Natural Language Processing (NLP) has emerged as a crucial technology for understanding and generating human language, playing an essential role in tasks such as machine translation, sentiment analysis, and more pertinently, question classification. As a subfield within NLP, question classification focuses on determining the type of information being sought, a fundamental step for downstream applications like question answering systems. This study presents an innovative ensemble approach for question classification, combining the strengths of Electra, GloVe, and LSTM models. Rigorously tested on the well-regarded TREC dataset, the model demonstrates how the integration of these disparate technologies can lead to superior results. Electra brings in its transformer-based capabilities for complex language understanding, GloVe offers global vector representations for capturing word-level semantics, and LSTM contributes its sequence learning abilities to model long-term dependencies. By fusing these elements strategically, our ensemble model delivers a robust and efficient solution for the complex task of question classification. Through rigorous comparisons with well-known models like BERT, RoBERTa, and DistilBERT, the ensemble approach verifies its effectiveness by attaining an 80% accuracy score on the test dataset.
Short-video recommendation is one of the most important recommendation applications in today's industrial information systems. Compared with other recommendation tasks, the enormous amount of feedback is the most typical characteristic. Specifically, in short-video recommendation, the easiest-to-collect user feedback is from the skipping behaviors, which leads to two critical challenges for the recommendation model. First, the skipping behavior reflects implicit user preferences, and thus it is challenging for interest extraction. Second, the kind of special feedback involves multiple objectives, such as total watching time, which is also very challenging. In this paper, we present our industrial solution in Kuaishou, which serves billion-level users every day. Specifically, we deploy a feedback-aware encoding module which well extracts user preference taking the impact of context into consideration. We further design a multi-objective prediction module which well distinguishes the relation and differences among different model objectives in the short-video recommendation. We conduct extensive online A/B testing, along with detailed and careful analysis, which verifies the effectiveness of our solution.
Black-box unsupervised domain adaptation (UDA) learns with source predictions of target data without accessing either source data or source models during training, and it has clear superiority in data privacy and flexibility in target network selection. However, the source predictions of target data are often noisy and training with them is prone to learning collapses. We propose BiMem, a bi-directional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly, leading to robust black-box UDA that can generalize across different visual recognition tasks. BiMem constructs three types of memory, including sensory memory, short-term memory, and long-term memory, which interact in a bi-directional manner for comprehensive and robust memorization of learnt features. It includes a forward memorization flow that identifies and stores useful features and a backward calibration flow that rectifies features' pseudo labels progressively. Extensive experiments show that BiMem achieves superior domain adaptation performance consistently across various visual recognition tasks such as image classification, semantic segmentation and object detection.
In today's machine learning (ML) models, any part of the training data can affect its output. This lack of control for information flow from training data to model output is a major obstacle in training models on sensitive data when access control only allows individual users to access a subset of data. To enable secure machine learning for access controlled data, we propose the notion of information flow control for machine learning, and develop a secure Transformer-based language model based on the Mixture-of-Experts (MoE) architecture. The secure MoE architecture controls information flow by limiting the influence of training data from each security domain to a single expert module, and only enabling a subset of experts at inference time based on an access control policy. The evaluation using a large corpus of text data shows that the proposed MoE architecture has minimal (1.9%) performance overhead and can significantly improve model accuracy (up to 37%) by enabling training on access-controlled data.
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information as it learns new information. As large language models (LLMs) have shown excellent performance, it is interesting to uncover whether CF exists in the continual fine-tuning of LLMs. In this study, we empirically evaluate the forgetting phenomenon in LLMs' knowledge, from the perspectives of domain knowledge, reasoning, and reading comprehension. The experiments demonstrate that catastrophic forgetting is generally observed in LLMs ranging from 1b to 7b. Furthermore, as the scale increases, the severity of forgetting also intensifies. Comparing the decoder-only model BLOOMZ with the encoder-decoder model mT0, BLOOMZ suffers less forgetting and maintains more knowledge. We also observe that LLMs can mitigate language bias (e.g. gender bias) during continual fine-tuning. Moreover, we find that ALPACA can maintain more knowledge and capacity compared with LLAMA during the continual fine-tuning, which implies that general instruction tuning can help mitigate the forgetting phenomenon of LLMs in the further fine-tuning process.
