GiVE: Guiding Visual Encoder to Perceive Overlooked Information

Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack semantic alignment or overlook non-salient objects. We propose the Guiding Visual Encoder to Perceive Overlooked Information (GiVE) approach. GiVE enhances visual representation with an Attention-Guided Adapter (AG-Adapter) module and an Object-focused Visual Semantic Learning module. These incorporate three novel loss terms: Object-focused Image-Text Contrast (OITC) loss, Object-focused Image-Image Contrast (OIIC) loss, and Object-focused Image Discrimination (OID) loss, improving object consideration, retrieval accuracy, and comprehensiveness. Our contributions include dynamic visual focus adjustment, novel loss functions to enhance object retrieval, and the Multi-Object Instruction (MOInst) dataset. Experiments show our approach achieves state-of-the-art performance.

Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks

Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2) \textit{plausibility}, where explanations are consistent with domain experts. However, the question arises: do faithfulness and plausibility inherently conflict? In this study, through a comprehensive quantitative comparison between the explanations from the selected explainability methods and expert-level interpretations across three NLP tasks: sentiment analysis, intent detection, and topic labeling, we demonstrate that traditional perturbation-based methods Shapley value and LIME could attain greater faithfulness and plausibility. Our findings suggest that rather than optimizing for one dimension at the expense of the other, we could seek to optimize explainability algorithms with dual objectives to achieve high levels of accuracy and user accessibility in their explanations.

DRGame: Diversified Recommendation for Multi-category Video Games with Balanced Implicit Preferences

The growing popularity of subscription services in video game consumption has emphasized the importance of offering diversified recommendations. Providing users with a diverse range of games is essential for ensuring continued engagement and fostering long-term subscriptions. However, existing recommendation models face challenges in effectively handling highly imbalanced implicit feedback in gaming interactions. Additionally, they struggle to take into account the distinctive characteristics of multiple categories and the latent user interests associated with these categories. In response to these challenges, we propose a novel framework, named DRGame, to obtain diversified recommendation. It is centered on multi-category video games, consisting of two {components}: Balance-driven Implicit Preferences Learning for data pre-processing and Clustering-based Diversified Recommendation {Module} for final prediction. The first module aims to achieve a balanced representation of implicit feedback in game time, thereby discovering a comprehensive view of player interests across different categories. The second module adopts category-aware representation learning to cluster and select players and games based on balanced implicit preferences, and then employs asymmetric neighbor aggregation to achieve diversified recommendations. Experimental results on a real-world dataset demonstrate the superiority of our proposed method over existing approaches in terms of game diversity recommendations.

IDVT: Interest-aware Denoising and View-guided Tuning for Social Recommendation

In the information age, recommendation systems are vital for efficiently filtering information and identifying user preferences. Online social platforms have enriched these systems by providing valuable auxiliary information. Socially connected users are assumed to share similar preferences, enhancing recommendation accuracy and addressing cold start issues. However, empirical findings challenge the assumption, revealing that certain social connections can actually harm system performance. Our statistical analysis indicates a significant amount of noise in the social network, where many socially connected users do not share common interests. To address this issue, we propose an innovative \underline{I}nterest-aware \underline{D}enoising and \underline{V}iew-guided \underline{T}uning (IDVT) method for the social recommendation. The first ID part effectively denoises social connections. Specifically, the denoising process considers both social network structure and user interaction interests in a global view. Moreover, in this global view, we also integrate denoised social information (social domain) into the propagation of the user-item interactions (collaborative domain) and aggregate user representations from two domains using a gating mechanism. To tackle potential user interest loss and enhance model robustness within the global view, our second VT part introduces two additional views (local view and dropout-enhanced view) for fine-tuning user representations in the global view through contrastive learning. Extensive evaluations on real-world datasets with varying noise ratios demonstrate the superiority of IDVT over state-of-the-art social recommendation methods.

Asymmetric feature interaction for interpreting model predictions

In natural language processing (NLP), deep neural networks (DNNs) could model complex interactions between context and have achieved impressive results on a range of NLP tasks. Prior works on feature interaction attribution mainly focus on studying symmetric interaction that only explains the additional influence of a set of words in combination, which fails to capture asymmetric influence that contributes to model prediction. In this work, we propose an asymmetric feature interaction attribution explanation model that aims to explore asymmetric higher-order feature interactions in the inference of deep neural NLP models. By representing our explanation with an directed interaction graph, we experimentally demonstrate interpretability of the graph to discover asymmetric feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods in identifying influential features for model predictions. Our code is available at https://github.com/StillLu/ASIV.

Collaborative Residual Metric Learning

In collaborative filtering, distance metric learning has been applied to matrix factorization techniques with promising results. However, matrix factorization lacks the ability of capturing collaborative information, which has been remarked by recent works and improved by interpreting user interactions as signals. This paper aims to find out how metric learning connect to these signal-based models. By adopting a generalized distance metric, we discovered that in signal-based models, it is easier to estimate the residual of distances, which refers to the difference between the distances from a user to a target item and another item, rather than estimating the distances themselves. Further analysis also uncovers a link between the normalization strength of interaction signals and the novelty of recommendation, which has been overlooked by existing studies. Based on the above findings, we propose a novel model to learn a generalized distance user-item distance metric to capture user preference in interaction signals by modeling the residuals of distance. The proposed CoRML model is then further improved in training efficiency by a newly introduced approximated ranking weight. Extensive experiments conducted on 4 public datasets demonstrate the superior performance of CoRML compared to the state-of-the-art baselines in collaborative filtering, along with high efficiency and the ability of providing novelty-promoted recommendations, shedding new light on the study of metric learning-based recommender systems.

Efficient and Scalable Recommendation via Item-Item Graph Partitioning

Collaborative filtering (CF) is a widely searched problem in recommender systems. Linear autoencoder is a kind of well-established method for CF, which estimates item-item relations through encoding user-item interactions. Despite the excellent performance of linear autoencoders, the rapidly increasing computational and storage costs caused by the growing number of items limit their scalabilities in large-scale real-world scenarios. Recently, graph-based approaches have achieved success on CF with high scalability, and have been shown to have commonalities with linear autoencoders in user-item interaction modeling. Motivated by this, we propose an efficient and scalable recommendation via item-item graph partitioning (ERGP), aiming to address the limitations of linear autoencoders. In particular, a recursive graph partitioning strategy is proposed to ensure that the item set is divided into several partitions of finite size. Linear autoencoders encode user-item interactions within partitions while preserving global information across the entire item set. This allows ERGP to have guaranteed efficiency and high scalability when the number of items increases. Experiments conducted on 3 public datasets and 3 open benchmarking datasets demonstrate the effectiveness of ERGP, which outperforms state-of-the-art models with lower training time and storage costs.