Personalized Image Generation with Large Multimodal Models

Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload. However, these systems merely filter existing content and are constrained by its limited diversity, making it difficult to meet users' varied content needs. To address this limitation, personalized content generation has emerged as a promising direction with broad applications. Nevertheless, most existing research focuses on personalized text generation, with relatively little attention given to personalized image generation. The limited work in personalized image generation faces challenges in accurately capturing users' visual preferences and needs from noisy user-interacted images and complex multimodal instructions. Worse still, there is a lack of supervised data for training personalized image generation models. To overcome the challenges, we propose a Personalized Image Generation Framework named Pigeon, which adopts exceptional large multimodal models with three dedicated modules to capture users' visual preferences and needs from noisy user history and multimodal instructions. To alleviate the data scarcity, we introduce a two-stage preference alignment scheme, comprising masked preference reconstruction and pairwise preference alignment, to align Pigeon with the personalized image generation task. We apply Pigeon to personalized sticker and movie poster generation, where extensive quantitative results and human evaluation highlight its superiority over various generative baselines.

DiFashion: Towards Personalized Outfit Generation and Recommendation

The evolution of Outfit Recommendation (OR) in the realm of fashion has progressed through two distinct phases: Pre-defined Outfit Recommendation and Personalized Outfit Composition. Despite these advancements, both phases face limitations imposed by existing fashion products, hindering their effectiveness in meeting users' diverse fashion needs. The emergence of AI-generated content has paved the way for OR to overcome these constraints, demonstrating the potential for personalized outfit generation. In pursuit of this, we introduce an innovative task named Generative Outfit Recommendation (GOR), with the goal of synthesizing a set of fashion images and assembling them to form visually harmonious outfits customized to individual users. The primary objectives of GOR revolve around achieving high fidelity, compatibility, and personalization of the generated outfits. To accomplish these, we propose DiFashion, a generative outfit recommender model that harnesses exceptional diffusion models for the simultaneous generation of multiple fashion images. To ensure the fulfillment of these objectives, three types of conditions are designed to guide the parallel generation process and Classifier-Free-Guidance are employed to enhance the alignment between generated images and conditions. DiFashion is applied to both personalized Fill-In-The-Blank and GOR tasks, and extensive experiments are conducted on the iFashion and Polyvore-U datasets. The results of quantitative and human-involved qualitative evaluations highlight the superiority of DiFashion over competitive baselines.

Plug-In Diffusion Model for Embedding Denoising in Recommendation System

In the realm of recommender systems, handling noisy implicit feedback is a prevalent challenge. While most research efforts focus on mitigating noise through data cleaning methods like resampling and reweighting, these approaches often rely on heuristic assumptions. Alternatively, model perspective denoising strategies actively incorporate noise into user-item interactions, aiming to bolster the model's inherent denoising capabilities. Nonetheless, this type of denoising method presents substantial challenges to the capacity of the recommender model to accurately identify and represent noise patterns. To overcome these hurdles, we introduce a plug-in diffusion model for embedding denoising in recommendation system, which employs a multi-step denoising approach based on diffusion models to foster robust representation learning of embeddings. Our model operates by introducing controlled Gaussian noise into user and item embeddings derived from various recommender systems during the forward phase. Subsequently, it iteratively eliminates this noise in the reverse denoising phase, thereby augmenting the embeddings' resilience to noisy feedback. The primary challenge in this process is determining direction and an optimal starting point for the denoising process. To address this, we incorporate a specialized denoising module that utilizes collaborative data as a guide for the denoising process. Furthermore, during the inference phase, we employ the average of item embeddings previously favored by users as the starting point to facilitate ideal item generation. Our thorough evaluations across three datasets and in conjunction with three classic backend models confirm its superior performance.

Diffusion Recommender Model

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic limitations such as the instability of GANs and the restricted representation ability of VAEs. Such limitations hinder the accurate modeling of the complex user interaction generation procedure, such as noisy interactions caused by various interference factors. In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner. To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis. In addition, we extend traditional DMs to tackle the unique challenges in practical recommender systems: high resource costs for large-scale item prediction and temporal shifts of user preference. To this end, we propose two extensions of DiffRec: L-DiffRec clusters items for dimension compression and conducts the diffusion processes in the latent space; and T-DiffRec reweights user interactions based on the interaction timestamps to encode temporal information. We conduct extensive experiments on three datasets under multiple settings (e.g. clean training, noisy training, and temporal training). The empirical results and in-depth analysis validate the superiority of DiffRec with two extensions over competitive baselines.

Mitigating Spurious Correlations for Self-supervised Recommendation

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious correlations, existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features. Nevertheless, ID-based SSL approaches sacrifice the positive impact of invariant features, while feature engineering methods require high-cost human labeling. To address the problems, we aim to automatically mitigate the effect of spurious correlations. This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL. To handle the two challenges, we propose an invariant feature learning framework, which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments. Based on the mask mechanism, we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation. Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models.