact role of augmentation remains limited. Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator, suggesting that learning a linear probe atop such representation can be connected to RKHS regression. Building on this insight, this work delves into a statistical analysis of augmentation-based pretraining. Starting from the isometry property, a geometric characterization of the target function given by the augmentation, we disentangle the effects of the model and the augmentation, and prove two generalization bounds that are free of model complexity. Our first bound works for an arbitrary encoder, where the prediction error is decomposed as the sum of an estimation error incurred by fitting a linear probe with RKHS regression, and an approximation error entailed by RKHS approximation. Our second bound specifically addresses the case where the encoder is near-optimal, that is it approximates the top-d eigenspace of the RKHS induced by the augmentation. A key ingredient in our analysis is the augmentation complexity, which we use to quantitatively compare different augmentations and analyze their impact on downstream performance.more » « less
