Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization

• URL: http://arxiv.org/abs/2409.09774v3
• Date: Wed, 6 Nov 2024 05:16:59 GMT
• Title: Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization
• Authors: Haoyuan Sun, Bo Xia, Yongzhe Chang, Xueqian Wang,
• Abstract summary: This study focuses on extending reverse Kullback-Leibler divergence in the alignment paradigm of text-to-image models to $f$-divergence. We conduct comprehensive evaluation on image-text alignment performance, human value alignment performance and generation diversity performance under different divergence constraints.
• Score: 9.242941447250969
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) has recently expanded its successful application from aligning large language models (LLMs) to aligning text-to-image models with human preferences, which has generated considerable interest within the community. However, we have observed that these approaches rely solely on minimizing the reverse Kullback-Leibler divergence during alignment process between the fine-tuned model and the reference model, neglecting the incorporation of other divergence constraints. In this study, we focus on extending reverse Kullback-Leibler divergence in the alignment paradigm of text-to-image models to $f$-divergence, which aims to garner better alignment performance as well as good generation diversity. We provide the generalized formula of the alignment paradigm under the $f$-divergence condition and thoroughly analyze the impact of different divergence constraints on alignment process from the perspective of gradient fields. We conduct comprehensive evaluation on image-text alignment performance, human value alignment performance and generation diversity performance under different divergence constraints, and the results indicate that alignment based on Jensen-Shannon divergence achieves the best trade-off among them. The option of divergence employed for aligning text-to-image models significantly impacts the trade-off between alignment performance (especially human value alignment) and generation diversity, which highlights the necessity of selecting an appropriate divergence for practical applications.

Related papers

• Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast [7.092718945468069]
  Domain adaptation aims to reduce the model degradation on the target domain caused by the domain shift between the source and target domains. Probabilistic proto-typical pixel contrast (PPPC) is a universal adaptation framework that models each pixel embedding as a probability. PPPC not only helps to address ambiguity at the pixel level, yielding discriminative representations but also significant improvements in both synthetic-to-real and day-to-night adaptation tasks.
  arXiv  Detail & Related papers  (2024-09-27T08:25:03Z)
• Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation [87.50120181861362]
  VisionPrefer is a high-quality and fine-grained preference dataset that captures multiple preference aspects. We train a reward model VP-Score over VisionPrefer to guide the training of text-to-image generative models and the preference prediction accuracy of VP-Score is comparable to human annotators.
  arXiv  Detail & Related papers  (2024-04-23T14:53:15Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment [46.44464839353993]
  We introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context. RiC only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time.
  arXiv  Detail & Related papers  (2024-02-15T18:58:31Z)
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback [70.32795295142648]
  Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step. Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
  arXiv  Detail & Related papers  (2024-01-21T10:46:23Z)
• OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization [65.57380193070574]
  Vision-language pre-training models are vulnerable to multi-modal adversarial examples. Recent works have indicated that leveraging data augmentation and image-text modal interactions can enhance the transferability of adversarial examples. We propose an Optimal Transport-based Adversarial Attack, dubbed OT-Attack.
  arXiv  Detail & Related papers  (2023-12-07T16:16:50Z)
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [26.274786600234876]
  The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but amplify safety concerns. RLHF has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. DPO has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified
  arXiv  Detail & Related papers  (2023-09-28T08:29:44Z)
• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback [106.63518036538163]
  We present a novel unified bilevel optimization-based framework, textsfPARL, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning. Our framework addressed these concerns by explicitly parameterizing the distribution of the upper alignment objective (reward design) by the lower optimal variable. Our empirical results substantiate that the proposed textsfPARL can address the alignment concerns in RL by showing significant improvements.
  arXiv  Detail & Related papers  (2023-08-03T18:03:44Z)
• Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation [15.411325887412413]
  This paper proposes a novel model named "Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment" (FSA-CDM) FSA-CDM introduces contrastive positive/negative samples into the diffusion model to boost performance for markup-to-image generation. Experiments are conducted on four benchmark datasets from different domains.
  arXiv  Detail & Related papers  (2023-08-02T13:43:03Z)
• Posterior Differential Regularization with f-divergence for Improving Model Robustness [95.05725916287376]
  We focus on methods that regularize the model posterior difference between clean and noisy inputs. We generalize the posterior differential regularization to the family of $f$-divergences. Our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness.
  arXiv  Detail & Related papers  (2020-10-23T19:58:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.