While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that augments diffusion models with low-dimensional latent variables that capture high-level factors of variation in the data. InfoDiffusion relies on a learning objective regularized with the mutual information between observed and hidden variables, which improves latent space quality and prevents the latents from being ignored by expressive diffusion-based decoders. Empirically, we find that InfoDiffusion learns disentangled and human-interpretable latent representations that are competitive with state-of-the-art generative and contrastive methods, while retaining the high sample quality of diffusion models. Our method enables manipulating the attributes of generated images and has the potential to assist tasks that require exploring a learned latent space to generate quality samples, e.g., generative design.
With the meteoric rise of video-on-demand (VOD) platforms, users face the challenge of sifting through an expansive sea of content to uncover shows that closely match their preferences. To address this information overload dilemma, VOD services have increasingly incorporated recommender systems powered by algorithms that analyze user behavior and suggest personalized content. However, a majority of existing recommender systems depend on explicit user feedback in the form of ratings and reviews, which can be difficult and time-consuming to collect at scale. This presents a key research gap, as leveraging users' implicit feedback patterns could provide an alternative avenue for building effective video recommendation models, circumventing the need for explicit ratings. However, prior literature lacks sufficient exploration into implicit feedback-based recommender systems, especially in the context of modeling video viewing behavior. Therefore, this paper aims to bridge this research gap by proposing a novel video recommendation technique that relies solely on users' implicit feedback in the form of their content viewing percentages.
Monocular 3D object detection is a crucial and challenging task for autonomous driving vehicle, while it uses only a single camera image to infer 3D objects in the scene. To address the difficulty of predicting depth using only pictorial clue, we propose a novel perspective-aware convolutional layer that captures long-range dependencies in images. By enforcing convolutional kernels to extract features along the depth axis of every image pixel, we incorporates perspective information into network architecture. We integrate our perspective-aware convolutional layer into a 3D object detector and demonstrate improved performance on the KITTI3D dataset, achieving a 23.9\% average precision in the easy benchmark. These results underscore the importance of modeling scene clues for accurate depth inference and highlight the benefits of incorporating scene structure in network design. Our perspective-aware convolutional layer has the potential to enhance object detection accuracy by providing more precise and context-aware feature extraction.
The increasing trend in adopting electric vehicles (EVs) will significantly impact the residential electricity demand, which results in an increased risk of transformer overload in the distribution grid. To mitigate such risks, there are urgent needs to develop effective EV charging controllers. Currently, the majority of the EV charge controllers are based on a centralized approach for managing individual EVs or a group of EVs. In this paper, we introduce a decentralized Multi-agent Reinforcement Learning (MARL) charging framework that prioritizes the preservation of privacy for EV owners. We employ the Centralized Training Decentralized Execution-Deep Deterministic Policy Gradient (CTDE-DDPG) scheme, which provides valuable information to users during training while maintaining privacy during execution. Our results demonstrate that the CTDE framework improves the performance of the charging network by reducing the network costs. Moreover, we show that the Peak-to-Average Ratio (PAR) of the total demand is reduced, which, in turn, reduces the risk of transformer overload during the peak hours.
The Information Bottleneck (IB) is a method of lossy compression. Its rate-distortion (RD) curve describes the fundamental tradeoff between input compression and the preservation of relevant information. However, it conceals the underlying dynamics of optimal input encodings. We argue that these typically follow a piecewise smooth trajectory as the input information is being compressed, as recently shown in RD. These smooth dynamics are interrupted when an optimal encoding changes qualitatively, at a bifurcation. By leveraging the IB's intimate relations with RD, sub-optimal solutions can be seen to collide or exchange optimality there. Despite the acceptance of the IB and its applications, there are surprisingly few techniques to solve it numerically, even for finite problems whose distribution is known. We derive anew the IB's first-order Ordinary Differential Equation, which describes the dynamics underlying its optimal tradeoff curve. To exploit these dynamics, one needs not only to detect IB bifurcations but also to identify their type in order to handle them accordingly. Rather than approaching the optimal IB curve from sub-optimal directions, the latter allows us to follow a solution's trajectory along the optimal curve, under mild assumptions. Thereby, translating an understanding of IB bifurcations into a surprisingly accurate numerical algorithm.