---
title: 解釈・制御可能なMulti-Interest推薦モデルの提案
tags:  #国内会議  
author: [Okamoto Lab. (The Univ. of Electro-Communications)](https://image.docswell.com/user/okmt_lab)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/LE1Y6Z9V7G.jpg?width=480
description: 小西 渓士郎, 岡本 一志, 軽部 幸起, 原田 慧, 柴田 淳司: 解釈・制御可能なMulti-Interest推薦モデルの提案, 第40回人工知能学会全国大会, 2026.6, 群馬県高崎市.
published: June 08, 26
canonical: https://image.docswell.com/s/okmt_lab/58ND8Y-2026-06-08-jsai2026-konishi
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/LE1Y6Z9V7G.jpg)

Multi-Interest
2026.06.08
2026
1 / 21


# Page. 2

![Page Image](https://bcdn.docswell.com/page/GEWGW9Q3J2.jpg)

2026.06.08
2026
2 / 21


# Page. 3

![Page Image](https://bcdn.docswell.com/page/47ZL59WGJ3.jpg)

1.
2.
Multi-Interest
2026.06.08
2026
3 / 21


# Page. 4

![Page Image](https://bcdn.docswell.com/page/YJ6W9KGQJV.jpg)

Multi-Interest
2026.06.08
2026
4 / 21


# Page. 5

![Page Image](https://bcdn.docswell.com/page/GJ5MNPV2J4.jpg)

Multi-Interest
MIND [Li+, 2019]
Dynamic Routing
×
×
ComiRec-SA [Cen+, 2020]
Attention
×
×
TimiRec [Wang+, 2022]
Attention
×
×
Attention
2026.06.08
2026
5 / 21


# Page. 6

![Page Image](https://bcdn.docswell.com/page/9E2956317R.jpg)

→
RQ.1:
RQ.2:
2026.06.08
2026
6 / 21


# Page. 7

![Page Image](https://bcdn.docswell.com/page/D7Y4K914EM.jpg)

[1/4]
2026.06.08
2026
7 / 21


# Page. 8

![Page Image](https://bcdn.docswell.com/page/VENYRL26J8.jpg)

[2/4]
MLP
2026.06.08
2026
8 / 21


# Page. 9

![Page Image](https://bcdn.docswell.com/page/Y79PM41RE3.jpg)

Task1
MLP
[3/4]
α
α
Sampled Softmax Cross-Entropy Loss
2026.06.08
2026
9 / 21


# Page. 10

![Page Image](https://bcdn.docswell.com/page/G78DLQ4G7D.jpg)

Task2
[4/4]
Load Balancing Bias
Binary Cross Entropy
2026.06.08
2026
10 / 21


# Page. 11

![Page Image](https://bcdn.docswell.com/page/L7LMLX6XJR.jpg)

2026.06.08
2026
11 / 21


# Page. 12

![Page Image](https://bcdn.docswell.com/page/4EMYML53EW.jpg)

MovieLens 1M
EC
Yelp
MovieLens 1M
Yelp
6,040
69,912
3,706
14,480
1,000,209 713,662
19
2026.06.08
2026
1026
12 / 21


# Page. 13

![Page Image](https://bcdn.docswell.com/page/PER9VK3RJ9.jpg)

Hit@
NDCG@
TargetRate@
2026.06.08
2026
13 / 21


# Page. 14

![Page Image](https://bcdn.docswell.com/page/P7XQZL4YEX.jpg)

GRU4Rec [Hidasi+, 2015]
Single Interest
RNN
SASRec[Kang+, 2018]
Single Interest
Transformer
BERT4Rec[Sun+, 2019]
Single Interest
MIND [Li+, 2019]
Multi-Interest
ComiRec-SA[Cen+, 2020]
Multi-Interest
2026.06.08
2026
14 / 21


# Page. 15

![Page Image](https://bcdn.docswell.com/page/37K98LZ47D.jpg)

MovieLens 1M
Metric
RQ.1
[1/2]
GRU4Rec BERT4Rec SASRec MIND ComiRec-SA
HIT@1
0.220
0.181
0.217
0.141
0.169
0.178
HIT@5
0.464
0.434
0.459
0.400
0.388
0.465
HIT@10
0.607
0.563
0.580
0.558
0.562
0.601
NDCG@5
0.346
0.315
0.344
0.272
0.281
0.327
NDCG@10
0.392
0.357
0.383
0.322
0.337
0.371
2026.06.08
2026
15 / 21


