HGraphormer injects the hypergraph structure information (local information) into Transformers (global information) by combining the attention matrix and hypergraph Laplacian.
Recently, multimodal recommendations have gained increasing attention for effectively addressing the data sparsity problem by incorporating modality-based representations.
Micro-videos have recently gained immense popularity, sparking critical research in micro-video recommendation with significant implications for the entertainment, advertising, and e-commerce industries.
Learning a recommender system model from an item's raw modality features (such as image, text, audio, etc.
Then, to show the effectiveness of the dataset's image features, we substitute the itemID embeddings (from IDNet) with a powerful vision encoder that represents items using their raw image pixels.
Ranked #1 on Recommendation Systems on PixelRec
If yes, we benchmark these existing adapters, which have been shown to be effective in NLP and CV tasks, in the item recommendation settings.
Furthermore, we compare the performance of the TCF paradigm utilizing the most powerful LMs to the currently dominant ID embedding-based paradigm and investigate the transferability of this TCF paradigm.
In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.
Existing benchmark datasets for recommender systems (RS) either are created at a small scale or involve very limited forms of user feedback.
Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions.
That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms.
In this paper, we plan to exploit such redundancy phenomena to improve the performance of RS.
This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system.
To realize such a goal, we propose AdaRec, a knowledge distillation (KD) framework which compresses knowledge of a teacher model into a student model adaptively according to its recommendation scene by using differentiable Neural Architecture Search (NAS).
In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization.
Fine-tuning works as an effective transfer learning technique for this objective, which adapts the parameters of a pre-trained model from the source domain to the target domain.
We validate the performance of StackRec by instantiating it with four state-of-the-art SR models in three practical scenarios with real-world datasets.
In this paper, we delve on research to continually learn user representations task by task, whereby new tasks are learned while using partial parameters from old ones.
Specifically, our framework divides proximal information units into chunks, and performs memory access at certain time steps, whereby the number of memory operations can be greatly reduced.
Current state-of-the-art sequential recommender models are typically based on a sandwich-structured deep neural network, where one or more middle (hidden) layers are placed between the input embedding layer and output softmax layer.
To overcome this issue, we develop a parameter efficient transfer learning architecture, termed as PeterRec, which can be configured on-the-fly to various downstream tasks.
In this work, we emphasize on modeling the correlations among embedding dimensions in neural networks to pursue higher effectiveness for CF.
To capture the sequential dependencies, existing methods resort either to data augmentation techniques or left-to-right style autoregressive training. Since these methods are aimed to model the sequential nature of user behaviors, they ignore the future data of a target interaction when constructing the prediction model for it.
To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning.
Information Retrieval Multimedia
Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation.
Stochastic Gradient Descent (SGD) with negative sampling is the most prevalent approach to learn word representations.
Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i. e., the gap between images' visual features (low-level) and labels' semantic features (high-level).
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood.