arXiv subjects

Cheng Ling

Publications and source records attributed to Cheng Ling.

6 recordsLinked to original sources

arXiv2024

Generative Recommender with End-to-End Learnable Item Tokenization

Generative recommendation systems have gained increasing attention as an innovative approach that directly generates item identifiers for recommendation tasks. Despite their potential, a major challenge is the effective construction of item identifiers that align well with recommender systems. Current approaches often treat item tokenization and generative recommendation training as separate processes, which can lead to suboptimal performance. To overcome this issue, we introduce ETEGRec, a novel End-To-End Generative Recommender that unifies item tokenization and generative recommendation into a cohesive framework. Built on a dual encoder-decoder architecture, ETEGRec consists of an item tokenizer and a generative recommender. To enable synergistic interaction between these components, we propose a recommendation-oriented alignment strategy, which includes two key optimization objectives: sequence-item alignment and preference-semantic alignment. These objectives tightly couple the learning processes of the item tokenizer and the generative recommender, fostering mutual enhancement. Additionally, we develop an alternating optimization technique to ensure stable and efficient end-to-end training of the entire framework. Extensive experiments demonstrate the superior performance of our approach compared to traditional sequential recommendation models and existing generative recommendation baselines. Our code is available at https://github.com/RUCAIBox/ETEGRec.

cs.IR↗

arXiv2024

Modeling User Fatigue for Sequential Recommendation

Recommender systems filter out information that meets user interests. However, users may be tired of the recommendations that are too similar to the content they have been exposed to in a short historical period, which is the so-called user fatigue. Despite the significance for a better user experience, user fatigue is seldom explored by existing recommenders. In fact, there are three main challenges to be addressed for modeling user fatigue, including what features support it, how it influences user interests, and how its explicit signals are obtained. In this paper, we propose to model user Fatigue in interest learning for sequential Recommendations (FRec). To address the first challenge, based on a multi-interest framework, we connect the target item with historical items and construct an interest-aware similarity matrix as features to support fatigue modeling. Regarding the second challenge, built upon feature cross, we propose a fatigue-enhanced multi-interest fusion to capture long-term interest. In addition, we develop a fatigue-gated recurrent unit for short-term interest learning, with temporal fatigue representations as important inputs for constructing update and reset gates. For the last challenge, we propose a novel sequence augmentation to obtain explicit fatigue signals for contrastive learning. We conduct extensive experiments on real-world datasets, including two public datasets and one large-scale industrial dataset. Experimental results show that FRec can improve AUC and GAUC up to 0.026 and 0.019 compared with state-of-the-art models, respectively. Moreover, large-scale online experiments demonstrate the effectiveness of FRec for fatigue reduction. Our codes are released at https://github.com/tsinghua-fib-lab/SIGIR24-FRec.

cs.IR↗

arXiv2024

Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation

Nowadays, reading or writing comments on captivating videos has emerged as a critical part of the viewing experience on online video platforms. However, existing recommender systems primarily focus on users' interaction behaviors with videos, neglecting comment content and interaction in user preference modeling. In this paper, we propose a novel recommendation approach called LSVCR that utilizes user interaction histories with both videos and comments to jointly perform personalized video and comment recommendation. Specifically, our approach comprises two key components: sequential recommendation (SR) model and supplemental large language model (LLM) recommender. The SR model functions as the primary recommendation backbone (retained in deployment) of our method for efficient user preference modeling. Concurrently, we employ a LLM as the supplemental recommender (discarded in deployment) to better capture underlying user preferences derived from heterogeneous interaction behaviors. In order to integrate the strengths of the SR model and the supplemental LLM recommender, we introduce a two-stage training paradigm. The first stage, personalized preference alignment, aims to align the preference representations from both components, thereby enhancing the semantics of the SR model. The second stage, recommendation-oriented fine-tuning, involves fine-tuning the alignment-enhanced SR model according to specific objectives. Extensive experiments in both video and comment recommendation tasks demonstrate the effectiveness of LSVCR. Moreover, online A/B testing on KuaiShou platform verifies the practical benefits of our approach. In particular, we attain a cumulative gain of 4.13% in comment watch time.

cs.IR↗

arXiv2011

Electrical Transport Properties of Graphene Nanoribbons Produced from Sonicating Graphite in Solution

A simple one-stage solution-based method was developed to produce graphene nanoribbons by sonicating graphite powder in organic solutions with polymer surfactant. The graphene nanoribbons were deposited on silicon substrate, and characterized by Raman spectroscopy and atomic force microscopy. Single-layer and few-layer graphene nanoribbons with a width ranging from sub-10 nm to tens of nm and length ranging from hundreds of nm to 1 {\mu}m were routinely observed. Electrical transport properties of individual graphene nanoribbons were measured in both the back-gate and polymer-electrolyte top-gate configurations. The mobility of the graphene nanoribbons was found to be over an order of magnitude higher when measured in the latter than in the former configuration (without the polymer electrolyte), which can be attributed to the screening of the charged impurities by the counter-ions in the polymer electrolyte. This finding suggests that the charge transport in these solution-produced graphene nanoribbons is largely limited by charged impurity scattering.

cond-mat.mtrl-sci↗

arXiv2011

Approaching the Intrinsic Bandgap in Suspended High-Mobility Graphene Nanoribbons

We report electrical transport measurements on a suspended ultra-low-disorder graphene nanoribbon(GNR) with nearly atomically smooth edges that reveal a high mobility exceeding 3000 cm2 V-1 s-1 and an intrinsic band gap. The experimentally derived bandgap is in quantitative agreement with the results of our electronic-structure calculations on chiral GNRs with comparable width taking into account the electron-electron interactions, indicating that the origin of the bandgap in non-armchair GNRs is partially due to the magnetic zigzag edges.

cond-mat.mes-hall↗

arXiv2011

Room-Temperature High On/Off Ratio in Suspended Graphene Nanoribbon Field Effect Transistors

We have fabricated suspended few layer (1-3 layers) graphene nanoribbon field effect transistors from unzipped multiwall carbon nanotubes. Electrical transport measurements show that current-annealing effectively removes the impurities on the suspended graphene nanoribbons, uncovering the intrinsic ambipolar transfer characteristic of graphene. Further increasing the annealing current creates a narrow constriction in the ribbon, leading to the formation of a large band-gap and subsequent high on/off ratio (which can exceed 104). Such fabricated devices are thermally and mechanically stable: repeated thermal cycling has little effect on their electrical properties. This work shows for the first time that ambipolar field effect characteristics and high on/off ratios at room temperature can be achieved in relatively wide graphene nanoribbon (15 nm ~50 nm) by controlled current annealing.

cond-mat.mes-hall↗