Discrete Factorization Machines for Fast Feature-based Recommendation
Authors: Han Liu, Xiangnan He, Fuli Feng, Liqiang Nie, Rui Liu, Hanwang Zhang
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through extensive experiments on two realworld datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss. |
| Researcher Affiliation | Academia | Han Liu1, Xiangnan He2, Fuli Feng2, Liqiang Nie1 , Rui Liu3, Hanwang Zhang4 1School of Computer Science and Technology, Shandong University 2School of Computing, National University of Singapore 3University of Electronic Science and Technology of China 4School of Computer Science and Engineering, Nanyang Technological University |
| Pseudocode | No | The paper describes mathematical formulations and optimization steps but does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | Yes | Codes are available: https://github.com/hanliu95/DFM |
| Open Datasets | Yes | Datasets. We experiment on two publicly available datasets with explicit feedbacks from different real-world websites: Yelp and Amazon. Note that we assume each user has only one rating for an item and average the scores if an item has multiple ratings from the same user. a) Yelp. This dataset [Lian et al., 2017] originally contains 409,117 users, 85,539 items (points of interest on Yelp such as restaurants and hotels), and 2,685,066 ratings with integer scores ranging from 1 to 5. Besides, each item has a set of textual reviews posted by the users. |
| Dataset Splits | No | We first randomly split the ratings from each user into training (50%) and testing (50%). No explicit mention of a separate validation split was found. |
| Hardware Specification | Yes | It is worth mentioning that we conduct all the experiments on a computer equipped with an Intel(R) Core(TM) i7-7700k 4 cores CPU at 4.20GHZ, 32GB RAM, and 64-bit Windows 7 operating system. |
| Software Dependencies | Yes | We implement our proposed DFM method using Matlab2 and compare it with its real-valued version and stateof-the-art binarized methods for Collaborative Filtering: [...] As lib FM is implemented based on C++, we re-implement the testing algorithm of DFM with C++ and compile it with the same C++ compiler (gcc-4.9.3) for a fair comparison. |
| Experiment Setup | Yes | For lib FM, we test the l2 regularization on feature embeddings V of {10 i|i = 4, 3, 2, 1, 0, 1, 2}. Under the same range, we test the de-correlation constraint (i.e., β in Eq. (3)) of DFM. Besides, we test the code length in the range of [8, 16, 32, 64]. |