Frequency-domain sequential recommendation models enhance sequence representation capacity through spectral transformations. However, existing methods typically adopt coarse-grained spectrum reweighting strategies that strengthen high-frequency components while amplifying random noise within frequency bands. Moreover, they generally rely on a coupled modeling mechanism that handles both long-term and short-term preferences within a single backbone network, lacking dedicated modeling paths tailored to their distinct temporal characteristics. To address these challenges, we propose a Balanced Frequency Decoupling Sequential Recommendation model (BFDRec). Specifically, we design an energy-aware spectrum denoising mechanism to adaptively suppress low-energy noises according to the energy distribution within each frequency band while preserving salient behavioral fluctuation signals. Additionally, we construct a multi-scale decoupled architecture to model users' multi-scale preferences and adaptively integrate them through a dynamic gating mechanism, aligning the sequence modeling process with the distinct temporal characteristics of different frequency bands. Extensive experiments across five real-world datasets demonstrate that BFDRec effectively achieves noise suppression and accurate multi-scale preference modeling, with average improvements of 6.67% and 5.05% in HR and NDCG, respectively, over advanced baseline models. Our code is available at https://anonymous.4open.science/r/BFDRec.

To maintain an effective memory of old knowledge in a dynamically growing knowledge environment, continual knowledge graph embedding (CKGE) focuses on alleviating catastrophic forgetting. However, existing CKGE methods still suffer substantial performance degradation in dynamic knowledge graphs (DKG). We have found this challenge is mainly posed by spurious forgetting, a previously overlooked phenomenon that arises from the inherent interference effects in the continual learning (CL) process. In this paper, we deeply explore spurious forgetting in CKGE. First, we reveal two primary causes of spurious forgetting, knowledge interference and knowledge misalignment, and how to affect knowledge biasing within dynamic learning scenarios. Second, to fill this research gap, we propose a robust and efficient CKGE method (DebiasedKGE) for mitigating spurious forgetting. Specifically, to alleviate knowledge interference, we propose a mutual information-guided disentangled learning mechanism, which identifies latent features of different knowledge types and learns independent semantic representations for each, thereby reducing interference in knowledge embedding. Furthermore, to mitigate the deviation of new knowledge from previously learned knowledge, we design a dual-view regularized knowledge alignment mechanism that jointly constrains both the magnitude and direction of embedding transitions. Finally, we evaluate DebiasedKGE on four public CKGE datasets and two additional datasets constructed to contain knowledge perturbations of different dimensions. The results show that DebiasedKGE effectively alleviates spurious forgetting and achieves significant performance improvements. Our codes and datasets are available at https://anonymous.4open.science/r/DebiasedKGE.

Conversational recommender systems provide users with item recommendations via interactive dialogues. Existing methods using graph neural networks have been proven to be an adequate representation of the learning framework for knowledge graphs. However, the knowledge graph involved in the dialogue context is vast and noisy, especially the noise graph nodes, which restrict the primary node’s aggregation to neighbor nodes. In addition, although the recurrent neural network can encode the local structure of word sequences in a dialogue context, it may still be challenging to remember long-term dependencies. To tackle these problems, we propose a sparse multi-hop conversational recommender model named SMCR, which accurately identifies important edges through matching items, thus reducing the computational complexity of sparse graphs. Specifically, we design a multi-hop attention network to encode dialogue context, which can quickly encode the long dialogue sequences to capture the long-term dependencies. Furthermore, we utilize a variational auto-encoder to learn topic information for capturing syntactic dependencies. Extensive experiments on the travel dialogue dataset show significant improvements in our proposed model over the state-of-the-art methods in evaluating recommendation and dialogue generation.

Knowledge graph (KG) is of growing significance in enabling explainable recommendations. Recent research works involve constructing propagation-based recommendation models. Nevertheless, most of the current propagation-based recommendation methods cannot explicitly handle the diverse relations of items, resulting in the inability to model the underlying hierarchies and diverse relations, and it is difficult to capture the high-order collaborative information of items to learn premium representation. To address these issues, we leverage hyperbolic dynamic neural networks for knowledge-aware recommendation (KHDNN). Technically speaking, we embed users and items (forming user–item bipartite graphs), along with entities and relations (constituting KGs), into hyperbolic space, followed by encoding these embeddings using an encoder. The encoded embedding is passed through a hyperbolic dynamic filter to explicitly handle relations and model different relational structures. Furthermore, we design a fresh aggregation strategy based on relations to propagate and capture higher-order collaborative signals as well as knowledge associations. Meanwhile, we extract semantic information via a bilateral memory network to fuse item collaborative signals and knowledge associations. Empirical results from four datasets show that KHDNN surpasses cutting-edge baseline methods. Additionally, we demonstrate that the KHDNN can perform knowledge-aware recommendations with complex relations.