Hateful videos have become prevalent on online platforms, highlighting an urgent need for effective detection. However, existing studies primarily focus on binary classification and fail to provide contextual rationales that reveal the implicit meanings behind these judgments, significantly undermining model explainability. To fill this gap, we aim to achieve explainable hateful video detection, enabling models to provide contextual rationales that integrate relevant evidence and logical reasoning alongside decisions. This approach can comprehensively enhance the understanding of video content and the explainability of the decision-making process. We first introduce two datasets, Ex-HateMM and Ex-ImpliHateVid, for explainable hateful video detection. Each dataset provides fine-grained annotations of multimodal harmful elements, along with contextual rationales. We then propose an Information Augmentation and Reasoning Enhancement (IARE) framework designed for explainable detection. The framework employs an information augmentation phase that leverages the multimodal chain-of-thought to integrate harmful elements, thereby enriching rationale evidence. Additionally, IARE incorporates a reasoning enhancement phase, in which Direct Preference Optimization guides the model toward correct reasoning paths and away from incorrect ones, thereby improving the logical coherence of its justifications. We conduct extensive experiments on the two datasets, comparing multiple baselines with our proposed IARE framework. The results demonstrate that IARE achieves state-of-the-art performance while also generating accurate rationales.

Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-augmented generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness. In this paper, we comprehensively review existing efforts that integrate RAG techniques into AIGC scenarios. We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators. This unified perspective encompasses all RAG scenarios, illuminating advancements and pivotal technologies that help with potential future progress. We also summarize additional enhancement methods for RAG, facilitating effective engineering and implementation of RAG systems. Then from another view, we survey practical applications of RAG across different modalities and tasks, offering valuable references for researchers and practitioners. Furthermore, we introduce the benchmarks for RAG, discuss the limitations of current RAG systems, and suggest potential directions for future research.

Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR. However, we identify two critical challenges in existing LLM-based SR methods: 1) embedding collapse when incorporating pre-trained collaborative embeddings and 2) catastrophic forgetting of quantized embeddings when utilizing semantic IDs. These issues dampen the model scalability and lead to suboptimal recommendation performance. Therefore, based on LLMs like Llama3-8B-instruct, we introduce a novel SR framework named MME-SID, which integrates multimodal embeddings and quantized embeddings to mitigate embedding collapse. Additionally, we propose a Multimodal Residual Quantized Variational Autoencoder (MM-RQ-VAE) with maximum mean discrepancy as the reconstruction loss and contrastive learning for alignment, which effectively preserve intra-modal distance information and capture inter-modal correlations, respectively. To further alleviate catastrophic forgetting, we initialize the model with the trained multimodal code embeddings. Finally, we fine-tune the LLM efficiently using LoRA in a multimodal frequency-aware fusion manner. Extensive experiments on three public datasets validate the superior performance of MME-SID thanks to its capability to mitigate embedding collapse and catastrophic forgetting. The implementation code and datasets are publicly available for reproduction: https://github.com/Applied-Machine-Learning-Lab/MME-SID.

Large Language Models for Recommendation (LLM4Rec) have shown great potential. Many LLM4Rec approaches technically leverage a learnable tokenizer to assign item identifiers and then enable a Recommender LLM (RecLLM) to process tokenized items and user interactions for recommendation. However, a key challenge in their real-world deployment is the need for continuous retraining over time to accommodate new items and evolving user interests. While existing retraining methods can be applied to RecLLMs, learnable tokenizers introduce additional retraining challenges. We conduct a comprehensive investigation into the joint retraining of RecLLMs and learnable tokenizers, identifying key issues such as identifier collision and identifier shifts across periods. To address these, we propose Reformer, an incremental learning framework to fine-tune RecLLMs and learnable tokenizers at each period. Reformer employs a dynamic codebook to mitigate identifier collision by appending new codes and enforcing a diversity-oriented code assignment constraint. Additionally, Reformer adopts an identifier freezing strategy to ensure the invariance of previously assigned item identifiers across retraining periods. We instantiate Reformer on two representative RecLLMs and conduct extensive experiments on three real-world datasets. Substantial results demonstrate its superior retraining performance, facilitating the real-world deployment of LLM4Rec.