# Page. 16

![Page Image](https://bcdn.docswell.com/page/LJ3W23DDJ5.jpg)

Yelp RQ.1
Metric
[2/2]
GRU4Rec BERT4Rec SASRec MIND ComiRec-SA
HIT@1
0.210
0.154
0.256
0.164
0.200
0.227
HIT@5
0.487
0.349
0.492
0.391
0.420
0.479
HIT@10
0.595
0.518
0.646
0.530
0.544
0.613
NDCG@5
0.354
0.249
0.381
0.280
0.313
0.358
NDCG@10
0.390
0.303
0.433
0.325
0.352
0.402
Yelp
MovieLens 1M
RQ.1
2026.06.08
2026
16 / 21


# Page. 17

![Page Image](https://bcdn.docswell.com/page/8JDKZ4P2EG.jpg)

RQ.2
α
95%
MovieLens 1M
2026.06.08
1.47
2026
Yelp
1.73
RQ.2
17 / 21


# Page. 18

![Page Image](https://bcdn.docswell.com/page/VEPKDMNL78.jpg)

2026.06.08
2026
18 / 21


# Page. 19

![Page Image](https://bcdn.docswell.com/page/27VV19K67Q.jpg)

Multi-Interest
RQ.1
MovieLens
2026.06.08
1.47
2026
Yelp
1.73
RQ.2
19 / 21


# Page. 20

![Page Image](https://bcdn.docswell.com/page/5JGL2ZQ27L.jpg)

[Cen+, 2020]Y. Cen, J. Zhang, X. Zou, C. Zhou, H. Yang, J. Tang, ``Controllable Multi-Interest Framework for
Recommendation", in Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2942–2951, 2020
[Li+, 2019] C. Li, Z. Liu, M. Wu, Y. Xi, H. Zhao, P. Huang, G. Kang, Q. Chen, W. Li, D. Lun Lee, ``Multi-interest
network with dynamic routing for recommendation at Tmall,'' in Proc. 28th ACM Int. Conf. Inf. Knowl. Manag.,
2615--2623, 2019.
[Wang+, 2022] C. Wang, Z. Wang, Y. Liu, Y. Ge, W. Ma, M. Zhang, Y. Liu, J. Feng, C. Deng, and S. MaA, ``Target
Interest Distillation for Multi-Interest Recommendation,'' in Proc. 31st ACM Int. Conf. Inf. Knowl. Manag., 2007-2016, 2022.
[Li+, 2022] J. Li, J. Zhu, Q. Bi, G. Cai, L. Shang, Z. Dong, X. Jiang, and Q. Liu, ``MINER: Multi-Interest Matching
Network for News Recommendation,'' in Find. Assoc. for Comput. Lnguist.: ACL 2022, 343--352, 2022.
[Kouki+, 2019] P. Kouki, J. Schaffer, J. Pujara, J. O'Donovan, L.Getoor, ``Personalized explanations for hybrid
recommender systems,'' in Proc. 24th Int. Conf. Intell. User Interfaces, 379--390, 2019.
[Hidasi+, 2015] B. Hidasi, A. Karatzoglou, L. Baltrunas, D. Tikk, ``Session-based recommendations with
recurrent neural networks,'' arXiv preprint, arXiv:1511.06939, 2015.
2026.06.08
2026
20 / 21


# Page. 21

![Page Image](https://bcdn.docswell.com/page/47QYPLK9EP.jpg)

[Sun+, 2019] F. Sun, J. Liu, J. Wu, C. Pei, X. Lin, W. Ou, P. Jiang ``BERT4Rec: Sequential recommendation with
bidirectional encoder representations from Transformer,'' in Proc. 28th ACM Int. Conf. Inf. Know. Manag., 1441-1450, 2019.
[Kang+, 2018] W. Kang, J. McAuley, ``Self-attentive sequential recommendation,'' arXiv preprint,
arXiv:1808.09781, 2018.
2026.06.08
2026
21 / 21