Equipping large language models (LLMs) with external tools has emerged as a promising paradigm for addressing real-world tasks. Nonetheless, with the web-based tool ecosystems rapidly expanding, it is impractical to include all tools within the limited input length of LLMs. To alleviate these issues, researchers have explored incorporating a tool retrieval module to select the most relevant tools or represent tools as unique tokens within LLM parameters. However, most state-of-the-art methods are under transductive settings, assuming all tools have been observed during training. Such a setting deviates from reality as tools on the web are constantly updated and new tools are frequently added to the online ecosystem. When dealing with these unseen tools, which refer to tools not encountered during the training phase, these methods are limited by two key issues, including the large distribution shift and the sensitivity of semantic-only retrieval. To this end, inspired by human cognitive processes of mastering unseen tools through discovering and applying the logical information from prior experience, we introduce a novel Logic-Guided Semantic Bridging framework for inductive tool retrieval, namely, LoSemB, which aims to mine and transfer latent logical information for inductive tool retrieval without costly retraining. Specifically, LoSemB contains a logic-based embedding alignment module to mitigate distribution shifts and a relational augmented retrieval mechanism to overcome the limitations of semantic-only similarity methods. Extensive experiments demonstrate that LoSemB achieves advanced performance in both the inductive and transductive settings.

Click-through rate prediction tasks estimate interaction probabilities using user–item features (i.e., the combined set of user and item features). LLMs have emerged as a promising approach by organizing these features into prompts and fine-tuning LLMs to predict the interaction label. However, our feature-wise and interaction-wise analysis reveals two critical limitations, leading to incomplete relationship modeling between user–item features and interaction labels: (i) LLMs tend to utilize only a subset of available features, neglecting others, and (ii) they struggle with predictions for tail items that appear less frequently in the training samples. To bridge this gap, we propose Feature-Instructed Large language model for Monitoring ( FILM ), which introduces a self-monitoring temperature mechanism that dynamically guides LLMs to focus on informative features, and an auxiliary compaction loss that facilitates better feature-interaction relationship learning for tail items. By integrating these two designs, FILM not only improves feature utilization in LLMs but also enhances predictions for tail items. Furthermore, we demonstrate that FILM -generated interaction embeddings can be transferred to lightweight models, enabling efficient deployment. Extensive experiments demonstrate that FILM achieves significant performance improvements over state-of-the-art baselines by learning better relationships between user–item features and interaction labels and generalizes under different LLM backbones.

The graph neural network-based collaborative filtering (CF) models user-item interactions as a bipartite graph and performs iterative aggregation to enhance performance. Unfortunately, the aggregation process may amplify the popularity bias, which impedes user engagement with niche (unpopular) items. While some efforts have studied the popularity bias in CF, they often focus on modifying loss functions, which can not fully address the popularity bias in GNN-based CF models. This is because the debiasing loss can be falsely backpropagated to non-target nodes during the backward pass of the aggregation.

Graph anomaly detection (GAD) has wide applications in real-world networked systems. In many scenarios, people need to identify anomalies on new (sub)graphs, but they may lack labels to train an effective detection model. Since recent semi-supervised GAD methods, which can leverage the available labels as prior knowledge, have achieved superior performance than unsupervised methods, one natural idea is to directly adopt a trained semi-supervised GAD model to the new (sub)graphs for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issues, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the graph. Motivated by this, we formally define the problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph(s) and the unseen test graph(s). Nevertheless, it is a challenging task since only limited labels are available, and the normal data distribution may differ between training and testing data. Accordingly, we propose a data augmentation method namedAugAN(Augmentation forAnomaly andNormal distributions) to enrich training data and adopt a customized episodic training strategy for learning with the augmented data. Extensive experiments verify the effectiveness ofAugANin improving model generalizability.

Learning interest representation plays a core role in click-through rate prediction task. Existing Transformer-based approaches learn multi-interests from a sequence of interacted items with rich attributes. The attention weights explain how relevant an item's specific attribute sequence is to the user's interest. However, it implicitly assumes the independence of attributes regarding the same item, which may not always hold in practice. Empirically, the user places varied emphasis on different attributes to consider whether interacting with one item, which is unobserved. Independently modeling each attribute may allow attention to assign probability mass to some unimportant attributes. Collaborative attributes of varied emphasis can be incorporated to help the model more reasonably approximate attributes' relevance to others and generate refined interest representations.

Session-based recommendation aims to predict the next item that is most likely to be clicked by an anonymous user, based on his/her clicking sequence within one visit. It becomes an essential function of many recommender systems since it protects privacy. However, as the accumulated session records keep increasing, it becomes challenging to model the user interests since they would drift when the time span is large. Efforts have been devoted to handling dynamic user interests by modeling all historical sessions at one time or conducting offline retraining regularly. These solutions are far from practical requirements in terms of efficiency and capturing timely user interests. To this end, we propose a memory-efficient framework - TASRec. It constructs a graph for each day to model the relations among items. Thus, the same item on different days could have different neighbors, corresponding to the drifting user interests. We design a tailored graph neural network to embed this dynamic graph of items and learn temporal augmented item representations. Based on this, we leverage a sequential neural architecture to predict the next item of a given sequence. Experiments on real-world datasets demonstrate that TASRec outperforms state-of-the-art session-based recommendation methods.