Sequential Recommendation (SR) aims to leverage the sequential patterns in users' historical interactions to accurately track their preferences. However, the primary reliance of existing SR methods on collaborative data results in challenges such as the cold-start problem and sub-optimal performance. Concurrently, despite the proven effectiveness of large language models (LLMs), their integration into commercial recommender systems is impeded by issues such as high inference latency, incomplete capture of all distribution statistics, and catastrophic forgetting. To address these issues, we introduce a novel Pre-train, Align, and Disentangle (PAD) framework to enhance SR models with LLMs. In particular, we initially pre-train both the SR and LLM models to obtain collaborative and textual embeddings. Subsequently, we propose a characteristic recommendation-anchored alignment loss using multi-kernel maximum mean discrepancy with Gaussian kernels. Lastly, a triple-experts architecture, comprising aligned and modality-specific experts with disentangled embeddings, is fine-tuned in a frequency-aware manner. Experimental results on three public datasets validate the efficacy of PAD, indicating substantial enhancements and compatibility with various SR backbone models, particularly for cold items. The code and datasets are accessible for reproduction: https://github.com/Applied-Machine-Learning-Lab/PAD.

To optimize large Transformer model training, both efficient parallel computing and advanced data management are indispensable. However, current methods often assume a stable and uniform training workload, neglecting data-induced imbalances-arising from both sampling and packing processes-which can impede training performance. Specifically, data sampling imbalance arises from uneven sequence length distribution of the training data, while data packing imbalance stems from the discrepancy between the linear memory complexity and quadratic time complexity of the attention mechanism. To address these imbalance issues, we develop Hydraulis, which jointly optimizes the parallel strategies and data assignment. For one thing, we introduce large model training with dynamic heterogeneous parallel strategies in response to the sequence length variations within and across training iterations. For another, we devise a two-stage data assignment approach, which strikes a good balance in terms of the training workloads both within and across model replicas. Empirical results demonstrate that Hydraulis outperforms existing systems by 1.32-2.66×. Our source code is available: https://github.com/PKU-DAIR/Hetu.

With the proliferation of Large Language Models (LLMs) in Business Intelligence (BI), existing solutions face critical challenges in industrial deployments: functionality deficiencies from legacy systems failing to meet evolving LLM-era user demands, interaction limitations from single-round SQL generation paradigms inadequate for multi-round clarification, and cost for domain adaptation arising from cross-domain methods migration. We present SiriusBI, a practical LLM-powered BI system addressing the challenges of industrial deployments through three key innovations: (a) An end-to-end architecture integrating multi-module coordination to overcome functionality gaps in legacy systems; (b) A multi-round dialogue with querying mechanism, consisting of semantic completion, knowledge-guided clarification, and proactive querying processes, to resolve interaction constraints in SQL generation; (c) A data-conditioned SQL generation method selection strategy that supports both an efficient one-step Fine-Tuning approach and a two-step method leveraging Semantic Intermediate Representation for low-cost cross-domain applications. Experiments on both real-world datasets and public benchmarks demonstrate the effectiveness of SiriusBI. User studies further confirm that SiriusBI enhances both productivity and user experience. As an independent service on Tencent's data platform, SiriusBI is deployed across finance, advertising, and cloud sectors, serving dozens of enterprise clients. It achieves over 93% accuracy in SQL generation and reduces data analysts' query time from minutes to seconds in real-world applications.

Recommender systems with cascading architecture play an increasingly significant role in online recommendation platforms, where the approach to dealing with negative feedback is a vital issue. For instance, in short video ad platforms, users tend to quickly slip away from ad candidates that they feel aversive, and recommender systems are expected to receive these explicit negative feedback and make adjustments to avoid these recommendations.Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback. In addition, we introduce a Pareto optimization solver to guarantee a better trade-off between recency and model performance.In conclusion, we propose Pareto-based Multi-Objective Recommender System with forgetting curve (PMORS), which can be applied to any multi-objective recommendation and show sufficiently superiority when facing explicit negative feedback.We have conducted evaluations of PMORS and achieved favorable outcomes in short-video scenarios on both public dataset and industrial dataset. After being deployed on an online short video ad platform named WeChat Channels Ads in May, 2023, PMORS has not only demonstrated promising results for both consistency and recency but also achieved an improvement of up to +1.45% Gross Merchandise Volume (GMV).

