Large language models (LLMs) have significantly influenced advancements in sequential recommendation. Nevertheless, the integration and alignment of LLMs with sequence recommenders is often underexploited in current research. Existing LLM-based sequential recommenders mostly rely on textual descriptions, neglecting user visual preferences and suffering from LLM hallucination, which can result in suboptimal recommendations. To address these challenges, we propose AlmostRec, a novel framework that incorporates multimodal information, including historical interaction IDs, textual descriptions, and images of items into large foundation models, to facilitate controllable predictions. Instead of employing a textual LLM, AlmostRec utilizes a large multimodal model (LMM) as a backbone, complemented by a content-behavior guidance module to align multimodal information. The framework's ID prediction objective, enhanced via the parameter-efficient LoRA approach, ensures a principal alignment with the sequential recommendation and is not swayed by hallucinations. AlmostRec effectively bridges the gap between large vision-language models with sequential recommenders, offering contextually relevant predictions in multimodal scenarios. Experimental results on real-world datasets demonstrate the superior performance of AlmostRec compared to both traditional and recent LLM-based recommendation approaches.

Sequential recommendation aims to recommend the next items that a target user may have interest in based on the user’s sequence of past behaviors, which has become a hot research topic in both academia and industry. In the literature, sequential recommendation adopts a Sequence-to-Item or Sequence-to-Sequence training strategy, which supervises a sequential model with a user’s next one or more behaviors as the labels and the sequence of the past behaviors as the input. However, existing powerful sequential recommendation approaches employ more and more complex deep structures such as Transformer in order to accurately capture the sequential patterns, which heavily rely on hand-crafted designs on key attention mechanism to achieve state-of-the-art performance, thus failing to automatically obtain the optimal design of attention representation architectures in various scenarios with different data. Other works on classic automated deep recommender systems only focus on traditional settings, ignoring the problem of sequential scenarios. In this article, we study the problem of automated sequential recommendation, which faces two main challenges: (1) How can we design a proper search space tailored for attention automation in sequential recommendation, and (2) How can we accurately search effective attention representation architectures considering multiple user interests reflected in the sequential behavior. To tackle these challenges, we propose an automated disentangled sequential recommendation (AutoDisenSeq) model. In particular, we employ neural architecture search (NAS) and design a search space tailored for automated attention representation in attentive intention-disentangled sequential recommendation with an expressive and efficient space complexity of \(O(n^{2})\) given \(n\) as the number of layers. We further propose a context-aware parameter sharing mechanism taking characteristics of each sub-architecture into account to enable accurate architecture performance estimations and great flexibility for disentanglement of latent intention representation. Moreover, we propose AutoDisenSeq-large language model (LLM), which utilizes the textual understanding power of LLM as a guidance to refine the candidate list for recommendation from AutoDisenSeq. We conduct extensive experiments to show that our proposed AutoDisenSeq model and AutoDisenSeq-LLM model outperform existing baseline methods on four real-world datasets in both overall recommendation and cold-start recommendation scenarios.

Congestion control has been a fundamental research focus in web transmission for over 30 years. However, with diverse network scenarios like cellular networks and WiFi, traditional models might no longer accurately describe current network conditions -- we empirically observe that the minimum round-trip time (RTTmin) still varies under different network conditions, challenging the assumption of its constancy in traditional models. In this paper, we model it as a normal distribution based on our measurements and propose a novel congestion control algorithm LingBo. LingBo consists of two phases: an offline trained decision model to achieve goals under different RTTmin distributions, and an online perception scheme to detect the current RTTmin distribution. We evaluate LingBo in various network environments and find it consistently performs well in terms of power metric and throughput compared to recent state-of-the-art baselines. Our code is available at https://github.com/thumedia/LingBo.

Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables collaborative training of machine learning models among multiple participants. However, despite recent progress, existing federated learning systems can still not handle heterogeneous models. For instance, candidate clients with heterogeneous models are inaccessible to the established federated system. And within the federated system, local models are forbidden to be updated to become heterogeneous models, even though the updated models work better.