Click-through rate (CTR) prediction is a crucial area of research in online advertising. While binary cross entropy (BCE) has been widely used as the optimization objective for treating CTR prediction as a binary classification problem, recent advancements have shown that combining BCE loss with an auxiliary ranking loss can significantly improve performance. However, the full effectiveness of this combination loss is not yet fully understood. In this paper, we uncover a new challenge associated with the BCE loss in scenarios where positive feedback is sparse: the issue of gradient vanishing for negative samples. We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability. To validate our perspective, we conduct theoretical analysis and extensive empirical evaluations on public datasets. Additionally, we successfully integrate the ranking loss into Tencent's online advertising system, achieving notable lifts of 0.70% and 1.26% in Gross Merchandise Value (GMV) for two main scenarios. The code is openly accessible at: https://github.com/SkylerLinn/Understanding-the-Ranking-Loss.

We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations. Our study begins by showcasing our approaches to preserving prior knowledge when encoding features of diverse types into embedding representations. We specifically address sequence features, numeric features, and pre-trained embedding features. Subsequently, we delve into two crucial challenges related to feature representation: the dimensional collapse of embeddings and the interest entanglement across different tasks or scenarios. We propose several practical approaches to address these challenges that result in robust and disentangled recommendation representations. We then explore several training techniques to facilitate model optimization, reduce bias, and enhance exploration. Additionally, we introduce three analysis tools that enable us to study feature correlation, dimensional collapse, and interest entanglement. This work builds upon the continuous efforts of Tencent's ads recommendation team over the past decade. It summarizes general design principles and presents a series of readily applicable solutions and analysis tools. The reported performance is based on our online advertising platform, which handles hundreds of billions of requests daily and serves millions of ads to billions of users.

Click-through rate (CTR) prediction plays a pivotal role in real-world applications, particularly in recommendation systems and online advertising. A significant research branch in this domain focuses on user behavior modeling. Current research predominantly centers on modeling co-occurrence relationships between the target item and items previously interacted with by users. However, this focus neglects the intricate modeling of user behavior patterns. In reality, the abundance of user interaction records encompasses diverse behavior patterns, indicative of a spectrum of habitual paradigms. These patterns harbor substantial potential to significantly enhance CTR prediction performance. To harness the informational potential within behavior patterns, we extend Target Attention (TA) to Target Pattern Attention (TPA) to model pattern-level dependencies. Furthermore, three critical challenges demand attention: the inclusion of unrelated items within patterns, data sparsity of patterns, and computational complexity arising from numerous patterns. To address these challenges, we introduce the Deep Pattern Network (DPN), designed to comprehensively leverage information from behavior patterns. DPN efficiently retrieves target-related behavior patterns using a target-aware attention mechanism. Additionally, it contributes to refining patterns through a pre-training paradigm based on self-supervised learning while promoting dependency learning within sparse patterns. Our comprehensive experiments, conducted across three public datasets, substantiate the superior performance and broad compatibility of DPN.

Side-information integrated sequential recommendation incorporates supplementary information to alleviate the issue of data sparsity. The state-of-the-art works mainly leverage some side information to improve the attention calculation to learn user representation more accurately. However, there are still some limitations to be addressed in this topic. Most of them merely learn the user representation at the item level and overlook the association of the item sequence and the side-information sequences when calculating the attentions, which results in the incomprehensive learning of user representation. Some of them learn the user representations at both the item and side-information levels, but they still face the problem of insufficient optimization of multiple user representations. To address these limitations, we propose a novel model, i.e., Multi-Sequence Sequential Recommender (MSSR), which learns the user's multiple representations from diverse sequences. Specifically, we design a multi-sequence integrated attention layer to learn more attentive pairs than the existing works and adaptively fuse these pairs to learn user representation. Moreover, our user representation alignment module constructs the self-supervised signals to optimize the representations. Subsequently, they are further refined by our side information predictor during training. For item prediction, our MSSR extra considers the side information of the candidate item, enabling a comprehensive measurement of the user's preferences. Extensive experiments on four public datasets show that our MSSR outperforms eleven state-of-the-art baselines. Visualization and case study also demonstrate the rationality and interpretability of our MSSR.