Modeling powerful interactions is a critical challenge in Click-through rate (CTR) prediction, which is one of the most typical machine learning tasks in personalized advertising and recommender systems. Although developing hand-crafted interactions is effective for a small number of datasets, it generally requires laborious and tedious architecture engineering for extensive scenarios. In recent years, several neural architecture search (NAS) methods have been proposed for designing interactions automatically. However, existing methods only explore limited types and connections of operators for interaction generation, leading to low generalization ability. To address these problems, we propose a more general automated method for building powerful interactions named AutoPI. The main contributions of this paper are as follows: AutoPI adopts a more general search space in which the computational graph is generalized from existing network connections, and the interactive operators in the edges of the graph are extracted from representative hand-crafted works. It allows searching for various powerful feature interactions to produce higher AUC and lower Logloss in a wide variety of applications. Besides, AutoPI utilizes a gradient-based search strategy for exploration with a significantly low computational cost. Experimentally, we evaluate AutoPI on a diverse suite of benchmark datasets, demonstrating the generalizability and efficiency of AutoPI over hand-crafted architectures and state-of-the-art NAS algorithms.

The leading learning-based rate control method, i.e., QARC, achieves state-of-the-art performances but fails to interpret the fundamental principles, and thus lacks the abilities to further improve itself efficiently. In this paper, we propose EQARC (Explainable QARC) via reconstructing QARC's modules, aiming to demystify how QARC works. In details, we first utilize a novel hybrid attention-based CNN+GRU model to re-characterize the original quality prediction network and reasonably replace the QARC's 1D-CNN layers with 2D-CNN layers. Using trace-driven experiment, we demonstrate the superiority of EQARC over existing state-of-the-art approaches. Next, we collect several useful information from each interpretable modules and learn the insight of EQARC. Following this step, we further propose AQARC (Advanced QARC), which is the light-weighted version of QARC. Experimental results show that AQARC achieves the same performances as the QARC with an overhead reduction of 90%. In short, through learning from deep learning, we generalize a rate control method which can both reach high performance and reduce computation cost.

People and information are two core dimensions in a social network. People sharing information (such as blogs, news, albums, etc.) is the basic behavior. In this paper, we focus on predicting item-level social influence to answer the question Who should share What, which can be extended into two information retrieval scenarios: (1) Users ranking: given an item, who should share it so that its diffusion range can be maximized in a social network; (2) Web posts ranking: given a user, what should she share to maximize her influence among her friends. We formulate the social influence prediction problem as the estimation of a user-post matrix, in which each entry represents the strength of influence of a user given a web post. We propose a Hybrid Factor Non-Negative Matrix Factorization (HF-NMF) approach for item-level social influence modeling, and devise an efficient projected gradient method to solve the HF-NMF problem. Intensive experiments are conducted and demonstrate the advantages and characteristics of the proposed method.

In this paper, a novel unsupervised approach to mining categories from action video sequences is presented. This approach consists of two modules: action representation and learning model. Videos are regarded as spatially distributed dynamic pixel time series, which are quantized into pixel prototypes. After replacing the pixel time series with their corresponding prototype labels, the video sequences are compressed into 2D action matrices. We put these matrices together to form an multi-action tensor, and propose the joint matrix factorization method to simultaneously cluster the pixel prototypes into pixel signatures, and matrices into action classes. The approach is tested on public and popular Weizmann data set, and promising results are achieved.

Automatic topic discovery and tracking on web-shared videos can greatly benefit both web service providers and end users. Most of current solutions of topic detection and tracking were done on news and cannot be directly applied on web videos, because the semantic information of web videos is much less than that of news videos. In this paper, we propose a bipartite graph model to address this issue. The bipartite graph represents the correlation between web videos and their keywords, and automatic topic discovery is achieved through two steps - coarse topic filtering and fine topic re-ranking. First, a weight-updating co-clustering algorithm is employed to filter out topic candidates at a coarse level. Then the videos on each topic are re-ranked by analyzing the link structures of the corresponding bipartite graph. After the topics are discovered, the interesting ones can also be tracked over a period of time using the same bipartite graph model. The key is to propagate the relevant scores and keywords from the videos of interests to other relevant ones through the bipartite graph links. Experimental results on real web videos from YouKu, a YouTube counterpart in China, demonstrate the effectiveness of the proposed methods. We report very promising results.