Prevailing calibration methods may fail to generalize well due to the pervasively delayed feedback issue in online advertising. That is, the labels of recent samples are more likely to be inaccurate because of the delayed feedback by users, while the old samples with complete feedback may suffer from the data shift compared to the recent ones. In this paper, we propose to calibrate conversion rate prediction models considering delayed feedback via the knowledge distillation technique. Specifically, we deploy a teacher model modeling by the samples with complete feedback to learn long-term conversion patterns and a student model modeling by the recent data to reduce the impact of data shift. We also devise a distillation loss to buoy the student model to learn from the teacher. Experimental results on two real-world advertising conversion rate prediction datasets demonstrate that our method can provide more calibrated predictions compared with the existing ones. We also exhibit that our method can be extended to different base models.

In Click-through rate (CTR) prediction models, a user’s interest is usually represented as a fixed-length vector based on her history behaviors. Recently, several methods are proposed to learn an attentive weight for each user behavior and conduct weighted sum pooling. However, these methods only manually select several fields from the target item side as the query to interact with the behaviors, neglecting the other target item fields, as well as user and context fields. Directly including all these fields in the attention may introduce noise and deteriorate the performance. In this paper, we propose a novel model named AutoAttention, which includes all item/user/context side fields as the query, and assigns a learnable weight for each field pair between behavior fields and query fields. Pruning on these field pairs via these learnable weights lead to automatic field pair selection, so as to identify and remove noisy field pairs. Though including more fields, the computation cost of AutoAttention is still low due to using a simple attention function and field pair selection. Extensive experiments on the public dataset and Tencent’s production dataset demonstrate the effectiveness of the proposed approach.

Gradient boosting tree (GBT), a widely used machine learning algorithm, achieves state-of-the-art performance in academia, industry, and data analytics competitions. Although existing scalable systems which implement GBT, such as XGBoost and MLlib, perform well for datasets with medium-dimensional features, they can suffer performance degradation for many industrial applications where the trained datasets contain highdimensional features. The performance degradation derives from their inefficient mechanisms for model aggregation-either mapreduce or all-reduce. To address this high-dimensional problem, we propose a scalable execution plan using the parameter server architecture to facilitate the model aggregation. Further, we introduce a sparse-pull method and an efficient index structure to increase the processing speed. We implement a GBT system, namely TencentBoost, in the production cluster of Tencent Inc. The empirical results show that our system is 2-20× faster than existing platforms.

Video recommendation has attracted growing attention in recent years. However, conventional techniques have limitations in real-time processing, accuracy or scalability for the large-scale video data. To address the deficiencies of current recommendation systems, we introduce some new techniques to provide real-time and accurate recommendations to users in the video recommendation system of Tencent Inc.. We develop a scalable online collaborative filtering algorithm based upon matrix factorization, with an adjustable updating strategy considering implicit feedback solution of different user actions. To select high-quality candidate videos for real-time top-N recommendation generation, we utilize additional factors like video type and time factor to compute similar videos. In addition, we propose the scalable implementation of our algorithm together with some optimizations to make the recommendations more efficient and accurate, including the demographic filtering and demographic training. To demonstrate the effectiveness and efficiency of our model, we conduct comprehensive experiments by collecting real data from Tencent Video. Furthermore, our video recommendation system is in production to provide recommendation services in Tencent Video, one of the largest video sites in China, and verifies its superiority in performance.

Real-time stream computing becomes increasingly important due to the sheer amount of content continually generated in various kinds of social networks and e-commerce websites. Many distributed real-time computing systems have been built for different applications, and Storm is one of the most prominent systems with high-performance, fault-tolerance and low-latency features. However, the Storm programming paradigm is low level and leaves programmers’ codes hard to maintain and reuse. In this paper, we present a high-level abstraction system on Storm, called POS. The POS system provides a Pig Latin-like language on top of the Storm execution engine. Programmers can write POS program, and the system compiles the program into physical plans which are executed over Storm. We discuss the challenges in developing POS system and elaborate on its implementation details. Our experiments show that POS yields satisfactory performance compared with raw Storm.

With the arrival of the big data era, opportunities as well as challenges arise in both industry and academia. As an important service in most web applications, accurate real-time recommendation in the context of big data is of high demand. Traditional recommender systems that analyze data and update models at regular time intervals cannot satisfy the requirements of modern web applications, calling for real-time recommender systems.